A challenge to Frege on assertion
This grows out of the thread on References for discussion of truth as predication. That thread was inspired by some questions raised by Irad Kimhi in Thinking and Being. Ive realized that its hard to get clear on what those questions are unless youve read Kimhis book, which is a big ask.
So instead, I thought Id pick, one by one, some Kimhi-inspired challenges to Frege and describe them in my own words, without using Kimhis sometimes confusing terminology, trying as best I can to link them to questions that are already familiar to many philosophers. Thus, Ill be less concerned with what Kimhi says (which can be difficult to make out) and more concerned with the nature of the challenge, which I think can be raised regardless of whether youve read Kimhi or agree with him.
This OP offers the first one, which concerns assertion.
Frege wrote that his most important contribution to philosophy was dissociating the assertoric force from the predicate. We make statements in predicate logic that are blind or innocent as regards to truth-in-the-world. Frege says, A proposition may be thought, and again it may be true; let us never confuse the two things. (Foundations of Arithmetic) We can understand The grass is green without knowing whether or not it is true, and whether we should affirm or deny it.
The consequences of this, according to Frege, are probably familiar to most of us, and I wont repeat them all. Ill just point out that, in Fregean logic, the predicate does all the work, so to speak. The subject (or argument, in Freges terminology) is what Julian Roberts in The Logic of Reflection calls an empty center. Roberts goes on, And the ?object which fills that subject position, accordingly, is not a collection of attributes. It is a ?thing only to the extent that the function makes it into one. (cf. To be is to be the value of a bound variable)
So questions of existence, like questions of truth, are at one remove. All that logic can do is show us the grammar of predication, along with rules of inference that will hold when a subject/argument is added to the functional, predicative formula. Frege called this saturating or fulfilling the function, since a predicate without a subject cant receive a truth-value. As far as truth goes, Frege introduced the idea of the judgment- or assertion-stroke, which would mark a proposition as a true thought. (I cant resist quoting, parenthetically, another passage from Roberts that I love: There is, ultimately, something rather raffish about a function; it wanders the world, hoping to connect, but may well never succeed. There is nothing in the function that establishes it as a part of reality.)
But suppose we decide to question the absolute dissociation of force from sense. What grounds might we have to do this?
There seem to be two steps involved in Freges conclusion that assertoric force is necessarily dissociated from predication. The first is the claim that logical or functional sense is a feature of repeatable occurrences of p. p retains its identity (and sense) no matter where and how it appears.* If I state ?p and then ?If p then q, the only thing that entitles me to conclude ?q is the fact that ?p means the same thing in each of its occurrences. Nothing more is required for me to recognize these repetitions of ?p other than their logical identity. In contrast, an actual occurrence (and Ill say more about what that means) of ?p can have assertoric force. But regardless of whether ?p is asserted or unasserted, I can recognize ?p as the same proposition in each occurrence.
Thats Step 1. Step 2 is the potentially controversial one: Therefore, a proposition cannot contain assertoric force as part of its logical structure. If it could, then we would no longer be able to recognize repetitions of ?p as the same: Some would be asserted, some would not, and that would be internal to the structure. There would be some sort of deep or semantic assertion built into this Uber-proposition. Assertion would be functional in the Fregean sense. And since the self-identity of ?p is critical to the entire logical apparatus, we know this cannot be. Besides, it just stands to reason, doesnt it? I can use p and q and r and . . . z as much as I want, I can ascribe beliefs about them, or present them as part of hypothetical premises. (They work just fine in compound propositions, in other words.) None of this counts as actually judging p true.
Sounds simple. But does it really cover all that we mean by asserting p? That question is the basis for this challenge to Frege.
At this point I have to move into I dont know territory. Im not sure if the argument which Im about to spell out is a successful one, and at the end of this OP Ill invite opinions pro or con. Right now Ill just make the best case I can.
Lets go back to the judgment-stroke. Its composed of a horizontal and a vertical line. The horizontal line marks assertability, the vertical line marks actual assertion or being true. The horizontal line is part of the functional composition of p, and as we know, the vertical assertion line is not. So this gives us a way of talking about showing or displaying or manifesting assertability without adding the vertical line and claiming that we are dealing with an actual occurrence of assertion. So far this is just another way of revealing the dissociation of sense and force.
But arent there two different ways in which occurrence of an assertion can be understood? An assertion can be displayed, perhaps as an integral part of a proposition, without being an actual assertion. Or better, lets stipulate that to display force is not the same thing as to assert. Lets add a nuance to the vocabulary so that we can now claim to be able to discover the force of ?p without actually asserting it.
How do we do this? ?The grass is green displays the assertion, and at the same time, under the right circumstances, makes it. ?The grass is green is not neutral as to force; it is not the making of the assertion that would give it its force. What it displays is a positive predication, which can be affirmed or denied. In contrast, ?If the grass is green, then Im happy displays the assertion ?The grass is green but doesnt actually make it.
This is somewhat easier to see with denial. ?It is not the case that the grass is green displays the assertion ?The grass is green while not making it. ?It is not the case that the grass is green, just like ?The grass is green, is not neutral as to force, and in this instance we know that it cant be actual assertion which gives it its force, because in this case there is no assertion.
Frege wants simple or actual occurrences of ?p to be analyzable in the same way as hypothetical occurrences in ?if p then q. He has to say this based on his understanding of the centrality of repeatability and the self-identity of ?p, discussed above. But what actually warrants this? Surely we can look at a statement like ?The grass is green as occurring in other contexts besides logical arguments, and when we do, we discover that assertoric force is by no means absent. In fact, assertion as true is the reasonable default assumption in most everyday examples of stated propositions. Ill allow myself one quote from Kimhi: He says that Frege goes wrong by assuming that the repeated occurrence of a proposition . . . lies within the context of valid arguments. All actual occurrences of ?p are treated the same way as ?p is treated in modus ponens. Again, what is the warrant for this?
A natural response is to say, The ?warrant is that it enables us to construct a logical system thats clear and manipulable and can answer the questions we want answered. Whats the alternative way of understanding the language of predication and assertion? Will it give us the same desirable results? Can there really be a ?logic of this that isnt predicate logic? And thats what Kimhis book is about.
But for now, what do you all think? Have I succeeded in raising a genuine challenge to Frege, or does the Fregean have an obvious counter-argument?
*This shouldnt be read as a seeming contradiction to the Fregean context principle, which will come up in a different Kimhi-inspired challenge.
Comments (757)
Thanks for the excellent OP. I don't have access to Kimhi, but have read a few reviews and other articles. Instead of addressing Kimhi directly, I'll go over my own understanding of the Fregean account and subsequent developments. You are probably already familiar with what follows, so think of it as my rehearsing the arguments that got us to the sort of accounts being critiqued.
First we should be clear about the nature of illocutionary force. Taking your example, "The grass is green", we can imagine various situations in which this utterance does quite different things. Imagine a meeting in which a landscape gardener is presenting their plan for the forecourt of a new build. One of those present is unclear as to which parts of the drawing are cement and which are lawn, and asks "The grass is green?". The designer replies, "Yes. The grass is green." There follows a conversation about how best to represent the lawn after which the manager gives the instruction "The grass is green!". Here we have the same sentence being used in three quite different ways - as a question, as a statement and as an instruction. The same sentence is being used with three differing illocutionary forces.
Notice that the content of the sentence is much the same - in all three cases it is about the colour of the grass. Now truth-value is usually, but not always, associated with statements. So the statement "The grass is green" is the sort of thing that might be true or false, but the instruction "The grass is green!", meaning something like "You will colour the grass green in your diagram!", is neither true nor false. But we might answer the question "The grass is green?" with "Yes", or with "True". This has led to the idea that there is a propositional content that is the same for all three, which sets out the reference and the predicate in each case, and takes differing forces depending on the use to which the sentence is put. So the question, statement and instruction can be seen as all sharing the same propositional content but differing in illocutionary force.
We might right the propositional content in subject-predicate form: Green(grass). This is usually considered not to have an illocutionary force, but just to be setting out what the sentences are about. A big advantage of this is that it can be treated extensionally - as concerning only the things that it denotes. It's generally taken as read that in logic we are dealing not with sentences that include a full illocutionary content, that we set this aside for the purposes of examining in detail the propositional content.
What's salient here is that making an assertion is as much part of the illocutionary force of an utterance as is asking a question or giving an instruction.One might see this as setting aside the "assertoric" aspect of the sentence in order to deal with other aspects of its structure - what it is about.
The rather large advantage of this is the structure of formal logic. This is no small thing, since this provides the foundations of mathematics and computer science. Treating sentences in this way has undeniable advantages.
This is a somewhat seperate issue from the sense-reference distinction. I think it may be helpful for us to acknowledge that illocutionary force differs from sense and reference. I'll prehaps come back to sense and reference in another post.
For now, @J, do we agree roughly on the account I've given above?
Oh all right.
First, it's not clear to me what your argument is.
Quoting J
That doesn't sound like an argument; it sounds like you (ahem) asserting your proposed conclusion. Even so, the natural rejoinder is that the circumstances in question involve someone, you know, asserting it.
Quoting J
And again, the natural rejoinder is that the context of which you speak includes someone asserting this. You haven't actually shown why we ought to think force is part of logical form. Have you?
Second, it's a particular kind of argument you want to make: not so much that Frege is wrong or something, but that some other framework might prove more useful, or more perspicacious, might make easier to see something that Frege's framework makes hard to see, that sort of thing.
An Indirect Realist's challenge to Frege's disassociation of sense from reference
For Frege, a proposition such as "this grass is green" or "this unicorn is intelligent" have a sense and a reference, such that sense and reference can be disassociated. Kimhi is saying that sense and reference cannot be disassociated because they have a unity.
For the Indirect Realist, the colour red doesn't exist in any world outside the mind, but only exists as a concept within the mind. Similarly, other objects such as apples, unicorns and grass don't exist in any world outside the mind either, but only exist as concepts within the mind.
Consider the Schema "this grass is green" in language is true IFF this grass is green in the world. For the Indirect Realist, the world of apples, grass and unicorns exist in the mind as concepts. Therefore, the schema would become: "this grass is green" in language is true IFF the grass is green exists in the mind as a thought.
For the Indirect Realist, the sense of a proposition exists in language in the mind as a thought, and the reference of a proposition exists in the world, which also exists in the mind as a thought.
For the Indirect Realist, sense and reference are unified as both exist in the mind.
Khimi and Wittgenstein
Wittgenstein proposed that language was thought.
For example: Tractatus 5.6 "The limits of my language means the limits of my world."
The sense of a proposition is in language and the reference of a proposition is in the world.
But we only know language through our thoughts, and we only know the world through our thoughts.
It follows that we only know the sense of a proposition though our thoughts and we only know the reference of a proposition through our thoughts.
If Wittgenstein is correct in that language is thought, the sense and reference of a proposion are unified within thought.
Khimi does support Wittgenstein over Frege. From the Notre Dame review of Thinking and Being:
If Khimi also supports Wittgenstein's idea that language is thought, then for Khimi, this would be a mechanism by which sense and reference are unified, in being unified within thought.
Quoting Srap Tasmaner
Fun thread.
I bolded "a" in the quote since, if I read it right, you're construing Frege's view that every proposition cannot contain assertoric force as part of its logical structure. There's several degrees of freedom in that sentence.
1 ) What counts as a proposition.
2 ) What counts as a logical structure.
3 ) What counts as an integral part of a proposition.
4 ) I suppose whether you read "logical" as a subset of a "linguistic" or "sentential" structure or a more broad "performative" and "pragmatic" one.
But if the claim is that Frege's view applies to every proposition, all you'd need is one example of a proposition whose logical structure wasn't totally covered by Frege's account of logical structure.
I'd posit that Moore's Paradox's has an assertion as an integral part of a sentence, and highlights a kind of contradiction (underlying logical structure?) which isn't representable in normal flavours of sentential logic.
The sentence "It's raining but I believe that it's not raining" is weird. It can be true, and it will be true (extensionally) whenever it is raining but the utterer believes it is not raining. For example, if their curtains are closed and they just looked at a false weather forecast for their area, that is a plausible belief I could have.
What makes it strange is that writing or saying the sentence counts as an assertion, so the clause "It's raining" doesn't just state that it's raining, it imbues a state of awareness of the fact that it is raining to the speaker, which engenders us to ascribe that state of awareness to the speaker. Whereas the latter clause "but I believe it's not raining" cancels the ascription of the state of awareness to the speaker as well as ascribing opposed content to the clause "It's raining" to the speaker's state of awareness.
That sets up the statement as... weird... since it contains a performative contradiction of some kind, but it isn't a strict one. One would expect that the speaker believes that it is raining if they have indeed asserted it, and will do so on the basis of having inferred that it is raining somehow based on contact with the rain. Nevertheless the statement entails no logical contradiction. Though it could be analysed as entailing a contradiction when the utterance of the statement is treated as a speech act. However the sensible interpretation of the speech act is not what would make it true in virtue of its extension, as demonstrated with the example of not seeing the weather and seeing an inaccurate weather forecast.
With reference to the above list of degrees of freedom:
1 ) I'm counting the conjunct ((It is raining) and (I believe it is not raining)) as the proposition associated with the sentence.
2 ) I'm asserting that an analysis of the "logical structure" of the sentence should include an explanation of why it appears to be self contradictory, even though extensionally it is not self contradictory.
3 ) I'm asserting that whatever the answer is in ( 2 ), it should be seen as an integral part of the sentence, since the sentence strikes every competent interpreter as weird.
4 ) I think this engenders a broader, less formal, sense of logic as expectable behaviour and interpretation which should be considered as part of the analysis of propositions.
I do think it's possible to resolutely deny that the logical structure in 2 has anything to do with the logical structure of propositions, or to say that the contradiction is well explained by the common belief in the proposition that "if X asserts Y then X believes Y" as a default operation of language. But the post is long enough so I'll only offer detailed rejoinders to those things if asked to.
In a word, yes. Assertion as displaying illocutionary force is part of the "standard" picture. And the challenge here is about the nature of propositional content (intension vs. extension), just as you say.
The Indirect Realist challenge is interesting, but I'll leave it alone as my own metaphysics is much closer to direct realism.
Fun, for sure. Some go clubbing and do X, we worry about 'x'. :razz: (Some do both, no doubt.)
Quoting fdrake
But does it? Were you asserting it, just now when you wrote the sentence? I know you clarify this later, but in this OP Im claiming that much depends on exactly what we mean by assertion so Im being finicky here.
I like your degrees of freedom analysis a lot. (2) and (3) get to the heart of the matter how can a strictly Fregean understanding of propositions give us any insight into whats wrong with a logical structure that is not extensionally self-contradictory? The challenge Im offering concurs with (3) that an explanation of the self-contradiction must be part of our logical analysis of the sentence. Im trying to keep Kimhi mostly out of this, but will just note that (3) is absolutely essential to his revisionist philosophy of logic.
I also agree that its possible simply to deny (2) isnt that what Frege (and probably Donald Davidson) do? Id be interested, though, to hear more about what a default operation in language is, and how it might answer the problem.
Quoting Srap Tasmaner
Right, my argument is more that Frege fails to provide a way of dealing with certain features of assertion and its connection with thought or consciousness, not that hes wrong per se in what he does countenance as part of logic. I guess thats why I think of it as a challenge to Frege rather than a refutation.
Quoting Srap Tasmaner
Here, Im hoping to get the readers agreement on a point of observation namely that theres nothing incoherent about trying to draw a distinction between force and assertion. The challenging part, perhaps, lies not in the second use of ?The grass is green -- I quite agree that under these right circumstances someone is indeed asserting it but the first. Were not used to thinking that p can display an assertion without making it. The Fregean picture is more like p would or could be an assertion under the right illocutionary circumstances (thanks, @Banno), but unless its actually being asserted, p has nothing in the way of force. Thats what Im challenging. The argument for that is in the OP and Im sure it can be improved, so please feel free to sharpen it in the process of disagreeing, if you do.
The closest Frege's system can get to modeling something like this is to say, "There exists something which is both grass and green." Fregian logic has an especially hard time with individuals since it is built for concepts or classes. Given that the statement is not Fregian in the first place, it raises a whole host of issues.
Quoting J
All the objections to Frege's logic that I have seen are metalogical objections, and yours is no exception. says that there is no (counter)-argument being offered, and this is true at least insofar as there is no counter-argument which adopts Fregian presuppositions. What is being questioned is the presupposition.
So how does one offer an argument against logical presuppositions? The most obvious way is to argue that the presupposition fails to capture some real aspect of natural logic or natural language, and by claiming that natural propositions possess a variety of assertoric force that Frege's logic lacks, this is what you are doing. Yet this is where a point like Novák's becomes so important, for logicians like Russell, Frege, Quine, et al., presuppose that natural language is flawed and must be corrected by logic. This moots your point. Further, Quine will set the stage for a "pragmaticizing" of logic, which destroys the idea of ontologically superior logics at its root:
Quoting Luká Novák, Can We Speak About That Which Is Not?, 166-7
It is a question of what you're up against.
Quoting J
Kimhi's approach strikes me as a attempt to kill Frege by a kind of "death by a thousand cuts." Whether or not this works, it will not be convincing to entrenched Fregians, as it requires a willingness to abandon Fregian presuppositions for the sake of argument. Beyond that, with each small cut Fregians will presumably respond, "It's such a minor issue - who really cares?" It seems to me that your Sider paperwhich never in fact received a hearing within your earlier threadwas much more "punchy" and effective as directed against Fregians. Kimhi's book seems to be directed towards those who are predisposed to question the sovereignty of Fregianism, rather than committed Fregians themselves.
And finally, this argument about assertoric force is an argument where I can see both sides, and I don't know that the clarity and merits of the OP are sufficient to overcome the weight and presuppositions of the opposing side. For example, on the one hand we have some obscure gesturing towards real problems or at least wrinkles with the Fregian presupposition. What do we have in favor of the Fregian presupposition? Something like this, which is both clear and strong:
* In fact all logic seems to require a distinction between sense and assertoric force, and therefore if the conclusion of your argument is that these cannot in any way be separated then logic itself would appear to be doomed. The subtlety of Kimhi's argumentation results in a subtle conclusion. There is the danger here of throwing out the baby with the bathwater.
This is a precise question, thank you.
"Does it?" and "were you asserting it?" seem to be a false dichotomy to me. There is another possibility.
Reading the sentence "It is raining but I believe it is not raining", as a competent interpreter of English, produces the uncanny effect. I don't believe I, as the writer of the sentence, was asserting it. Rather I believe the sentence "It is raining but I believe it is not raining" suggests, as part of a normal interpretation of it, that the ambiguous referent "I" in the sentence is ascribing an ambiguous/ambivalent/weird state of being to themselves through the opposition between the clauses. Whether I write the sentence or not is irrelevant, I suppose, what matters is that the proposed speaker conjured into being by "I" in the sentence ascribes the unusual state to themselves.
So in the context of the sentence, it would count as an assertion on the part of whoever "I" refers to. Even if that reference isn't fixed. The odd part of what makes it count as an assertion seems to be "I" conjures an asserter. Which isn't the person who writes the sentence (me), it's the person in the sentence.
The simple argument from Geach in Kimhi's book is that p has assertoric force in (2) but not in (1):
What you seem to be saying is that if we let p = "The grass is green", then it will have assertoric force in (1). Is that really true?
The force of a locution is context-dependent, but doesn't formal logic always need to nail down and simplify this context-dependency? If the argument of the OP is that natural language is a more powerful or complete logical tool than formal logic, then I would agree. But is there any formal logic that will really be able to dodge this bullet and provide the same cornucopia of locutionary flavors that natural language possesses?
Quoting Leontiskos
It looked to me like the argument form here was something like this:
A: Fs are not Gs.
B: But in a way they are.
That's a disagreement, I guess, but I wouldn't call it an argument. And yes maybe it's a disagreement over presuppositions, but what's the argument for dropping the presupposition?
@fdrake brought up Moore's paradox, which did immediately leap to mind, but --
What's the plan here? What do we think we're doing?
What I want to ask specifically is this: are we to proceed as if there is a fact of the matter here? Do we expect to discover that force is or is not part of a sentence's logical form, as we might discover, I don't know, humans reached North America tens of thousands of years earlier than we thought?
If we find that there are multiple frameworks for analyzing the symbol systems of humans and their utterances, and each is useful for particular purposes, we might consider the possibility that the speakers of a language also have at their disposal multiple frameworks for thinking about the utterances of their fellows. The distinction between between force and logical form might not be a fact, so much as a strategy, something people do because for some purposes it's very useful to do so.
The example that leaps to mind for me is indirect discourse. Even if you follow @fdrake in thinking there is a sort of default use of language -- and I very much do (and here we might mention Lewis's truthfulness and trust) -- indirect discourse presents some challenges. The idea of force is helpful here, because you can distinguish between reporting what someone else asserts and asserting it yourself. (That this is a strategy we are not required by the nature of things to follow is clear in the phenomenon of blaming (or killing) the messenger.)
All of this probably aligns me with
Quoting Leontiskos
But I'm making the further suggestion that it's not just a question of our theories of language as philosophers, but that these theories are founded on the practices of language speakers, and that such theories do not stand aside as explanations of how people talk but are deployed strategically by speakers and listeners.
"I" always refers to the person speaking the sentence, does it not? These are two different claims:
I have seen analytics fall into this trap of thinking that sentences can float in the ether without any speaker, even a logically remote one. In that sense I would agree with the OP that all sentences have a kind of force, but I would call it an intentional force rather than an assertoric force.
Yes, that's fair. :up:
Quoting Srap Tasmaner
I don't think it is a question of whether there are non-logical forms of discourse. That can be granted. The question is whether Frege's system is a flawed logical form of discourse.
Kimhi defines philosophical logic as, "the idea of a study that achieves a mutual illumination of thinking and what is: an illumination through a clarification of human discursive activity in which truth (reality, aletheia) is at stake" (1).
So logic is not indirect discourse, and indirect discourse would not function as a counterexample to Frege's system. It may be otherwise for Quine, but for Frege the ontological question is not moot, and Frege did not consider his system to be a strategic, pragmatic deployment. Specifically, the system was meant to capture logic in its entirety. You are saying that it does not capture all of human symbolic activity. Would you also say that it does not capture all of logic?
Shrug. He can define as he likes.
Quoting Leontiskos
I don't think "logic in its entirety" is a thing.
I'll pass on Frege exegesis, but I'll say his system is spectacularly useful for doing mathematics; I believe this is mainly what he was after, but it doesn't much matter to me.
Are there forms of reasoning it is less useful for? Without question. But there are also occasions when presenting a bit of informal reasoning in the language of FOL is clarifying and useful if not dispositive. Again, I see it as a tool; you can use it and you can overuse it, and you can forget you have other tools. Tools aren't true or false.
Quoting Srap Tasmaner
Do you think logic is a thing?
Another black eye for modern thought.
Quoting Leontiskos
If you like, go for it. Sometimes it's more useful to speak of "logics" in the plural. It's just a word, you know.
Quoting Leontiskos
Insufficient for what? For the "mutual illumination of thinking and what is"?
I don't know man. I'm not sure how damning it is to describe something as merely useful, but you've got a hobby horse to ride and I'll not stop you.
If I'm part of that "we", I see a relatively clear but restrictive theory proposed as Frege's in and clarified wonderfully in . I wanted to put some pressure on the restriction in it. The restriction being that an account of a sentence's "logic" ought to solely concern under what conditions is that sentence true. And moreover, in the final analysis, that logical structure of truth conditions spells out all of what is asserted in an assertion and thus how that assertion works whenever it is asserted.
I don't think this has much grander significance, at least to me. I just enjoy thinking about formal vs informal reasoning and how that interplays with speech acts and extensional semantics.
No one said it was damning. Is mine the hobby horse, here? If you are averse to the topic of a thread, why post in it? After all, if you are ultimately just going to say, "None of this matters at all, and 'logic' is nothing more than a word," then it would seem that you are averse to the topic.
No, the way the we use terms like force doesnt reveal facts about the world in the way natural history does. Such terms are, as you say, tools. But that is not the same thing as saying there is no fact of the matter as to whether hallowed terms like being and truth reflect genuine ontological structures. They may or they may not it depends on what we mean by them, what we want such terms to describe. We cant go out and discover this, any more than we can discover that the number 2 precedes 3 and follows 1.
The takeaway here is that ontologically superior languages, to use @Leontiskoss phrase, might be precisely those which are the most useful to us, as you seem to suggest. But this does require one to drop the idea of a truth about ontology that is independent of hermeneutics. Which relates to this from Leontiskos:
Quoting Leontiskos
Yes to the pragmatic part (or at least I dont know where in Frege to look for that kind of language), but we should be careful about Freges ontological commitments. Again, I like Julian Roberts on this:
Its true that this doesnt moot the ontological question, but its a special and severe restriction on what we can say about existence. Its also a precise description of the order in which Fregeans have to proceed: quantification first.
Quoting fdrake
Works for me. Good way of putting it.
Quoting Leontiskos
Im still an undecided voter on the question of whether Freges system is insufficient, though I obviously regard Kimhis challenge as serious, otherwise I wouldnt be devoting so much head- and forum-space to it. But lets say it is insufficient. Merely a tool, then? Here is another perspective, which comes closest to the spirit of the challenge in my OP: If Freges system is insufficient in its basic understanding of how propositions work, how they must be understood within logic, then while it may remain a powerful tool, its defective in explanatory power at the metalogical level. That would be very serious, but hardly unprecedented. Newtonian physics is still a powerful tool, despite getting the big picture all wrong.
**
Does this Kimhi-inspired challenge question the dissociation of sense from assertoric force tout court (completely, without qualification)? No. Then:
Quoting Leontiskos
The claim under challenge is that assertoric force must always be dissociated from sense. Kimhi clearly says that this is mistaken. He believes that p may sometimes appear with its force displayed that is, as positive predication without being asserted. And he also believes that, sometimes (usually within the context of predicate logic), the separation of force and sense is necessary and unproblematic.
To unpack this, and to stay away from the jargon of categorematic and syncategorematic (which Kimhi uses in an idiosyncratic way), Im suggesting we think of force as something that can be displayed without assertion. And having said that, the question is whether this is just playing with words whether the nuance Im proposing really clarifies anything, or would change how we think about logic. To that question I would say, Kimhi thinks it does, but Im not clear on it yet.
**
Both@Leontiskos and @Fdrake have concerns about the I of assertion. This is very important, in my opinion. For instance:
Have I asserted p when I write ?p? How can you tell?
Is there a difference between thinking p and saying it out loud? Does vocalizing p usher it across the assertion barrier?
Here is the first sentence of Camus The Stranger: Mother died today. Call it ?p. Has p been asserted? By whom? The narrator of the novel is named Meursault. Should we say its his assertion? But of course there is no Meursault. Is it then Camus assertion? But its not about his mother. Maybe it's not an assertion after all. Sure looks like one, though . . . etc. etc.
So, much as I wish I could agree with Leontiskos (it would make things so much simpler):
Quoting Leontiskos
I think the answer is no. @Fdrake prefers to think of the asserter as the person in the sentence, and this seems closer, but demands a generous ascription of personhood.
Theres a lot more I could respond to, but enough for now. High-quality posts.
I see the thread has gotten away, with various posts the relevance of which are uncertain. That makes it difficult to do the step-by-step work needed here.
Let's next take a look at sense and reference. Again, you are probably already familiar with what follows, and think of this as rehearsing the arguments that got us to the sort of accounts being critiqued.
We find it useful to differentiate between what was referred to and how it was referred to. So we use the word "Venus" to refer to Venus, and we can also use "Hesperus" to refer to Venus, but seen in the evening. What differs here is not the individual being talked about. There were attempts to remove individuals all together from the calculus, but there turned out to be cases where they were most useful, especially in modal logic. So now we usually use constants, a,b,c..., sometimes even calling them "names", and usually think of them as simply referring extensionally to individuals.
But that's a more recent development. It seems Frege worked with a more general understanding of the things he was representing. So his
might now be parsed as U(x)f(x), and we might think of "x" as ranging over individuals. For Frege the gothic [math]\mathfrak a[/math] was the argument of a function.
What I would draw attention to is that illocutionary force is a different issue to sense and reference. Frege was perhaps unable to accomodate this difference in his nomenclature.
Again, small steps. Does this seem correct to you?
I don't see a problem with fictional characters asserting stufffictional character/ fictional assertion.
I don't think this is correct at all. Here is Frege:
Quoting Luká Novák, Can We Speak About That Which Is Not?, 157-8
Quoting Luká Novák, Can We Speak About That Which Is Not?, 159
Given this evidence it would seem that it is incorrect to claim that for Frege quantification is wider than existence. I think the sources from your thread on QV attest to this same fact.
I have been snipping the second sentence of that title, "Can we speak about that which is not? Actualism and Possibilism in Analytic Philosophy and Scholasticism." The general critique of Frege seems closely related to the Actualism and Possibilism debates.
-
Quoting J
As I said in the first sentence of that post, "I think it is a useful tool." By "tool" Srap is apparently implying a strong sort of ontological pluralism, as he favored in your earlier thread. You are welcome to press him on it, or on the question of better and worse logical tools.
Quoting J
Yes, well put.
Quoting J
This is what I suspected, and said, "...But is there any formal logic that will really be able to dodge this bullet and provide the same cornucopia of locutionary flavors that natural language possesses?" ().
There are systems of logic that set about mapping other forms of force, such as belief, but it doesn't strike me as a great approach to lay the charge at Frege's feet that he hasn't sufficiently accounted for non-assertoric forms of locution. This is where I think Srap's critiques are helpful, for they demand more precision as to the actual conclusion being argued for.
Quoting J
It strikes me as a simple question of intent. One asserts something if and only if they intend to, and I don't think any material sign contains within itself any variety of illocutionary intent. For example, "The grass is green" can be placed in that modus ponens premise, and thus stripped of its assertoric force. Now it does have a kind of prima facie assertoric force, which must be stripped or prescinded from if we want to avoid it. Is that the same as being intrinsic?
Quoting J
I don't think you understand what I am saying. "I" refers to the person speaking the sentence, and this person is not fdrake. The oddity is that @fdrake seems to think that there was no asserter prior to the one who was "conjured" by the "I", but I recognize that he is not trying to give an answer to the paradox.
Quoting Leontiskos
Does, "It is raining," have assertoric force, and if so, who is the asserter? There is a sense in which it has a kind of meta-assertoric force insofar as we are forced to imagine at least an implicit speaker. But my use of the quotation marks indicates that I am holding it aloof rather than asserting it myself. I don't suppose this is all Kimhi is saying?
I've been rereading your OP, and I think I get the argument now. Here's the key point, I believe:
Quoting J
Two alternative definitions of "assertion" contrasted here:
(1) Assertion is (a person, an agent) claiming that the possible state of affairs, let's say, described by a statement does in fact hold.
(2) Assertion is (a person, an agent) affirming the claim about the world made by a statement.
In (1) the claim is not made until someone asserts it, or asserts that the statement at issue is true, that what it describes is the case. In (2), the statement itself is a claim that things stand thus-and-so, and asserting that statement is affirming, agreeing with, that claim, endorsing its claim to truth.
One thing that's nice about (2) is that the statement underlying the claim is readily picked out. We could try to avoid some of the awkwardness of (1) (and ditch the somewhat Tractarian "possible state of affairs") something like this:
(1A) Assertion is (a person, an agent) claiming that what a statement says, is in fact the case.
And now it feels like we're halfway to (2) already.
---- I want to stop there for a moment, because there's more to say about this business of sentences saying something, but I want to add a brief detour back to Frege and truth values.
Frege isn't remembered for the propositional calculus, which predates him, but for quantifiers and their use in tidying up the predicate calculus, to make it safe for mathematics.
So a typical, and trivial, bit of post-Frege argumentation might be this:
1. For all integers x, if x is a prime greater than 2, then x is odd.
2. 5 is a prime greater than 2.
Therefore
3. 5 is odd.
What interests me about this for the sake of this discussion is that it is not some statement that could take a truth value that is repeated: it is the unsaturated function "... is a prime greater than 2." It appears first with a bound variable in 1, and then with a specific named object in 2, and it's the use of the same predicate that allows the conclusion in 3, repeating the other unsaturated function "... is odd" but now applying it to a named object so that it is a complete symbol and can take a truth value.
This seems slightly at odds with the descriptions involving a repeated identical 'p': there are no repeated complete symbols here.
2 and 3 are straightforward, and the sorts of statements that say things. But 1? Does 1 say something? Evidently, but it says a different sort of thing than 2 or 3.
I noticed that too. Absolutely. I think the general thrust of the whole modern Frege-Tarski-model-theoretic approach is to presuppose the existence of the objects within the universe of discourse, and then the questions addressed are which objects satisfy which predicates, and that's all.
Added: This all goes hand-in-hand with Frege's straightforward platonism -- mathematical objects just exist, and they have to exist for us to talk about them as we do.
Just for the specific sentence "It is raining but I believe it is not raining", taken as a stand alone. When you read that, you can understand it. Even though you don't know who "I" refers to. You just know it's the person in the sentence.
I'm saying conjured because the sentence is really weird. Firstly it's a philosophy brainrot meme, no one is actually going around saying that sentence. I can't expect it to work like a sentence outside of a philosophy thought experiment in all respects. Which is fine, it's made to illustrate something tacit about our intuitions surrounding statements, assertions, logic and beliefs.
The sentence is free floating. The sentence "Sally said, 'It is raining but I believe it is not raining'", also illustrates the paradox, but now you know "I" refers to the speaker Sally. Rather than some retrojected speaker you conjure into existence, for the sentence, when you get to the words "I believe" and form a coherent interpretation of the sentence in light of that.
I'd make the same conjured into existence analysis for "I" or "me" in the sentences:
A) It's an egg, I know it's an egg.
B) Ask not for whom the egg tolls, it tolls for me.
C) I have to block out thoughts of eggs so I don't lose my egg.
when they are presented without further context.
Because, as internet brainrot would have it, the who "I" is is ghosted, for real.
This would be a fairly minor point were it not that this thread is trying to understand the exact connection between assertion and truth values.
Assertion vs. reference
As you said, Frege wrote that his most important contribution to philosophy was disassociating the assertoric force from the predicate.
It is true that an assertion and a reference are not the same thing, but they are inseparable. In order to make an assertion, in order for there to be the act of asserting, something must be being asserted. In this case, what is being asserted is a reference.
For example, given the proposition "this grass is green", the somerthing that is being asserted is that this grass is green, where the truth value of the proposition "this grass is green" is given by its referent, ie, that this grass is green.
Frege in On Sense and Reference noted the connection between the assertoric and its referent:
IE, the duality between assertoric force and predicate may well be equally expressed as the duality between sense and reference.
Wittgenstein and assertion
Within the Tractatus there is no reference to either "assertoric force" or "reference", but only to "sense".
As normal with Wittgenstein, he conflates many topics, whether falsehood and negation, the intensional and the extensional, the psychological and the logical as well as "sense" and "reference".
The unity of thinking and being is the cornerstone of Wittgenstein's Tractatus.
In the Tractatus, it is not the case that a proposition has a sense prior to anything that is being referred to, in that sense may be disassociated from reference, in that the sense of "this grass is green" may be disassociated from its referent in reality, that this grass is green. But rather, the sense of the proposition is what is being referred to, in that there is a unity between the sense of "this grass is green" and its referent, that this grass is green.
TLP 2.221 - What a picture represents is its sense.
TLP 2.222 The agreement or disagreement of its sense with reality constitutes its truth or
falsity
Wittgenstein in the Tractatus is unifying thought and being, and is unifying Frege's "sense" and "reference" into the single term "sense".
Indirect Realism vs Direct Realism
It is in the nature of Indirect Realism that there is a natural unity of thought and being, in that on the one hand we think about the world, and on the other hand, the world we think about exists as a thought. Such a unity is a consequence of logical necessity.
The Direct Realist, on the other hand, has the thought of a red postbox, and the belief that the postbox is red. However, there is no logical necessity that the fact that there is a red postbox in the world will give rise to the thought that there is a red postbox in the world. Any agreement between what exists in the world and any thought about what exists in the world remains contingent.
Indirect Realism has the advantage of thoughts as being necessarily true, whereas Direct Realism has the disadvantage of thoughts as only being contingently true.
Excellent citations from Frege. My claim was twofold: 1) that predicate logic restricts what we can say about existence; and 2) we have to start with a logically grammatical proposition that fills the argument slot with a term, thus creating what Frege called a name, before we can say whether it exists or not. Im not sure what wider than existence means exactly, but your citation clearly shows that Frege believed we have to presuppose that sentences [can?] express judgments and that there is a world out there, about which we are trying to say things. No disagreements here, and sorry if I seemed to say otherwise.
One point about something Frege also says here. He asks: Can you produce an example where a sentence of the form 'A is B' is meaningful and true, A being a name of an individual, and yet 'There are Bs' is false? To me, this shows why quantification comes first in his method. He requires, correctly, that A is B be meaningful and true before the contradiction with There are no Bs can be shown. But what does it mean for A is B to be meaningful and true? Correct grammar, and the judgment-stroke. Both of these require quantification first. If we changed Freges question to read: Can you produce an example where a sentence of the form 'A is B' is unasserted, A being a name of an individual, and yet 'There are Bs' is false?, the answer would be, Of course we can. It goes back to Freges basic assumption that all ps occur in the context of logical argument.
Quoting Leontiskos
The charge is more radical than that. The Kimhi-inspired challenge says that the mandatory dissociation of force from sense in logic is wrong. Kimhi: [Frege and Geach] want to dissociate assertoric force from anything in the composition or form of that which is primarily true or false in a propositional sign. And yes, I hope Srap keeps pressing his points; we need to interrogate this challenge sharply.
Quoting Leontiskos
But in all seriousness, what if the person cant do any speaking at all? Meursault has never said a word no surprise, since he isnt real. Pursuing this much further would probably take us away from the main concerns of the thread, so I wont belabor. What we need is an account of how so-called fictional assertions work, and what requirements we place on personhood in order to have apparently non-existent persons asserting things. I find this all fascinating but, as I say, I don't want us to digress.
Yes! Youve got it precisely, and have expressed it better than I did. Many thanks. The key difference is affirming a claim that is, a statement -- rather than making your own statement about how the world is.
Quoting Srap Tasmaner
Im puzzled too. Can a more expert logician weigh in and help?
Sure. But what I was trying to point out (or what I think Roberts means, anyway) is that the universe of discourse isnt neutral or discoverable or God-given or whatever. We have to determine it, which requires quantification. What we presuppose, I think, is that once we do this, theres no problem with saying that objects exist.
That said, I know some Frege and Tarski but would flunk a test on "the whole modern Frege-Tarski-model-theoretic approach," so feel free to school me.
Good, that fits the Fregean picture.
Quoting RussellA
Yes, to the best of my understanding (with help from Kimhi).
Quoting RussellA
Cf. this from Notes on Logic:
And cf. the elucidation @Srap Tasmaner provided between affirming a claim and making a judgment about the world.
Quoting Srap Tasmaner
I am struggling to see the difference here, but maybe that is just me. I was understanding @J to be saying that propositions can have assertoric force independent of persons/agents who would speak them. Therefore I would prefer a distinction between a possessor of assertoric force which requires a speaker/asserter and one that does not. I thought J was saying, "This thing has assertoric force even before you pick it up and assert it."
Quoting Srap Tasmaner
Interesting point. Substitution of individuals/particulars occurs beginning with (2), and substitution is a different kind of logical move.
But I would say the middle term (the recurrence of 'p') is found in the substitutability itself. (1) quantifies over all integers, and because '5' and '2' are integers they are substitutable into the formula of (1). Does the OP's point about the repeatability of p break down in cases of substitution? I shouldn't think so, but perhaps that argument needs to be refined.
I suppose it is worth noting:
Quoting Srap Tasmaner
According to Anthony Kenny's history of philosophy Frege and Peirce simultaneously and independently developed the propositional calculus (which therefore did not predate them, at least in this robust form). But you are right that Frege is remembered for his predicate calculus. The point, though, is that a critique of propositional calculus (and the repeatability of propositions) is a Fregian critique just as much as a critique of predicate calculus would be.
Quoting Srap Tasmaner
Yes, that's right. Jumping ahead a bit, I am curious about the Fregian presupposition which cleanly distinguishes predicate bearers from predicates, because apparently it associates existence with the former but not the latter. That is, apparently we can talk about non-existent predicates but not non-existent predicate bearers. This seems to reveal an odd lack of parity. For Aristotle a substance and an accident both play by the same general rules, even though an accident has a different kind of being than a substance does.
I am disputing your (2). For Frege we don't quantify things and then go on to decide whether they actually exist (and this is very much related to your QV thread).
Quoting J
His claim seems to be counterfactual, not temporal. "If there are no B's then 'A is B' is neither meaningful nor true."
Quoting J
You seem to be reading this word "before" into the text, contrary to the text.
Quoting J
I don't know if what you are saying here makes sense, as Frege's whole point is that if there are no B's then 'A is B' cannot be meaningful or true. Were you able to download Luká Novák's paper? I think it would be of great benefit.
The irony here is that Frege would presumably not say, "Of course we can." If there are no B's then 'A is B' is not merely unasserted, it is not meaningful. The second quote I gave has Frege literally denying that we can meaningfully deny that something exists (tout court).
Quoting J
For Frege there is no non-existent universe of discourse. Existence is not an afterthought to quantification.
Quoting J
Okay. I can see how Frege mandates a dissociation between sense and assertion. Is that the same as mandating a dissociation between sense and force? Or sense and assertoric force? Kimhi seems to believe that something can have assertoric force without being asserted. It seems like Frege wants to make one big distinction (between propositions and their truth values), and Kimhi wants to make lots of small distinctions (between different kinds of force, or different levels of assertoric force).
Quoting J
Agreed. :up:
Let me first say that I think the first half of your first post was excellent and deeply relevant. As to the second half, about Moore's paradox, I continue to vacillate on whether it is really relevant. It sheds a bit of light but also raises a lot of issues that seem to be tangential. With that said...
Quoting fdrake
I can't understand it. The received view seems to be that it is absurd. I don't know who "I" refers to. And I don't know who "the person in the sentence" is supposed to refer to. The problem is that, taken at face value, the locution is schizophrenic, and therefore talking about a single speaker is not intuitive.
This is why talking about Moore's paradox seems to require a great deal of explanation and verbiage, in the first place as to how it is being interpreted.
Quoting fdrake
I worry that we're on a tangent, but the difference is that any statement has a kind of implicit, "I say..." "(I say) It's an egg." Moore's sentence is absurd (and contradictory) because the speaker disagrees with himself (or else has a very idiosyncratic notion of belief).
It seems that originally Moore was looking at two propositions, both of which are said to be true:
1. It is raining
2. I believe it is not raining
He supposes that any two true things can be conjoined and spoken, hence, "
One way it seems relevant is that understanding the sentence as weird and contradictory on a gut level...
Quoting Leontiskos
pumps the intuition that it must function as an assertion. It would never be uttered in normal circumstances since part of its mechanism asserts something and then undermines the act of assertion.
If it is indeed contradictory in some sense, it is contradictory by virtue of a property it has as an asserted statement, and not its propositional content (what makes it true or false). Since extensionally it's fine. It can be raining while its speaker believes it is not raining, so I can assert "It's raining and I believe it is not raining" and it could true.
The reason that would be relevant is that it highlights a kind of contradiction which can occur by virtue of the acts and attitudes contained in the statement relating to the statement's propositional content, which suggests that there is a type of contradiction which is not governed by the phrase's propositional content. In the sense that a stairway implies distinct floors.
Maybe analysing it in terms of illocutionary forces is good. And it would probably be better to look at it in the form "Sally said "It is raining but I believe it is not raining"", since that dodges all the weird crap involving "I", since we know who is saying it.
"It is raining but I believe it is not raining" is asserted by Sally. It has assertoric force.
"It is raining", the first clause, is something which could be true or false. Sentences that begin with "It is" parse as assertions. EG:
Sally said "It is an egg".
Sally said "It is a nice day today".
Sally said "It is going to be 3 degrees Celsius this evening".
So reading the sentence, the first clause invites us to interpret that Sally has asserted that it is raining.
Then there's "but", which registers an opposition or contrast between what came before and what came after. The sentence is still odd with "and" instead, so I shan't make too much of the "but" in it.
The second clause is "I believe it is not raining", which invites us to interpret it as an assertion. Sentences which begin with "I believe" parse as assertions of belief on the part of their speaker. EG:
Sally said "I believe it is an egg".
Sally said "I believe it is a nice day today".
Sally said "I believe it is going to be 3 degrees Celsius this evening".
When someone asserts something, they are often taken to believe it. I think that's a good default assumption when someone makes a simple claim, and you've no reason to otherwise doubt them. Though it isn't necessary that when someone asserts something, they believe it - they could be lying, they could misspeak, they could be confused, they could be deluded, they could have very unstable beliefs in the moment etc. The expectation is that when someone says "I believe (blah)", they count as asserting (blah) truthfully.
So when Sally says the second clause, "I believe it is not raining", a reading of the phrase in which Sally's assumed to be truthful and sincere associates the "I believe" in the sentence with asserting the claim "It is not raining". So the first clause appears to assert "It is raining", the second clause appears to assert "It is not raining", and those things clash together in our heads.
Nevertheless, Sally is not in a state of contradiction. For Sally only appears to assert that it is raining, and only appears to assert that it is not raining. With logical heads on, that feels like she has just asserted that it is raining and that it is not raining, which is a contradiction. But I think a better explanation of the weirdness in the sentence is that appearing to assert X is both logically and behaviourally consistent with appearing to assert not-X in some contexts. I'd bet this conflict of appearances and a scramble for context is something you sever if you remove the attempt to contextualise the statement (radical interpretation eh?). And moreover, I'd bet that this conflict of appearances is commonplace and essential out in the wild.
Eg, I've said "I don't believe it's raining!" while wincing up at a sky thick with summer rain. And I wasn't insane at the time, I was just complaining. Making sense of "belief" in that statement didn't require too much work on the part of my friend who was with me, since they'd known that was the only day with a good forecast that week.
A similar logic lets you provide a model for Sally's odd phrase. I'm sitting here now, I believe it's not raining since it wasn't forecast to rain this evening last time I checked. But my curtains are closed. I just said "It is raining and I believe it's not raining" aloud... and it turned out it wasn't raining after all, when I opened the curtain.
What I think makes Moore's paradox a good gateway in this discussion is that there's a whole context of cooperative use and interpretation, which contains a myriad of exploitable oppositions and contradictions, that just don't show up when you analyse the phrase as an instance of asserts(p & believes not-p) & asserts(p)=>believes(p). Particularly how you can make sense of it, and the kind of doubt you might have regarding Sally's faculties and situation. Maybe those are the kind of things @J was looking to incorporate into a logic.
Though there remains the question of whether this can be incorporated into normal flavours of logic, whether it's something that can be formalised, whether it should be formalised... and so on.
As an aside, when I said the phrase aloud I felt a powerful compulsion to immediately open the curtain to check... Surely something we expect Sally to have done in my shoes!
Quoting Leontiskos
The distinction is total and fundamental. Frege goes so far as to say you cannot talk about functions (i.e., predicates) at all, because to talk about them is to treat them as objects. We do, nevertheless, talk about them, because it's handy, but he considered this a shortcoming of natural languages. In his system, it is simply not possible: functions cannot be values of variables. ((That's first-order, of course, and it's well known that even to define arithmetic you have to pass on to second-order. I don't recall what he says about this, and whether a switch to classes as stand-ins for functions is good enough. Anyway, there's a gap in my account here.))
He goes further, and says that he cannot even tell you what a function is -- that is, what belongs to the type
((This distinction -- that there are some things that can only be shown -- I think had a tremendous influence on Wittgenstein, that was still percolating after the Tractatus, or so I believe.))
Quoting Leontiskos
Kinda, but I'd be more inclined to say that predicates neither exist nor fail to exist. No more than red is tall or short. It just doesn't apply. Objects are the sorts of things that exist (or fail to), and functions aren't objects.
I don't remember how Frege deals with non-existent objects, or if it even comes up, but in the world he left us, empty classes serve. I can name "the smallest positive rational number" but it will turn out I have defined an empty singleton class. (Extensionally equivalent to any other empty class, but not intensionally, if that matters.)
Quoting Leontiskos
Peirce had quantifiers too, I hear, but I've never studied his logic. I certainly defer to Kenny -- I just think of the likes of Boole and De Morgan being quite nearly there already.
###
That's all the housekeeping. I'm tagging the quotes below, because this is the meat of it, of course, but I'm going to hold off posting and think a bit more.
Quoting Leontiskos
I think we're all on the same page, I'm just using the word "claim" instead of "assert", and also drafting the word "say", all three of which have considerable overlap in everyday speech.
Quoting Leontiskos
Quoting J
Some points I'm mulling:
(1) We have to decide something about locutions like "This sentence claims ..." or "This sign says ..." and so on. I consider it a live option to take them at face-value. It is more common to treat this as a manner of speaking, perhaps glossing "The sign says we have stop" as "If a person were to speak the word printed on the sign, she would be saying that we have to stop," on the smarty-pants grounds that signs don't talk and to say otherwise is anthropomorphizing them. You can also say that they are said to "speak" by courtesy, or argue directly that either an artifact or an abstract object like a proposition, as it were, "borrows" our ability to mean things, that we, as it were, "lend" them our ability to mean things --- as if to say a stop sign is a sort of ghostly police officer, and he has imbued the sign with his spirit.
(2) There's a little bit of a puzzle about the "affirming" language, because it makes asserting sound like it has an extra step, so that it strongly resembles indirect discourse. As if a person making an assertion were "channeling" a spirit guide: there's an internalized claim presented, which you speak on Ephraim's behalf, and by so speaking endorse it.
((3) And here I'll note that this pattern is reminiscent of the prosentential theory of truth, as well as other deflationary theories of truth such as Ramsey and Wittgenstein appeared to hold, such that the use of "... is true" is primarily to endorse what someone else has said.)
(4) @Leontiskos seems almost to suggest that statements have a sort of hole in them, like Frege's functions, waiting for an agent to be inserted and complete the assertion. But we need more than an agent, we need an actual utterance (even if internal), and then we're faced with the problem of intention as well --- some of that context will take care (I'm acting in a play), but some it won't (I was just saying what he wanted to hear).
(5) We have to decide --- (4) mentions some of this --- what we want to count as an assertion. Is it fully disambiguated? Are indexicals all resolved? Is the assertion the statement itself, or the claim in the context and at the time it was made? (Is an assertion an event?) ---- Several of these issues do not arise for the language of mathematics, which is entirely tenseless, to start with, requires no speakers or audience, has no sensitivity to context, etc.
(6) And, finally I guess, what about the social aspect of assertion? We generally think of making an assertion as incurring an obligation to stand by it, perhaps to provide justification, to license others to rely upon it, and so forth. There are pragmatic maxims such as "Do not say what you do not have good evidence for" (Grice) or "Do not say what you do not know" (Williamson). It's easy to talk about all this if assertion is entirely external to the "content" of the statement asserted, but goes wobbly if you want to push some of that into the sentence itself.
Good, this is precisely the way that it sheds light on the OP.
Quoting fdrake
Yep, this helps a great deal to clear away the tangential issues.
Quoting fdrake
Right.
Quoting fdrake
Isn't she, though?
Quoting fdrake
This is a different matter as far as I'm concerned:
Did she appear to say it or did she say it? First we were dealing with (1), but now we have suddenly switched to talking about (2), which is quite different. If she only appeared to say something, then of course she could not contradict herself. The conclusion would not be, "Sally contradicted herself," but rather, "Sally appeared to contradict herself."
Quoting fdrake
But note that this is no longer an assertion. The assertion would be, drawn out, "It is false that it is the case that it is raining." Or, "It is not the case that it is raining."
Quoting fdrake
This doesn't strike me as intelligible. Why did you say it was raining? Were you having a stroke, with random words exiting your mouth? There is no question here that people can say nonsensical things and contradict themselves. The question is whether some utterance is contradictory.
I would say that to assert is to believe. Therefore if Sally asserts that it is raining then she believes that it is raining. This is all that is needed to recognize her contradiction, and this premise seems very secure. What you have done is given some possibilities where she doesn't actually assert, but that strikes me as beside the point.
Quoting fdrake
That's fair. You've sufficiently established your thesis about the relevance of Moore's paradox.
Now, in my opinion, the sort of ways that you are defending the coherence of Sally's statement are not going to be plausible ways to critique Frege. But with that said, I have seen folks who are devoted to Fregian logic who have a tendency to oversimplify locutions, so there is that. That's a hard thing to critique.
Quoting fdrake
I would say that the context-independent interpretation is clearly contradictory, and that it doesn't make much sense to present it as context-independent and expect the hearer to place it in some idiosyncratic context. The additional context could be as simple as, "Sally, a deeply intelligent woman, said..."
Quoting fdrake
Right.
Quoting fdrake
:grin:
I suppose appears was inopportune. I meant to say that the reader is invited to interpret Sally to be asserting that it is raining, and invited to interpret Sally as asserting that it is not raining in virtue of her statement of belief. Those two things oppose each other somehow.
So with "appears to say", I meant something like "appears to us", "can be interpreted as", and so on. And I mean those expansively, provisionally and contingently. I think part of what makes Moore's Paradox interesting is because it invites us to bracket a normal functioning of language and thus throws it into relief.
Quoting Leontiskos
I don't agree with that. On the basis that I interpret Sally's utterances truthfully and sincerely, I believe it's appropriate to infer that Sally would be in unusual scenario that makes sense of the bizarre composite of asserting that she believes not-p and asserts p in the same breath. In the wild I'd be inclined to read "believe" somewhat figuratively, like an exasperation, or an alternatively that Sally is experiencing a disconnect between whatever engenders her to assert statements and whatever engenders her to assert her own belief in statements. Basically I want to trust Sally rather than calling her out.
My points might not be well targeted at Frege though, so point taken. I hope it is at least relevant to whether assertoric force should be severed from the logic (whatever that is) of an asserted statement.
I want to take a look at two more things: the use of ?, and the notion of extension.
As I understand it, extensionality enters into Frege's system with Basic Law 5:
[math]\stackrel{,}{\varepsilon}\!\!f(\varepsilon) =\, \stackrel{,}{\alpha}\!g(\alpha) \equiv \forall x(f(x) = g(x))[/math]
(From SEP). This may be read as "the course-of-values of epsilon is the same as the course of values of alpha if and only if for all x, if x is f then x is g". That is, f and g are the same predicate if and only if every member of f is also a member of g.
The import of this fairly simple point might be clearer if we use a more recent nomenclature and example. I'll refer to the Open Logic Project:
I'll ask the reader to note that this is the very first formula in this rather extended treatment of logic. This might give an indication of how foundational extensionality is in logic. It is worth I think lingering on what is being said here. Consider the groupings {a,a,b}, {a,b} and {b,a}. Extensionality says that for the purposes of doing the logic that follows, all of these can be treated as {a,b}. What we have here is a tool for simplifying whole groups of expressions down to a single form.
So why the fuss? This all seems straight forward enough. The Open Logic text goes on to give a further example, which I will modify slightly. Consider S, such that S={Ruth}. As it turns out, Ruth is Richard's sibling. So we also have the set S' such that S'={Richard's sibling}. Since Ruth is Richard's sibling, we have S=S'. We say that S and S' differ in sense but not in reference, they differ in intension but not in extension.
Treating groups of things in this way is one of the several great contributions Frege made to logic.
So when Frege 'wrote that his most important contribution to philosophy was dissociating the assertoric force from the predicate', he could not have been talking simply or explicitly about illocutionary force, but had in mind at least partly something of the sort given here, were the assertive force of "S is Richard's sister" is simplified by treating it extensionally as S={Ruth}. The "assertoric force" being removed here is at least in part the sense of our statements, so that we might set them aside and deal with the reference.
Again, this is by way of setting out what is at stake here, of what Frege did and how it has developed since. The device on which you are reading this might well not be available if it were not for the developments that took place from considering Basic Law 5. It is central to the logic used, albeit in sorting out its inherent inconsistency as much as in making direct use of it.
Very interesting. That all makes sense, and fills out my understanding a bit.
Quoting Srap Tasmaner
Good, and this is more accurate than the way I was stating it.
My idea was basically that it is curious that Frege is comfortable saying that Fido is not a cat, but is unwilling to say that Fido does not exist. As you point out, this makes sense for Frege given that the former statement is just a matter of class exclusion, and given that classesempty or otherwiseare not said to exist. ...But I think @J's confusion about Frege may stem from a similar place. J may be thinking, "Kimhi criticizes Frege for divorcing the sense of a proposition from its assertoric force; 'Fido exists' is a proposition; therefore Frege divorces this proposition's sense from its assertoric force; therefore Frege thinks we can quantify over Fido before predicating existence of Fido." At the same time, J knows that Frege does not accept the idea that existence is a predicate, and so there is a tension.
Quoting Srap Tasmaner
According to the paper I have been citing:
Quoting Luká Novák, Can We Speak About That Which Is Not?, 158-9
Quoting Srap Tasmaner
Yes - my point is only that a critique of Frege could be a critique of his propositional or predicate calculus. I assume that bit about the repeatability of 'p' pertains to the propositional calculus.
Quoting Srap Tasmaner
:up:
Quoting Srap Tasmaner
I have often given an impromptu and half-baked account, and this will be no exception. The idea is not so much that they have a hole, but rather that in order to be understood even qua proposition they must have an intentional sense, and they cannot have an intentional sense without an implicit speaker. And there is no neutral intentional sense, or non-intentional sense.
So to take @fdrake's example of Sally asserting Moore's paradox, there is no interpretation of Sally's linguistic utterance which is entirely divorced from an intentional sense and an implicit speaker (in fact fdrake cleared up the implicit speaker problem by making the speaker explicit). According to @J, and as I supposed, Kimhi is after something more substantial and controversial than this. But my point is that there is a kind of default or prima facie intentional sense of every proposition, given the fact that there is no way of interpreting or even apprehending a proposition without assuming some intentional context or another. It's not so much that the proposition has a hole or an intrinsic intentional force by its very nature, but rather that it can never be handled as a proposition, or as a linguistic utterance, without some intentional sense (and implicit speaker) being supplied. There is no possibility of fully prescinding from the intentional sense of a proposition, and the intentional sense would seem to involve a "force" dynamic. In your language we might say that affirming a pre-existing saying will involve one in different intentions and assertoric force, depending on the content of the saying.
I must be missing something. I can see no more of a problem with fictional assertions than I can with fictional imaginings, fictional events, fictional places, fictional characters and so on.
I'm also not clear on what an "exact connection between assertion and truth values" could be. If I claim something is the case I am either right or wrong depending on whether what I've claimed is the case or not. I can't see what more could be said about that.
Here is my edit in case you didn't see it:
Quoting Leontiskos
For me the paradox is too obviously contradictory to be a good candidate for exercises regarding misinterpretation or ambiguity of meaning. It's not a coincidence that you will go through your entire life without ever once hearing someone say, "X is true but I believe it is false."
I would say that the detective who has only Sally's statement in front of him is not a good detective if he multiplies all sorts of theories without any evidential basis for those theories. The exercise feels like being put in the place of a sophist's pupil who receives the task, "Politician Sally said this and nothing more. Find a way to spin it so that she didn't contradict herself. It won't be easy."
And what is the difference between Sally saying, "It is raining but I don't believe it is raining," and Sally saying, "It is raining but it is not raining"? I think the difference is only minor, and the same maneuvers that saved the first could equally well save the second. If this is right then on your approach every statement is unfalsifiably noncontradictory.
Quoting fdrake
When we hear something like this in the wild we either ignore it given our dearth of information, or else we try to gather more information in an attempt to account for the seeming contradiction. But the fact that it is a contradiction at face value will not go away.
Is it a contradiction? Yes. Could there be some extenuating circumstance or idiosyncratic use of language or intent that renders it non-contradictory? Yes.
Quoting fdrake
Supposing it never occurs in the wild, does that matter? In that case, "What would an unspoken sentence mean," is a bit like the question about the sound of the tree falling in the unoccupied woods. Perhaps there is a good reason why Moore's sentence is never actually spoken.
Language is flexible, but there are limits to this.
I'm going to recast what you're saying in this post. (That's just a representative quote.)
I think what you're actually circling around is this: given a sentence (not even necessarily a statement, though that's been the main focus), what would a speaker of this language use it for? You're taking about use, and the default use of statements is assertion.
Yes, and it need not even be limited to logical sentences. It applies to any piece of language. I am saying that we do not have any notion of what a piece of language means without a background of intentional sense and implicit speaker. And yes, the default for statements would seem to be assertion. It is something like asking what a speaker of the language would use it for, but pre-critically.
I suppose a question that arises is whether the material symbol of a pun or ambiguous reference can itself be pointed to. The answer is probably: Yes, but only as a material symbol and not as a proper linguistic sign. To take an old example: 'bank'. In the river sense or the money sense? More to the point, can we reference the single bearer of both separate senses? Sure, but that bearer is a material token rather than a proper and meaningful word: b-a-n-k.
Are fictional assertions true? Here is Frege:
Quoting Frege Reader, 300
The very next sentence of the unabridged text begins the section on dissociating the assertoric force from the predicate.
To stick with Frege, this is the motivation for the context principle: never ask for the meaning of a word except in the context of (as it is used in) a sentence.
Let's come back to @J 's issue (instead of doing all of philosophy of language).
If you think of something people use, you might think of a tool. Tools capture the problem we face pretty well.
Take a screwdriver. It is a designed artifact, with an intended and, in practice, overwhelmingly common use. That's what it's for. (You might also say that obvious use is what it does, if you're comfortable saying things like that.) When you want to drive a screw, you reach for a screwdriver (of the right sort) because it is the right tool for the job.
But you can use a screwdriver for an unknown number of purposes improvised in the moment. And you can use an unknown number of other objects to drive a screw in a pinch.
The activity of driving screws and screwdrivers are only loosely coupled, though they are indeed coupled and statistics on how screws have been driven and how screwdrivers have been used would certainly show that.
And the analogy to words should be clear, although we're really aiming for sentences, and I think it does no harm to pass the analogy up a rung.
So we have a statement, which, like a screwdriver, carries in its very design its fitness for being asserted; on the other hand, we have the act of assertion which makes use of the appropriate statement. But this coupling is loose: the sentence has other uses as well, and the assertion can be made using other sentences.
For the duration of an act of assertion, there may be a temporary tightening of the coupling --- to produce an utterance you have to commit to a particular sentence. But that grip is immediately slackened: this forum consists almost entirely of people trying to express the same thoughts using different words.
All of which, I think, explains both @J 's sense that statements display assertoric force without themselves being assertions -- in much the way a screwdriver has a clear and unambiguous purpose ---but also why Frege distinguishes them, because the coupling of a statement to the assertion it would naturally be used to make is loose.
We could also note that Frege's sense/reference distinction is in some ways an acknowledgement of such looseness: "3 + 2" and "5" are different expressions denoting the same object; that means you have some freedom in choosing what expression to use to pick out an object, and both proofs and methods for solving equations rely on this possibility of rewriting a mathematical sentence using expressions that can be substituted salva veritate.
Yes, I was thinking of the same analogy.
Quoting Srap Tasmaner
Right, good.
Quoting Srap Tasmaner
I think it is worth asking this question of why Frege distinguishes the assertoric force from the predicate. Your idea seems to be that it is because different predicates can be used to make the same assertion. Here is Frege, and @J may also be interested:
(Of course "assertoric force" is here binary, as on/off or true/false)
This is what I would want to question:
Quoting Srap Tasmaner
Now in that bolded phrase you switch from 'statement' to 'sentence', but regardless, I would question the idea that a statement has other uses than assertion. Appealing again to my idea of intentional senses and implicit speakers, I don't think statements are ever wielded while wholly prescinding from their assertoric nature. I don't know whether Frege would think of a quoted phrase as a "subordinate clause" (or the equivalent German), but suppose I put quotation marks around, "The grass is green." This is sufficient to indicate that I am expressing a thought without asserting it to be true. Is that proposition assertoric? No and yes. No, insofar as I am explicitly indicating that I do not intend to assert it. Yes, insofar as the intentional sense and the implicit speaker associated in my mind with the proposition both have everything to do with assertion; or in other words: it is a statement, albeit quarantined and muted. Similarly, tigers are dangerous. If we put a tiger in a cage does it become non-dangerous? Yes and no, for the cage only exists because it is dangerous, and the cage is what holds the danger at bay.
This is part of what I understand @J to be saying in the OP and elsewhere, but as I said in my first post, I am not yet convinced that it is something Fregian logic must worry about.
They are fictionally, as opposed to actually, true or false, or their truth or falsity may not be sepcified in the work. I still don't see a problem, just a matter of different contexts.
Quoting bongo fury?
@Banno @Leontiskos @Srap Tasmaner @RussellA @fdrake
Whew, weve got the makings here of a solid weeklong conference on Frege and Kimhi!
Impossible to address all the interesting points and questions, but Ill do my best to respond to folks one by one. Leontiskos up first!
Quoting Leontiskos
The difference is that (1) is an assertion, couched of course in language, about something in the world, e.g. the green grass. (2) is an assertion, couched as affirmation or denial (which could be in symbolic language rather than words) of the sentence used in (1) about the grass.
The irony is that Kimhi claims there is no difference this is his monism. He says theres no logical gap between (1) and (2). But in order to appreciate how he could say such a thing, we first have to get clear on what appears to be the difference. Hope this helps.
Quoting Leontiskos
I know, this is really hard to be clear about. When I suggested adding a nuance to the vocabulary that would separate force from assertion, I was suggesting a possible way to clarify. My idea was that we could then talk about displaying force without asserting. So, to respond to your paraphrase: No, not exactly. I?m suggesting that we should stop thinking of force as something that only an assertion can create. The term assertoric force kind of twists our arm into thinking that theres no force without assertion. So instead, This statement has force [positive or negative predication] even before you pick it up and assert it.
Quoting Leontiskos
Right, but its the introduction of the argument into the function that allows us to claim it exists. I see how you could have read my before we can say whether it exists or not to mean that there would be a further decision process. But no, all Im positing is that, for Frege, ontological commitment can only be shown through his predicate logic.
Quoting Leontiskos
Good questions. If you accept my proposal to disambiguate force from assertion, then we need to clarify the relations among all these terms, which is a headache, not just for Kimhi -- much less so than for Frege, as you point out. Just to repeat the point from above, though: I think Kimhi believes that something can have force (not assertoric force) without being asserted.
Quoting Leontiskos
Hmmm. Well, ?Fido exists isnt a proposition, if I understand Frege. So for that very reason, we dont have to do anything with Fido other than use him in a function in order to claim he exists. We do have to do that much, though.
Can you say more about this point? Its possible Im not following you.
Oh, and about the Novak paper: Your link didnt seem to take me there. Mind verifying and posting it again? Thanks.
And I'm usually so careful about that. At any rate, I'm just using 'statement' to mean 'indicative mood sentence.'
Quoting Leontiskos
Are you using 'statement' here the same way I was, or as 'a sentence that is being asserted'? (Or something else? Everyday terminology does not lend itself to the distinctions we're discussing.)
Sentences is in the indicative mood are of course used to ask questions, give commands, suggest doubt, make wishes, and so on.
Quoting Leontiskos
This is the whole point of my screwdriver discussion. Driving screws is an activity, like making assertions. The favored use of screwdrivers is driving screws, as the favored use of indicative mood sentences is making assertions. But, as I argued, this coupling is loose. So we are right to recognize that a screwdriver is longing to drive screws, and this is the most joy it can find in life, but we still might drive screws without it, or use it for something else. What I'm not sure there's grounds for saying is that the screwdriver itself is always kinda driving screws; it's really not, though that is its special purpose and we are right to recognize it.
Here is the link that was buried in the original post, which I have verified is working: "Can We Speak About That Which Is Not? Actualism and Possibilism in Analytic Philosophy and Scholasticism," by Luká Novák. (Pages 155-188)
Right.
Quoting Banno
In other words, by identifying the two extensional sets as the same, we're able to "make the assertion" that S is Richard's sister without any appeal to some actual act of assertion (i.e. illocutionary act). Have I understood you? And if I have, do you see the addition of the judgment stroke as referring to assertion in this sense? This is one place where Frege confuses me. When he says that the judgment stroke marks "a true thought," does he mean a thought asserted to be true, or one that actually is true? So again, different senses of "assertion" might arise here.
Not to beat a dead horse but this is another exemplar of the pattern I've been talking about. We do generally credit candid speech -- and there's an argument that it must be so for a language to have any consistent semantics -- and it is also true that by and large when we speak we intend and expect others to believe us, but for all that the coupling of understanding and belief is loose: you can understand what someone says without believing it or endorsing it yourself.
Perhaps nothing more, in that simple case. But as this thread demonstrates, "assertion" gets used in some much more complicated and ambiguous contexts. As @Banno points out, above, Frege didn't think in terms of actual illocutionary acts such as the one you're using as an example. And Russell talks about a "non-psychological sense" of assertion whereby we can say that "If p then q" asserts an implication without asserting either p or q. And I would add, though Russell doesn't, that the implication "If p then q" can be asserted on paper, so to speak, without anyone claiming it's true.
I like the screwdriver analogy. ?The grass is green is all set, ready to go -- its "purpose" is what I'm calling its force -- but someone does have to pick it up and use it. A lot of the interest in this thread centers on how best to understand picking it up and using it. The Fregean loosening is also good for him, it is logically necessary that assertion does nothing to sense.
Quoting Srap Tasmaner
This passage from Julian Roberts is worth quoting in full:
I agree with this, and it seems to support your understanding as well. Notice, though, that Roberts puts explained in scare-quotes. Fair enough: Is this really an explanation or just an ontological move?
Quoting Srap Tasmaner
Yeah, and its this overlap thats driving us all slightly crazy! So far we lack a rigorous analysis of how the terms relate.
Quoting Srap Tasmaner
Thats a big chunk of Kimhis argument as well. I was going to save the whole believes that / thinks that / judges that issue for a different OP, but (sigh) of course its relevant here too.
Quoting Srap Tasmaner
Nice to meet another Merrill fan!
I didn't consider for a moment anyone would get that reference!
This phrase, "just an ontological move", is interesting.
My first instinct, as suggested earlier with force and content, is to suggest that what's at work here is not the agent adapting her behavior to the facts of the world, but adopting a strategy to treat this as force and that as content, this as function and that as object. (Frege admits as much when he says talking about functions is treating them as objects.)
The explanation on offer, then, would be an explanation of "how I intend to proceed", how I intend to treat these "things".
Now if you think there is one true ontology out there, you'll naturally ask if functions and objects are really distinct ontological categories; that distinction may be overlooked or abstracted away when it's not of interest, but it lies in wait as an aspect of reality, and this is why we are even able, when we so desire, to distinguish them. The contrary position, I suppose, would be that we "impose" the distinction, it's all in our head, or in our language, or in our culture, whatever. I guess you just deny that any explanation for how we do this is necessary, or you you reach for the magic of consciousness, or something complicated and Peircean.
Obviously I don't know what to say about all that, but I like getting the facts we're trying to explain clear, rather than passing as quickly as possible to the contest of ideologies. To that end, I prefer looking at what people do, and how they think and talk about what they do, to speculating about how things are.
And here I'll add to my previous suggestion: people are very aware of the subtleties of assertion, whether you meant what you said, whether you have committed to a certain claim and can be held to account, etc., and recognize that there are degrees of belief and degrees of conviction in speaking. We put considerable effort into managing these uncertainties. (Think of the conventions surrounding agreement to a contract.)
So I don't really expect an absolute, almost mechanical explanation of what assertion is and how it works, and when faced with a deliberately mechanical system like Frege's I'll tend to see it as a strategy that must be useful for some purposes, with no expectation that it is some total solution to a supposed problem.
Wow, kinda rambled there. Sorry about that.
Quoting Srap Tasmaner
Something like that: "A sentence being asserted (as true)." I avoided the indicative mood language because a statement is only one kind of utterance in the indicative mood.
Quoting Srap Tasmaner
I read your screwdriver analogy as having three points, characterized here:
Quoting Srap Tasmaner
First, the screwdriver has a latent orientation towards driving screws; second, it can be used for things other than driving screws; and third, other things can be used to drive screws.
I am pointing to a fourth point, and it requires moving from the equivocity of the indicative mood to the univocity of statements. The idea is that we never handle statements independent of assertions, even when we are not asserting them. In that way a statement is like a tool with only one purpose. Suppose we put the tool in our shed for storage. In doing this have we used it for an alternative purpose? No, because we are preserving the tool in order that it may be used for its singular purpose at a later date. The storing of the tool is related to its singular purpose, even though it is not itself its purpose.
When I was thinking about tools before you posted about them, I was thinking about the first and fourth points, not the second or third, and the fourth point stretches the tool analogy (which is why I didn't present that analogy). If we wanted to try to fit the fourth point to the screwdriver analogy we would probably say that the form of the screwdriver makes it fit for some tasks and unfit for other tasks, and that it therefore has a limited and determinate range of uses. But analogies aside, the point is that statements and assertions really do go hand in hand (and this holds even if we put the statement in the cage of quotation marks). A statement cannot really be used to ask a question or give a command, apart from its inalienable purpose of asserting. If a statement manages to do any of these other things, it only does so in virtue of asserting, and there is no way to handle or wield a statement while separating it from its shadow, its assertoric nature. I think this goes beyond the three points you were making, and at least qualifies your claim that "the [screwdriver] has other uses." The question is whether the "other uses" of a statement are truly independent of its assertoric nature.
- Yes, I agree.
The petri dish or sandbox metaphor is a bit different. I think this is related to @J's idea that quantification and claims of existence are two quite unrelated things, which seems closer to Quine than Frege. Now presumably everyone in this thread is closer to Quine than Frege on that question, which is an important wrinkle in the thread. Because of this we must take pains to ensure that the thesis Kimhi is critiquing is something that is still widely held, and has not been abandoned.* This is why I am inclined to read some of the critiques as critiques of the propositional calculus rather than the predicate calculus specifically, not because the latter has been abandoned but simply because the former is more widely known and held.
* Inversely, I don't think someone like Banno is being sufficiently careful about the differences between Fregian logic and contemporary logical intuitions. There is a sense in which we must sift contemporary intuitions, such as the Open Logic Project, into its Fregian and non-Fregian constituents, lest we run roughshod over key theoretical distinctions in our pragmatic shoes.
I'm not much concerned about this, but the single most interesting point, and relevant to this thread, is that the assertion stroke disappeared. Frege thought it was necessary and later logicians universally (?) don't. I'm no historian, so I'm not quite sure how this happened. I always assumed that Frege was just wrong, and that we can do formal logic as if there were an implicit assertion stroke at the start of each line. And if we can do that, it becomes clearer that what we're really doing is manipulating symbols according to rules, as when we do mathematics, and interpretation can wait until later.
(On the other hand, natural deduction systems often use some notation for assumptions and their later discharge, I think, so that's a way of singling out formulae you are not asserting simpliciter.)
Now for the hair-splitting.
Quoting Leontiskos
In most cases, but also I think obviously false as a rule. You might own a tool that you have no intention of ever using, an antique gun, for instance. Men have workshops with peg-boarded walls where lots of tools are impressively arrayed and the three or four they actually use are laying on the workbench or in a drawer. I could go on.
This hair isn't worth splitting though, because most sentences asserted are not ready-to-hand like a screwdriver, but one-offs. So there's no sense talking about storage and retrieval in the first place. (Words, on the other hand, ...) Where you do see the same sentence bouncing around repeatedly is in argument and discussion, and in quotation. That means we have the option of exploring whether there are different kinds of assertion; maybe assertion in an argument is a slightly different beast from the sort of extemporaneous sharing of information we do all day.
Quoting Leontiskos
And I'm just not sure what you're reaching for here with "handle", or "independent of", for that matter. Now and then I think you're making a sort of psychological or cognitive point: Hume noted that to conceive of an object is to conceive of it as existing; you almost seem sometimes to be saying that to conceive of a statement is to conceive of it as being asserted. Which might be true, but I don't believe this is what you're saying, or what the point of saying it would be. So what kind of "handling" of statements are you talking about, and how are possible assertions implicated?
We've sort of begun talking about the assertibility of a statement as an affordance, in direct analogy to screwdrivers. But we could instead think of the way simple objects in the Tractatus are said to sort of carry with them the possible states of affairs they could enter into. Just so, a sentence in a given language has what we might think of as chemical properties: there are other sentences it will have an affinity for, and bond with readily to create a narrative or an argument; there are sentences it will repel, sentences that if they bond it will reconfigure both into new configurations with new possibilities, and so on. Philosophers tend to treat statements as having built-in "affirm" and "deny" buttons, but that's surely a somewhat impoverished view, once you consider the wealth of ways sentences relate to each other.
The hairs that remain to be split are no fun: there's
(1) the sentence;
(2) the sentence in a given context;
(3) the elaborated sentence with indexicals resolved by context;
(4) the sentence as uttered;
(5) the sentence as uttered in a specific context;
(6) the actual uttering of the sentence;
(7) all the intentions involved (which Grice admits are infinite, though it's a pretty model and gets something clearly right).
I'm sure I'm leaving some out. I'm not sure which of these we've been talking about, which Frege has, which points made depend on whether you're talking about one or the other and which don't. We may have no choice but to wade into some of this -- though I'll note again that this is the sort of crap you don't have to worry about in mathematics, where Frege's machine is both happy and indispensable.
I'd like to say something useful about this last difficulty but it will have to wait.
I have been meaning to look into this same thing. I plan to look through this Master's thesis, "Frege, Russell and Wittgenstein on the Judgment Stroke."
Quoting Srap Tasmaner
For example, I'll go ahead and note (not assert) that in a mathematical or logical proof, you will often have occasion to rely on statements, derived or not, that it would be odd to call assertions. When you say "And since 2 is less than 3, ..." you're not asserting that 2 is less than 3, you're not claiming that it is, you're reminding the audience that it is, and pointing out to them that you are relying upon this as fact.
* Don't mind the "since" -- the point stands if the previous line was "Now, 2 is less than 3."
Very interesting, and what youre saying about it applies to a lot of issues, not just Roberts here with the separation of function and argument. To stick with that for a minute: I read the passage from Roberts as suggesting that Freges ontological move is a somewhat ad hoc or tendentious solution to a potential problem about psychologism. Its not enough, for Frege, to show that subjects and predicates (arguments and functions) are given an asymmetric treatment in the formal rules of calculation. He also wants to eliminate psychologism as an option for understanding what logic is fundamentally about. Logic is not about the way we think, it is rather a description of the objective structure of thought. By calling a function a thought, Frege wants to rule out the possibility of its appearing in the argument position, as a possible subject of logical discourse. Heres a bit more from Roberts:
Im not sold on the Wittgensteinian leap at the end, but I include it because a number of people on this thread have also noted this similarity. As for the legitimacy of this move, your comments now become pertinent. I agree that Frege is saying, Here is my method, these are the terms Ill use, this is how I intend to proceed. But he seems also to be firm about the ontological difference between arguments and functions. Roberts is asking, Has Frege explained anything, or is he merely declaring his own ?way of going on? We know we can rule out your 2nd option (that Frege would invoke all in the head / language / culture as his explanation), since that would be psychologism on steroids. So what about the 1st? It seems to me this is pretty close to what Frege believed, but again, we want to know why he believed it. Im not sure its enough simply to point out how tidy this makes everything, and how effective a weapon it is against psychologism. Frege was smarter than that. Like you, Im not sure what to say about it, and Id defer to those who know Frege better than I do.
I would also love to return, maybe in a fresh OP, to the wider implications of whether carving the world at its joints (Plato and Sider) is more than an ontological move, understood as something you just declare as useful methodology. A minor topic in philosophy! :wink:
Quoting Srap Tasmaner
Oh heck yeah -- the man was a genius.
Not quite. On to looking at ?. From what I understand, in the Begriffsschrift "?" is an explicit judgement; what follows is known, while would prefix "a mere complex of ideas", un-affirmed (SEP). In the Grundgesetze this has changes significantly; ? now says something like "The following names the true" (SEP). That's much closer to it's modern use, where ?? is "? is a theorem" and ??? says "? is derivable from ?". Notice that in these more recent uses, truth is not mentioned. That's important.
So historically there is a shift from "?" being read as "we know that..." to something with much less commitment. It's akin more to "We can write that..".
Notice also that for Frege there is a structure literally hanging from the ?. So we have
read from bottom to top, for what we might now write as
[math]\forall A\forall B (A \rightarrow (B \rightarrow A))[/math].
In the modern version all the assertive paraphernalia on the left is removed. Along with it goes much of the implication of commitment. (again, stolen from SEP)
Perhaps it would help at this stage to talk about deduction rules such as Modus Ponens. Historically this is thought of as a rule about deriving true propositions; so if ? is true and ? implies ?, then ? is also true. But that's not how it must be understood. Alternately, it can be seen as simply a licence to write certain things down in a game of symbols: so if you can write "?" and you can write "???" then you are, for the purposes of that game, entitled to write "?". And on this understanding, the truth of ?, ? and ??? are irrelevant.
Notice that the supposed "assertoric" implications of the process are here simply absent.
It might be objected that truth is somehow implicit in all this, after all even the Open Logic Project uses the falsum, ?, in setting out propositional logic, and makes use of gothic F and T. But non of these symbols need have the assertic force - they could happily be replaced by any other symbols. Remember the reading of "?" as "bottom"; the whole edifice of propositional logic might be built on "top" and "bottom" as much as on "true" and "false". All that is needed is a pair of opposite that can serve to differentiate the various well formed formula into those we are entitles to write - the theorems - and the rest.
It might also be objected that I'm talking only about syntax here, and that all this disappears when we give things a semantics. But in assigning ? or ? in propositional logic, we are giving it a semantics - since Frege, these are what propositions refer to. The issue becomes more complex with the semantics of predicate calculus, were satisfaction is more complicated, but the point I think remains.
All this by way of pointing out that "assertoric force" doesn't much feature in modern logic for very good reasons. We have the habit now of separating out the illocutionary force from our sentences, as well as setting aside any sense it might have in favour of the denotation (reference). We do this in order to display certain aspects of the structure of our sentences, that we can then examine in far greater detail than was previously possible. And we do it quite self-consciously.
So two things follow from this with regard to what Kimhi might have to say. The first is that while "assertoric force" might have featured in Frege, its place in logic is less prominent now than ever. The second is that the result of setting "assertoric force" aside is a quite powerful discussion, with implications for much of modern life. Kimhi had best present a subtle and powerful argument if he is to convince us of the benefits of doing otherwise.
Okay, yeah, I haven't thought about this in a while, but that's Frege all over. It's pure platonism.
Minor point, but yeah I should have been saying "declarative" all along!
I think we can say this: a world with declarative sentences in it, or a world in which they can be produced, is a world that also includes assertion. A screwdriver is an element in a system of fastening: without screws of the appropriate material and materials to be fastened that screws can be driven into, there's no reason to have screwdrivers. To then take the screwdriver as having, shall we say, significance in itself, would clearly be mistaken.
What that gets us, I'm not sure. If you say, for instance, that assertion "aims at truth" (which, perhaps mistakenly, I suppose is the sort of thing Kimhi will want to say), then a declarative sentence must be the sort of thing that can be aimed at truth, whatever that means. One adjustment to this I would probably make is to say the goal of assertion is to aim someone else at truth -- at what you take for truth, anyway, so that's another adjustment. It's a triangulation: if you imagine yourself at vertex A, observing a truth at vertex B, then you speak to someone else at C to guide their gaze toward the (purported) truth at B.
There is something faintly Fregean about this, because of B. Frege's arguments for the "third realm" were often intersubjective: there is not "my pythagorean theorem" and "your pythagorean theorem" but "the pythagorean theorem"; if I claim that P is true, in order to agree or disagree you must be considering the very same P, else we talk past each other; and, finally, there was the telescope, where we can each in turn view the image on the mirror, rather than viewing the moon directly, but it is the same image we observe -- this to explain the difference between sense and reference, as I recall, and to insist that senses are not subjective.
Yes, I feel this as well.
Quoting J
Well yes, but it is many more than the 'monists' like Kimhi who do not see a difference here. The difference presupposes a certain kind of sentence reification, and this is related to my complaint about thinking about sentences divorced from intentional sense and implicit speakers.
Quoting J
My impression is that you have spoken about assertoric force independent of assertions, and not just force, but I could be wrong about that. For example, if Kimhi questions the distinction between assertoric force and predicate, then the prima facie reading is that there is some kind of assertoric force associated with the predicate. The difficulty about simple force, or illocutionary force, or intentional force, is that it is very vague and seems to take us far beyond the realm of logic. A number of times throughout the thread this idea has been reigned in lest we move into the open sea of super-logical (linguistic) concerns.
Quoting J
Well, "before we can say whether it exists or not," seems to be simply anti-Fregian, given that we can never say that that an "argument" (in Frege's language) does not exist. As Frege said, to say that 'A is B' means that there are B's. We can never say 'A is B' and then go on to decide whether B's exist.
Quoting J
That's right - I agree with your claims here entirely, although I think Frege would go even further and say that there is no reason or sense in "claiming that Fido exists" via predication. Existence in that basic sense seems to be superfluous for Frege.
Quoting J
Okay, but do you see how this reading of Kimhi fails to contradict Frege?
Frege: "Assertoric force is dissociated from the predicate."
Kimhi: "I disagree, because the predicate has force."
Frege: "Unless you say that the predicate has assertoric force, you have not disagreed with me."
Quoting J
I read it as neither, but rather as merely "saying" or stipulating. If Roberts is right then it is an unargued premise. I find this whole line of Psychologism interesting, and Roberts' theories interesting and at least somewhat plausible.
Quoting J
Right.
This is where I see a large and sometimes unnoticed gap between analytic philosophy and scholasticism. The scholastics are quite happy to think about thinking, and are apt to switch into that mode at a moment's notice. If Frege really thinks logic is "a description of the objective structure of thought," then he will have to provide arguments for this thesis, and if he cannot argue about the psychological act of thinking, then he cannot do this.
Quoting J
I tend to agree. I think there is more here.
Quoting J
There are topics at hand that could easily resurrect your thread on Sider, and that might be the easier thing than drawing up a whole new OP. Especially because we don't want too many new OP's on the same constellation of topics.
Useful. :up:
Quoting Srap Tasmaner
Yes, that is a good way to put the point I was trying to make. Note also how philosophical anthropology is implicated, namely the question of whether the human being is capable of truth, where 'truth' means something high or Platonic.
Quoting Srap Tasmaner
And now we are on the edge of the deep waters again, but this is all on point. I am going to try to address some of the points I missed before diving into this headlong.
---
Quoting Srap Tasmaner
No, I agree with this. I was not trying to say that we store and retrieve declarative sentences. The point is that declarative sentences have a unique and inalienable nature. Your later considerations about our capacity for truth also point to their unique importance. The relation between a screwdriver and the act of driving screws is loose. The relation between a declarative sentence and a statement is not loose in that way, and I would go on to say that the relation between these two things and our capacity for truth is also not loose in that way. But again, I don't want to move too fast into this newer and deeper topic.
Quoting Srap Tasmaner
I don't see any problem agreeing with Hume in that even if I would probably go a bit further. But I worry that this tangential "hair-splitting" may have no force against Frege, and so I don't want to develop it too far. It's more that, "Here's something I hold, which sounds a lot like what Kimhi is saying. Maybe Kimhi could be interpreted this way? But I don't see how it intersects with Frege."
Quoting Srap Tasmaner
Yes, I like these ideas. I think this relates to what I have referred to as intentional force, and perhaps what @J has referred to as force. But again, I have no clear sense of how this will intersect with Frege, except for the basic point that Frege simplifies what is not simple.
Quoting Srap Tasmaner
Yes and yes. :up:
Quoting Srap Tasmaner
Yes, this looks like a kind of presupposition or premise in the way it functions logically. Our context and aim will determine whether such distinctions are necessary, but in a way you have already pulled the curtain on the obvious and difficult debateand that visitor was at the door from page 1. It is something like the realism debate, colored by your pragmatist approach.
Quoting Srap Tasmaner
Yes, but Frege and Kimhi do not seem to be at odds on this point. That's not to say it's not worth talking about. My next post will hopefully be on Frege's judgment stroke, and whether that idea had any lasting effect.
In the mind is the sense that "the sunset is red", and in the world is the referent that the sunset is red.
Frege argues that a proposition can have a sense in the mind even if there is no referent in the world. Khimi argues against this.
This is not a problem for the Indirect Realist, for whom the world exists in the mind, meaning that a referent in the world exists as a sense in the mind. Unity arises in thought, thoughts about sense and thoughts about referents.
However, this is a problem for the Direct Realist, where referents in the world can exist independently of being observed. EG, for the Direct Realist, sunsets were red prior to the existence of any observer thinking that "sunsets are red".
How does a Direct Realist support Khimi and explain a unity between a sense in the mind and a referent in the world when these are independent of each other.
In other words, can there be something in the world having a force, such as a red sunset, prior to it being asserted by an observer that "the sunset is red".
Quoting Banno
What's the better way to understand this? Is the problem that I'm still thinking in terms of assertions, which, as the rest of your post shows, are no longer much needed in logic?
Okay, good. I want to have a proper look at it today, but I think it may be helpful to bring the question into sharper relief first.
Quoting Leontiskos
@Srap Tasmaner - Similar to this, the Original Post tries place Kimhi's thesis in a cage so we can talk about it without talking about Kimhi (and for good reason!), but this can never be fully carried out by those who do not understand Kimhi's thesis as well as he does. I want to bring him in a bit given that we are trying to sort out how Kimhi's critique relates to Frege and the tradition that follows Frege, especially with respect to the dissociation of assertoric force from predicate.
In the other thread a useful review of Kimhi's book came up, which is publicly accessible and gives the very large scope:
Quoting Review of Kimhi's Thinking and Being, by Jean-Philippe Narboux
It is hard to quote from Kimhi's book on this topic, as the topic is very complex and interconnected to other issues. For those with access to the book, or who want to use a preview site like Google Books, two places where it seems to come up are page 37 and following, and then especially page 82 and following.
Here is an attempt at some relevant quotes:
This proposition is what Kimhi calls "Frege's observation" (which is in fact enunciated by Peter Geach):
(See here for footnote 27)
Isn't this just the difference between validity and soundness? In computer science, for example, all that matters is the structure can be parsed using the correct language structure to manipulate the 0s and 1s when it is compiled to machine code/binary. That doesn't convey truth. Something else needs to be added.
Ugh, are we Wittgensteining Banno now? I'll let Banno reference himself (I'm waiting for him to copy and paste your text :razz: ).
Ok I read @Banno's post. Yes, I think I agree with all he said there as to how emphasis on "truth" has been put aside for emphasis on proper structure and rules. I think it parallels what I was saying pretty much. But my question is rather, the question at hand (or so it would seem), "WHAT" criteria needs to be added to make it truth? Is it just default "judgements made from some amalgamation of verification and/or falsification principle"?
Shrug. That's how simplification works. It's a model; all models are wrong.
Quoting Leontiskos
For instance, my little triangulation model is waaaaaay simplified.
I always read the "language-game" analysis as an expansion of the context principle, so I have some sympathy with this view.
I do want to note the alternative approach, though, which is Grice's, and which I also have considerable sympathy with. Grice distinguishes sentence meaning from speaker's meaning, and defends the usual logical analysis of the meaning of a sentence as essentially correct, even if in a given context a speaker means something else by saying it.
An example I've used before: you're driving somewhere with a friend and ask, "Should we stop here to eat?" Your friend checks his phone and says, "The next town is like 70 miles." What he means by saying this is "yes", but that doesn't change the meaning of the sentence he uttered or of any of the words in it. --- Nor is "yes" logically implied by what he said; it is only implicated, and he might in fact be willing to wait.
I say all this because if you want to identify the meaning of a sentence with its use, as a move in a language-game -- what I think Kimhi might be pointing at with "actual occurrences" and so on -- you can get speaker's meaning right but skip entirely over sentence meaning, which in this case is a verifiable claim about geography.
It does seem like the principal subtext here is the picture theory of the Tractatus and its abandonment.
I'll go back over it, just to chaeck we are on the same page. I's said
Quoting Bannoand that FregeQuoting Banno
The point is a straight forward one, I hope.
Consider
and
Since {Ruth}={Richard's sibling}, extensionally, these arguments are the same. Whatever "force" there is in "Richard's sibling" drops out of consideration.
How Ruth is identified is irrelevant to the syllogism. All that counts is that Ruth satisfies "...is in Sydney".
But what is dropped here is not an illocutionary assertion. What is dropped is the sense, as used to make the identification. It seems that it must be something like this that Frege meant by dissociating the assertoric force from the predicate.
So you suggested Quoting J
And that's roughly right, but not quite what I wanted to draw attention to with talk of the extensional aspect fo Frege's logic.
I suspect Frege would not have been able to make the distinction between illocutionary force and what might be called "intensional" force, between the way a sentence is used to make an assertion and the way in which a sense is used to identify an individual. This distinction was made much later.
I've also suggested a seperate point, which I will try to clarify. When one looks at
[math]\vdash\forall A\forall B (A \rightarrow (B \rightarrow A))[/math]
with the much reduced use of space. Frege was asserting this, the whole illocution. In Begriffsschrift, it was within the scope of something like "I know..."; in Grundgesetze it was something like "this is true:...". I would suggest that now, the "true" part has faded, and although it is still used, it does not have the force it once had. I suggest it's more akin to "We are entitled to write...".
It might be objected, as I mentioned, that this treats of syntax and not semantics; that to look at soundness and completeness we must assign truth of falsity to the various well formed formulae. But truth and falsity are there defined in terms of satisfaction. We could get the same result by assigning any pair of terms - top and bottom, up and down, flipped and flopped.
The use of "true" and "false" in the development of propositional calculus might seem to imply that some formula are being asserted. But it ain't necessarily so. Further, it's satisfaction, not truth, that decides which formula are to be preferred. And I think that is the case of first order logic as well.
Which is not to say that making assertions is not something we can do with these logics. And indeed, that is the usual use to which all this structure is put. But use is something added on top of the logic. It's just not at the core, which is about manipulating symbols.
Edit: Some of the stuff I've read here (not by you) leads me to think that there are folk who suppose that each part of a theorem is being asserted, as if in
1. ???
2. ?
3. ?
each line must be asserted separately, or even that the "?" in "1. ???" is being asserted. But this need say nothing about wether (1) and (2) are true. What's asserted is the tautological whole of ?(((???) ^ ?)??). That's something Frege's approach makes clear.
I don't think so. Asserting that ? is true is different to asserting that ? is sound or valid. Not that ? on its own could be either sound or valid. So I'm not sure what you mean.
So this is too much technical parsing.. A "formal argument" having a "valid" conclusion and "sound" premise in many circles would be required for "TRUTH" to be claimed.
In regular conversational parlance, a PROPOSITION can be true or false. So either way, I think the TRUE of a propositional statement (the grass is green), and the TRUE of an argument's soundness (the premise 1 : the grass over there is green if I can see that it is green. Premise 2: I see that it is green. Conclusion: The grass is green.
The question at hand that I am asking, "What counts as it being TRUE", would be valid for the proposition "The grass is green." And the premises of a formal argument about the grass being green.
What counts as being true is being satisfied, under some interpretation.
So if you are talking about Australian Summer, grass is brown.
Point being we can pretty much drop truth for satisfaction.
What you say here is too simplistic, but there is something to it. In section 2.1.3 of, "Frege, Russell and Wittgenstein on the Judgment Stroke," Rombout is discussing the difference between an inference and a consequence. Frege's Grundgesetze is quoted:
Quoting Frege, Russell and Wittgenstein on the Judgment Stroke, by Floor Rombout, p. 14
What's interesting here is that in favoring inference over consequence Frege adheres to an older tradition, and in my opinion thereby avoids some the errors of modern logic-as-mere-symbol-manipulation. Before J's thread on QV I had mistakenly believed that this modern approach could be traced to Frege.
@Banno's posts are indicating that he doesn't like Frege's emphasis on truth given the way it disagrees with modern logical practice, but this seems to have little to do with the OP given that Kimhi is in no way critiquing Frege for his emphasis on truth or inference. Kimhi is not saying that there is a problem with Frege's judgment-stroke because judgment is no longer part of logic. Kimhi seems to agree with Frege that judgment/assertion is essential to logic. Banno's focus on this issue would seem to derive from his own personal interests rather than from the OP.
To me this just means "context matters". But in almost all instances, it seems when we are saying "true" about a proposition (or by extension a premise in a logical argument, leading to its soundness), then we are saying something about the verification and falsification principle. Thus:
a) Grass is green
If made as a categorical/universal statement about grass can be falsified that indeed under some circumstances it is not, usually via empirical means.
b) THAT grass (right now, right over there) is green
If made about a specific instance/case/existential quantification of grass can be said to be green if it is verified through empirical means.
But in almost any case here, we are almost always using some empirical verification/falsification aspect to these kind of statements for truth (or if you want to say "satisfy", I just see that as a specific context of truth in X circumstance).
Now you may say the truth changes based on how it is satisfied (in various circumstances.. or how it is "used" if you want to say), but in all these cases, it seems to be empirical verification of some sort that counts as what is "true".
So all good stuff here, but my question at hand here is what is the criteria for truth, for Frege or otherwise. We all seem to be circling in agreement that it isn't just symbol manipulation. You mention "judgements" for example. What are these judgements? What shall the be composed of? To Frege. To others...
Isn't it about judgements of truth versus simply finding the right logical architecture? And if it is about judgements of truth, I would think that that criteria would be of utmost importance.
Quoting J
It is that last part I am trying to focus on.. As clearly Frege believes it and Kimhi agrees.
I think the argument has been that Frege believes this must be so, and Kimhi claims it ain't necessarily so, but sometimes it is. I haven't wrapped my head around what is supposedly the main topic of this thread yet.
Quoting schopenhauer1
This phrase "criteria for truth" -- what could that possibly mean? How can anyone have one of those?
Eh, I probably don't have it, but when I look at it, it looks like Kimhi is accusing Frege of treating something like, "Sky is blue!" no differently if it was an actual assertion of something else, that would later be parsed out if we understood the real world context. In other words, we need real world context, and probably why @Banno mentioned the notion of "satisfaction".
Quoting Srap Tasmaner
This is more what I'm interested in, because I think at the end of the day, this is what the questions here circle around. What makes an assertion true... I think it's a lesser question whether the statement itself is being offered up as an assertion or something else.
Sorry, I didn't understand a word of that.
The real-world context of an argument matters. That's the gist of it.
Right:
---
I think I am starting to get a sense for the sub-thesis of Kimhi's that the OP is talking about. He is saying something like this: "Frege sucks all of the assertoric force out of its natural context within a statement and then plops it at the beginning of the declarative sentence in the form of a judgment-stroke." Further:
(See the review and quotes from <this earlier post> for context)
Another summary of the project can be found in the following excerpt, and note that Kimhi is fond of the quote from Wittgenstein in the footnote, which occurs a few times throughout the book:
The obvious question is then, "Isolating the assertoric force in that manner is admittedly strange, but what's the concrete issue here?" I have some ideas but no clear answer at this point, but what I want to say is that this critique of Kimhi's applies to post-Fregian logic as much as it does to Frege. These "functionalist/compositionalist assumptions" are alive and well. That is, propositional logic apparently still dissociates assertoric force from sense in this more subtle manner. This then helps to answer the question that many of us have been asking, "Supposing that the judgment-stroke has been dropped in the meanwhile, does Kimhi's critique apply to anything after Frege?"
I think this does raise the question, "How exactly does post-Fregian logic conceive of assertoric force?," and I am hoping that a clear answer will be found in that Master's thesis, "Frege, Russell and Wittgenstein on the Judgment Stroke." On the face of it it would seem that assertoric force moved into a metalogical position. (Note well that assertoric force (or judgment) and "truth" conceived as the '1' value in the internal 0/1 binary system of propositional logic are two different things, and Frege's recognition of this fact is part of what caused him to include the judgment-stroke in the first place.)
(@J)
Kimhi speaks about motives which he shares:
Kimhi's index contains 50% more references to Wittgenstein than Aristotle, both of whom are surpassed only by Frege.
I don't actually know Wittgenstein very well. Can you say a bit about his picture theory and its abandonment, and how it might relate? Kimhi seems fond of the theory, and I'm not sure he wants to abandon it wholesale. He notes that there are different interpretations of Wittgenstein.
Ahh, the light goes on. Got it, thanks.
I recommend we adopt this, for purposes of this discussion, as a reasonable consensus on criteria of truth etc. The huge potential area of disagreement would center on whether "some interpretation" is the best we can do, of course, so it leaves out some meta-philosophical issues, but we cant get distracted trying to work out a Theory Of Everything.
Or we can just agree to disagree about what makes a statement true, and stay focused on the Kimhi-inspired challenges to Frege.
Could you say more about this? Im not sure what sentence reification would be.
Quoting Leontiskos
No, youre right. In part, this thread for me has been a process of clarifying terminology. I now think its better just to speak of force understood as positive or negative predication rather than using the term assertoric force. This (my) sense of "force" might be close to what youre calling intentional force, but Im still not sure whether you mean intentional or intensional. Interestingly, either meaning might apply on this point!
Quoting Leontiskos
Theres an important question here. Yes, once an argument is attached to a predicate, we say it exists. But the question is, What was the status of the argument term before something was predicated of it? A rather Zen-like question, but what Im arguing is that an infinite number of nouns (just to simplify it to nouns) are floating around in our language, their status unknown. To place one into a function grants it existence in the only way that Frege thought made sense. So I do think its meaningful and important to speak about entities/nouns that may or may not exist it will depend on whether they become arguments in a function. Frege, on my reading, never disagrees with this. He is always talking about what we can say, that is, make grammatical propositions about. ?Grass is a word. The moment we try to do something with it, predicate something of it, we are inducting it into the world of things that can be talked about, that can be said to exist. Its not so much that Frege thinks some magic is at work here that brings objects into existence ; its more that his attitude is, Well, if you dont think it exists, why are you saying things about it? That's the sense in which he "assumes" existence, I believe.
Quoting Leontiskos
Yes, youve got it, as your later post with the extensive Kimhi quotes shows. Kimhi agrees with what he calls Freges observation but not what he calls Freges point. His line of dialogue should read, I disagree, if youre saying that the only thing which gives the predicate its force is assertion. But as I read you, you neednt be saying that at all. Thats a conclusion that Geach and other Fregeans have imposed on you. And thats what Ive been saying too.
Quoting Leontiskos
Im afraid this is probably true, but Im still going to avoid as much of Kimhis terminology as possible, out of consideration for others following the thread. The good reason! you mention isnt just his odd use of singular terms like syncategorematic, but his whole style of writing, which is dense, lacks examples, and asks you to remember his labels for complicated arguments (Freges observation vs. Freges point, for example). I agree that the ND review is a help. And everything youve cited from Thinking and Being here is absolutely on the mark, and important; Im just afraid it will be opaque without context and a lot of reflection.
I guess my question then is thus:
I have a thread about uninteresting philosophies.. My criteria for this is pedantic minutia-mongering and/or it takes common sense notions and makes it "write large" (as if it is profound revelation).
Curious, I know you find the topic interesting, but can you see why this might fall under those categories? I guess what I am trying to ask here for what Kimhi is saying about Frege is, can you find the important point that makes this interesting?
I'll make my own attempt at elevating this topic (to my own standards of interest)...
Frege created a system of logical symbolism whereby we can parse out various categories of a statement so that one can understand that we are referring to the same object, but with different senses.
However, his system seems to neglect the important question (one would think!) which is to say, "How do we know which propositions are true propositions?". And this question, the important one, is missing from Frege.. In fact, it's a throughline missing throughout some analytic philosophy, up to and including Wittgenstein's Tractatus (at which point he combines Russell's theory of atomic objects and such). It certainly is felt in later Wittgenstein, for example, in language games, and "context" (use). So, as far as I see Kimhi's critique as being interesting or relevant beyond some picuyunish ones, is that he is saying that analytic philosophy often loses its way when it doesn't focus on the older tradition of discerning TRUE propositions, rather than focusing on purely on language structures and how they are most clearly communicated to understand their sense and identity and things such as this.
I sympathize! I thought you yourself gave it the best interpretation, in your elucidation of the difference between affirming a statement and making a statement about the world. In the first case, were saying something about p, a bit of language, as Kimhi calls it. In the second case, we are creating a proposition, p, which states what is the case in the world; the world, of course, is not made of language. And the Kimhi-inspired challenge is trying to tie this back to Fregean notions of what can and cant serve as the argument of a proposition. This is where the dreaded categorematic / syncategorematic distinction comes in, but Ill fight to the bitter end against using those terms if I can present the idea more simply.
As for the quoted exchange with @schopenhauer 1, I think Frege and Kimhi are in agreement here. What Kimhi believes to be importantly controversial is not the separation of sense from (T/F) assertion, but the crucial difference between how logic treats statements of affirmation/denial vs. propositions. In a manner that I too am still struggling to grasp completely, he thinks that Fregean logic presupposes (or is it imposes?) a dualism that is artificial. One way he puts this is:
I added judges, asserts because Kimhi is often unclear whether he wants thinks to mean thinks truly and/or thinks that __ is the case or simply "has the thought in consciousness." In this instance, I believe any of those three senses of "thinks" would be part of the point he's making.
This is his psycho / logical monism put quite plainly.
Quoting Leontiskos
Looks like were at a similar place, then. I phrased it as Is this just playing with words? but its the same question about what, if anything, important follows from this. I have spent the least amount of time, so far, on final essay/chapter of Thinking and Being, which is called On the Quietism of the Stranger (referring to Platos Sophist) and takes a decidedly enigmatic, even mystical, turn, in a way that does remind me of Wittgenstein. I need to read that chapter more carefully before weighing in on what the point of it all might be. And, more down to earth, that Rombout thesis looks really good and should be a help.
About your elevation: For you, the question of truth is important, so if we can phrase the Frege/Kimhi discussion in terms of truth, that will make it of interest. Well, Im interested in truth too, but I dont see Frege or the analytic philosophers abandoning that question. Indeed, I can hardly think of a more written-about and argued-about question in my lifetime. I think its possible that you have a definition of truth which isnt shared by, e.g., Frege, and therefore it appears that the topic itself is missing from his writings. But a huge meta-question in anal phil (sorry, couldnt resist) is not just How do we know which propositions are true? but How do we decide what truth refers to, what we can say about it, what logic might tell us about it? etc. etc.
So no, I dont think Kimhi is saying that analytic philosophy often loses its way when it doesn't focus on the older tradition of discerning TRUE propositions. Now it may well be that, if we can absorb Kimhis ideas, well wind up with some important things to say about how to discern truth. But that is not his focus. He does indeed argue that anal phil was wrong from the start in creating a sort of dualism between what can be thought and what the world contains, but thats different. He wants us to recognize a unity here. Where this might take us in terms of understanding truth, Im not yet sure.
I mean, I think this actually contradicts your assertion here:
Quoting J
Rather, from what I've read so far, it seems Kimhi is trying to say that philosophy has to go back in a way to WHAT COUNTS. What counts? Things like Parmenides project (how is the one many?), etc. It seems like a sub-category of a kind of viewpoint about philosophy excoriating it for not getting back to the fundamentals of being, metaphysics, ethics, and discerning what is true and what is not. Rather, if one is lost in the world of parsing sentences (Frege, early Witt, Russell, et al) or even simply understanding how a sentence fits into a context (late Witt, postmodernists, etc.), then we are not getting to what matters (what is the world really? What are the fundamentals of reality? etc.). Again, this is just my interpretation.
If this helps, this NYT article seems to summarize pretty nicely Kimhi's main claim:
Quoting https://www.nytimes.com/2018/09/26/books/review/irad-kimhi-thinking-and-being.html
There is a temptation in this thread to anachronistically place some variety of current logical practice prior to Fregian logic. @Banno has been exemplifying this in his methodology by making his own conception of logic the norm against which Frege is to be measured. Banno seems to be trying to give a course on logic, saying, This is how you do logic, and these are the ways that Frege deviates from logic. One thing Rombout addresses is the differing conceptions of logic between Frege, Russell, and Wittgenstein. Banno's conception of logic includes things like this:
Quoting Banno
This is an interesting thesis that Banno is presupposing, but in fact it is a thesis that Frege, Kimhi, Aristotle, and presumably even Kimhi's interpretation of Wittgenstein all disagree with. A thread which argues for that thesis would be interesting and popular, but that debate has nothing to do with Frege and Kimhi. A logic which presupposes judgment is something fundamentally different from a logic that does not. Frege and Kimhi both maintain that logic presupposes judgment. A methodology which simply presupposes that Frege and Kimhi are both fundamentally wrong reflects a desire for a different OP, a different thread.
Of course one will approach Frege and Kimhi through their own lens, but we must avoid pigeonholing them into our paradigm, especially given the way that Frege is a historical antecedent of lenses like Banno's.
(I had already anticipated this problem in <this post> and others within that thread)
There are a number of posts I need to respond to, but at this point I am inclined to think that we have been on the wrong scent all along. I am starting to think that the sub-thesis of Kimhi's that the OP reflects can be accessed through a consideration of these two assertions/statements:
[hide][/hide]
And for reference, consider also a declarative sentence (as @Srap Tasmaner has usefully called it):
...Where "[math]\vdash[/math]" is Frege's judgment-stroke combined with the horizontal stroke, and "" is Frege's horizontal stroke.
Much of this thread has been comparing FG to FGH, and conceiving of KG in terms of either FG or FGH. That's understandable, for we are probably all Fregians.
But KG is not FG, and this is not merely because Fregian predicate logic struggles with individuals. KG is not FG because KG is pre-Fregian (i.e. it is Aristotelian). Again, both KG and FG are assertions or statements, but their assertoric natures differ considerably. The assertoric nature of FG consists entirely and only in the syncategorematic [math]\vdash[/math]. The assertoric nature of KG is at least centered on the verb 'is', but the entirety of the sentence is required in order to understand its assertoric nature. Like Humpty Dumpty, once KG has been separated into FG and FGH it becomes very difficult to put the pieces back together again and find the wholeness of KG.
...I have limited time at the moment so I am going to leave it there instead of trying to make the differences between KG and FG more clear and precise.
Quoting Leontiskos
Or in Frege's own words:
Quoting Frege, Posthumous Writings, 192
I missed this until now.
I mentioned earlier that a sentence such as "it is raining" can be mentioned without asserting its truth, while to use the sentence would seem to be to assert its truth. I also see that there is a sense in which such sentences have an inherent assertional logical or grammatical structure. Is there any more to it than that?
Well, that's the thing. You're talking about Frege says about his system. And I'll grant you, the first version of the system we all know now as "classical logic" included some notation that Frege thought important, which it turns out had so little to do with how the system was actually used that it disappeared without a trace, leaving the system essentially unchanged. You're right that Frege might not see it that way, but the facts on the ground tell a different story.
What's ironic about this story, is that it's as if we're talking about Frege's "interpretation" of the predicate calculus, considered as a system of symbol manipulation, which in a sense is precisely what's at issue. That means each side can retreat to their preferred view and consider the other misguided. Not a great result. (And of course a third party might see the dispute as "merely verbal".)
I'm going to propose what I hope is an alternative view in a separate post, so as to please no one.
Would it be better placed in the thread that generated this one? Or else the Quantifier Variance thread?
Many of the broader issues that people want to discusswith positions which presuppose that both Kimhi and Frege were wrong from the startwould seem to be better placed in one of those earlier threads. These questions of logical nominalism and logical pragmatism are certainly interesting, but I don't see them as relevant to this thread and I don't know that others who would be interested in discussing them will look for them in this thread.
Ultimately I would love to see such presuppositions presented as theses in a new thread, but those older threads would also be an option.
Edit: I get it: Kimhi is opaque and (literally) inaccessible. So then the TPFer reads Frege, inevitably disagrees with Frege, and wants to express how and why they disagree with Frege. Still, given that the topic of the OP is not dead, I think tangential critiques of Frege along the lines of logical nominalism or pragmatism are better placed in the other threads where they are more relevant.
I don't even want to talk about Kimhi, so new thread it is.
Behind that distinction is the claim that asserting something and affirming a sentence are two different things. But what else does it mean to affirm a sentence than to assert something? And how do we assert something without sentences?
You seem to want to say that when you say, "The grass is green," and I say, "I affirm the sentence that J has just asserted," we have done two different things. In order to say this we must reify the sentence and say that an affirmation of the sentence is not the same as an assertion of the sentence. I have never been able to make sense of this move. I see how we can speak about a sentence qua sentence, but I don't see how we can affirm a sentence without asserting it, or what that would even mean.
Quoting J
Okay, but I think you were right to speak about assertoric force. I think what is at stake is assertoric force specifically, not more general considerations such as force or illocutionary force or intentional force. Continuing:
Quoting J
So Kimhi doesn't disagree with Frege after all? He only disagrees with Geach? Then why does he call it "Frege's point" instead of "Geach's point"? No, Kimhi is explicit that he is critiquing Frege and Geach:
Quoting Kimhi, Thinking and Being, 38-9
This is the sort of mistake that occurs when one tries to make Kimhi speak about force rather than assertoric force, namely the mistake of claiming that Kimhi is critiquing Geach but not Frege. I worry that Banno is leading you into a pit.
Page 44 seems to be very good evidence against your view, for Kimhi presents a passage where Frege attempts to show that (assertoric) force is stripped from an assertoric sentence when uttered by an actor in a play, and Kimhi goes on to arguein a manner very similar to what I have argued in dialogue with Srapthat the assertoric nature of the sentence is still present in a latent sense. I would argue that each time 'force' appears on that page, it is just shorthand for 'assertoric force', and that in his final paragraph Kimhi consummates this by speaking very explicitly about assertability and assertoric force.
Quoting J
That's right, and therefore it does not make sense to ask Frege about the status of an argument term before something is predicated of it.
Quoting J
I don't think you're grasping the seriousness with which Frege excludes existence as a predicate. My second quote here literally has Frege explaining why it makes no sense to speak about the existence of entities or the non-existence of entities. I don't see how this claim of yours can be saved:
Quoting J
If "before" means "before" and "say whether" means "say whether," then Frege will deny this claim.
You apparently want to say, "The grass is green, therefore the grass exists." For Frege, "The grass exists," is always uninformative or empty. It doesn't matter that it is presented as the conclusion of an argument. Therefore the inference is not substantial, and for Frege is no better than, "The grass is green, therefore the grass is green." The redefinition (or eradication) of existence-predication is total. See Novák, who is explicitly focused on this topic.
Now I don't know that Kimhi's sub-thesis that this thread is considering requires us to understand Frege's position on existence as a predicate, but it is possible that I am wrong. The reason I brought some of this up is because I see an Aristotelian argument against Frege, but I am now unconvinced that it is Kimhi's.
Quoting J
That's fair, but the concept of the syncategorematic may need to be introduced, even if the word is not.
If folks want to circumvent Kimhi it may be possible to do so via Aristotle or Wittgenstein. I tried to provide a handle by pointing to Wittgenstein here.
---
Quoting J
Okay. :up:
Quoting J
Yes, it's a good question.
Banno is clearly incorrect:
Quoting Banno
The assertoric force of Frege's judgment-stroke is one kind of illocutionary force. Therefore Frege is clearly thinking "in terms of actual illocutionary acts" such as @Janus' assertion.* Frege need not be thinking in terms of the various illocutionary forces that we now recognize in order to be thinking in terms of the illocutionary force of an assertion. Even Banno recognized that assertion is part of illocutionary force in his first post:
Quoting Banno
And the idea that Frege did not distinguish assertoric force from sense and reference is simply wrong.
* See Rombout 2.1.2
Ok., good. Before I go on if it seems worth going on I might go over what I'm up to. Again, I haven't access to Kimhi, so can't address the book directly. But then it appears that you are after a better understanding of the context anyway, so rehearsing Frege may be useful.
So at issue is something to do with force, but what is contentious.
In my first post I went over illocutionary force, which we can differentiate from the propositional content of an utterance. Frege, and logic, moved from prefixing"I know..." to something more like "I can write..." over time. To be sure, what Frege does is not to set illocutionary force aside so much as to set it as the default in which all his formulations are couched: his judgment-stroke.
Setting illocutionary force aside allowed a focus on other aspects of language within the scope of illocutionary force.
In my second post I reviewed sense and reference, that we can use different and diverse words to talk about the very same thing, but for our purpose in doing the logic at hand what counts is the thing, not how it is differentiated from other things. So 'Venus' and 'Hesperus' are to be teated as picking out the same thing, and 'Ruth' and 'Richard's sibling' similarly pick out the very same person.
This led to the third post, in which I hope I made it explicit that what setting aside sense and keeping reference allowed us to do was to develop an extensional logic, allowing for developments that allowed truth to be set out in terms of satisfaction.
Looking at the process in reverse, we have some structure to which we give an interpretation, a sense and a use. Satisfaction, and so to a great extent truth, enter into the process if at all at the level of interpretation.
So now back to your OP. You talk of a two-step process, the first step is the observation that "...logical or functional sense is a feature of repeatable occurrences of p", the second that "...a proposition cannot contain assertoric force as part of its logical structure"; and the conclusion is that "...assertoric force is necessarily dissociated from predication".
I'm understanding the first to be something like that the "a" in
is the same in both occurrences. Without this, it would be hard to do anything that looked at the structure of our sentences; indeed it'd be difficult to understand how language could function if this were not so.
The second is perhaps what inspired Frege to place the assertic element the judgement stroke so that his logical expressions sit within it's scope. It's a clever move, setting the force aside so that we can focus on other structures.
The conclusion I suspect is too strong. I'm not keen in including "necessarily". Seems as what is needed is just to be able to set the force to one side in order to consider the propositional content. So I'd say "...assertoric force may be dissociated from predication".
I think this sort of thing quite central to logic. Earlier I reminded us that "the grass is green" could be an assertion, a question or a command. Which, depends on what is being done with it. Similarly, there are many ways to parse the same sentence in logical terms. So we might, if our purpose is general enough, need do no more than to parse "grass is green" as "p", a single proposition. That's all we would need to include it in a simple argument. But if we need to bring out a different aspect, say that all grass is green, we might present it as U(x)f(x)?g(x) for all x, if it is grass then it is green. Or we might treat "...is green" as a predicate and "grass" as a noun, and just write "g(a)" grass is green. We might even pars it as "?x((Grass(x) ? Green(x))", roughly "something is both grass and green", safely leaving it open for grass that is not green and green things that are not grass. The point being that "grass is green" can be understood in many, many different ways. It would be odd to think there was one, true parsing. We pars our utterances differently depending on what aspect of them we would focus on, sometimes focusing on illocutionary force, sometimes on truth value, sometimes on differing quantifications, and so on.
Anyway, that will do for now.
Quoting Srap Tasmaner
:lol:
Agreed. Good analysis. I'd only add that whether there is indeed a "wholeness of KG" is a central question, and Kimhi is trying very hard to argue for it, using pre-Fregean concepts of logic.
I'll put my original Step 2 here so we can have it in front of us:
Quoting J
Does this amount to an argument for the necessity of Frege's separation? I thought it did, on the grounds stated: We've got to have all repetitions of 'p' as identical, but if some of them have assertions "built in," then it wreaks havoc with synonymy, inference, etc., as Step 1 seems to show. But perhaps my conception here is too narrow.
I don't get why the "judgement stroke" shown at the beginning of the claim matters so much to Kimhi.. What am I not getting.. This is almost the definition of minutia-mongering to me..
"The grass is green", and rephrasing it in another way whereby it is indicated by a symbol that this is a judgement, seems like a bafflingly tenuous thing to take umbrage to.
If his point is that propositional logic takes the context out of the equation and thus makes the subtleties of human life distorted due to the logic, okay... But it's simply a tool, and can probably be used in a number of manners that can make it fit. But maybe I am not seeing how insidiously wrong Frege's analysis tool is..
@Pierre-Normand has found a very good short review of Thinking and Being here: unpublished review essay by Owen Boynton. I actually have a lot to say about it but time is tight, which brings me to the other thing I wanted to say:
I don't know if others have this problem, but I always feel like I ought to reply to interlocutors on an interesting thread as quickly as possible, maybe especially when it was my OP. Part of me knows there's no rule about this, and the fact is that I often can't because I have this Other Life where I have to go places and do things. No big deal, of course -- none of us is so terribly important to the others -- but I thought I'd just say it out loud. Right now, there are a number of points I'm eager to address but you won't be hearing from me till tomorrow at the earliest.
Yes, that's right. But it seems clear enough to me that the assertoric nature of KG is different from the assertoric nature of FG. That is where I think one should begin, and it moves us into the syncategorematic question.
---
Quoting schopenhauer1
That's an understandable read. But as Aristotle noted, small errors do add up over time. Kimhi is thinking in terms of decades and centuries.
Quoting schopenhauer1
Not for Frege or Kimhi (or Aristotle). If Kimhi or Frege thought logic were just a tool or an approximation or a pragmatic matter, then Kimhi's book would be completely moot.
To be fair, Aristotle would probably admit that his "syllogistic" maps human inference only imperfectly, but if you read that syllogistic in context it is not meant to be self-supporting.
---
Quoting Banno
You are still conflating Frege with your own approach and a post-Fregian trend in logic. Frege never does this. See Rombout, sections 2.1.2 and 2.1.3. Frege never prefers consequence to inference. In fact he explicitly opposes such a move. For Frege such an approach is, "playing with mere words."
Quoting Banno
Not for Frege. Not for Kimhi. See, for example, the abstract of, "Truth and Satisfaction: Frege Versus Tarski."
The problem with all this is it seems very much arguing abstractly.. like we are arguing over something that doesn't seem to have a real "center". WHAT exactly is Kimhi proposing.. Logic is part of thinking and being.. Okay, but WHAT does that really MEAN. I get he criticizes Frege for making logic more of a tool of analysis rather than tying it to human "use-contexts", or whathaveyou (or I think that's his complaint), but what of it? What is the real insight here that is profound, insightful, or meaningful? Why would his work matter?
And if it goes back to some more minutia about Frege, I think you have not quite got what it is that would answer this question.
That's very kind of you to highlight. I'm not expecting responses personally, and I encourage you - as a mod - to take whatever time you need to respond. Your posts and the discussion you have fostered here are a model in both content and conduct.
An example. Consider two predications: "Grass is green" and "J believes that Grass is Green". We might perhaps happily remove the assertoric force from the first "grass is green", but not so much from the second. That's because it is within the scope of the belief. It's extensionally opaque.
Now "It is raining" presumably is the same in both.
I don't wish to rule out a logical analysis of such belief statements. So I don't wish to say that the force, in this case a belief, must necessarily be dropped. There's no need for such a broad preemption.
This is by way of leaving open the possibility of say formal treatments of belief, doxastic modal logics, or analysis of belief revision.
And yes, this "wreaks havoc with synonymy", so that Davidson for example splits such belief predicates into "p" and "J believes that p" to bring out this very issue. The repetitions of "p" here are not identical - one is a proposition, the other is a name in a different proposition.
If you like, I would maintain the possibility of treating such utterances logically. So your rule might apply within a first-order logic, and so for Frege, but not for higher order logics in which we predicate with other propositions.
Anyway, given my tight wallet and the absence of a clear account of what Irad Kimhi has to say, I've probably finished with my comments. I'll keep an eye on developments.
Quoting Michael Dummett: Frege, Philosophy of Language, page 304
(My emphasis.)
I'm not falling down it. Maybe I need a push?
Yes, 'Peter is a Jew; if Peter is a Jew, Andrew is a Jew; therefore Andrew is a Jew' says that Peter is a Jew.
Whereas, 'If both Peter is a Jew and if Peter is a Jew, then Andrew is a Jew, then Andrew is a Jew' doesn't.
So what? Why deny, in the latter case, that the sub-string 'Peter is a Jew' (considered as such, apart from its context) still says so? You could perfectly well admit that it does but still say the whole, larger sentence doesn't.
And if you have a reason, why shouldn't it equally well apply for sense, and disqualify the inner occurrence of the sentence from having the same sense as a free-standing occurrence?
That's all I meant, yes. And of course there are several points of view in this thread, including Kimhi's, that call into question this way of seeing the matter.
Quoting Banno
I sure do, and also about his style. Where were the editors at Harvard UP?! But let's face it, he has this in common with other great philosophers. Kant's style is appalling, but when you work at it, much is revealed. And if someone asked me to explain the 1st Critique in a few hundred words, I'm sure I couldn't. Kimhi's book is much shorter but I believe the depth and importance is there, so paraphrasing isn't easy. I think the Boynton review does the best job, and I'm going to post a few thoughts about it later.
I'm not falling down it. Maybe I need a push?
Yes, "P; if P then A; therefore A" says that P. (Asserts "P".)
Whereas, "If (P and (if P then A)) then A" doesn't.
(As long as "P" is understood as shorthand for "Peter is..." etc.)
So what? Why deny, in the latter case, that each occurrence of the sub-string "P" (considered as such, apart from its context) still says that P? You could perfectly well admit that it does but still say the whole, larger sentence doesn't.
And if you have a reason, why shouldn't it equally well apply for sense, and disqualify the inner occurrence of the sentence from having the same sense as a free-standing occurrence?
No, youre right, I was oversimplifying for the sake of brevity. He thinks that both Frege and Geach maintain Freges point. So a better rewrite of the words addressed to Frege that I put in Kimhis mouth: I disagree, if youre saying that the only thing which gives the predicate its force is assertion. But as I read you, you neednt be saying that at all. But you do, and Geach and other Fregeans have emphasized this additional point without seeming to realize that you could have stopped with your ?observation and all would have been well.
Quoting Leontiskos
I interpret Frege differently here. To show how, let me start with a question. What do you think the status is of the term ?The grass in my backyard? Are you able to understand it? And now a second question: What do you think Frege would say?
Quoting Leontiskos
Im starting to think so too, and see Boynton. He does a far better job than I thought possible at giving the term some intuitive appeal, especially when he likens it to metaphysical.
The thread has flaws. I freely admit it. But I still think it is a good thread, precisely because it does not easily fit our preconceived categories and is not reducible to the standard tropes of TPF. It is an exploratory thread which favors a kind of thinking together. And at the very least it will generate many interesting thoughts, and probably also interesting threads.
Yikes! Thanks for the translation.
Quoting bongo fury
Well, here we are back to the vexing question of "assertion" a la Kimhi. To push you down the rabbit hole, I'd need to persuade you that your use of "say" and "says" is not innocent, but brings with it an entire apparatus involving what it is for a consciousness to think (and possibly assert) a proposition. I'm still working on the best way to talk about this (and I'm not sure it's true, but Kimhi makes it plausible at least).
Quoting bongo fury
This is a little easier. We can go along with Frege in the separation of sense from assertion as merely meaning that a concrete occurrence of a proposition may actually assert it, whereas this assertive force is not associated with the repeatable symbol 'p'. ("Frege's observation," above). What is necessarily associated is the sense.
I have a copy of Kimhis book on loan and I tried to put it down given the constraints that J laid out in the OP. Of course I picked it up again when the thread began stalling. On picking it up again, I am struck by the fact that it is primarily a Wittgenstenian book. This is true not only because Wittgenstein is the main source, but also because there is a lack of overly clear answers and theses. It is allusive and elusive.
Perhaps Wittgenstenians can comment on Kimhis use of Wittgenstein. We could look at a few of the things that Kimhi appeals to in Wittgenstein. I already gave one here:
Quoting Kimhi, Thinking and Being, 8
(Rombout gives the fuller context and an analysis of this quote on page 60 and following)
A second is footnote 27 from the excerpt given in <this post>:
A third:
A fourth:
So I finished reading Rombouts thesis, Frege, Russell and Wittgenstein on the Judgment Stroke (but I did skip the section on Kant). English is certainly not Rombout's first language, so there are errors of grammar and spelling, but it was on the whole very good. It sheds a lot of light on this issue, and interacts with Kimhi in a very odd way.
The thesis is something like this: Wittgensteins understanding of Frege and especially Freges judgment-stroke is flawed. Anscombe thinks this is because Wittgenstein was reading Frege through Russell. Was she right, or was it flawed for some other reason?
This raises two possibilities with regard to your thread. First, that Kimhi simply followed Wittgenstein in his misunderstanding of Frege. In that case Rombouts survey of Wittgensteins response to Frege inevitably captures Kimhi himself. Either way, that section is very helpful, both in itself; because Kimhi seems to be building on Wittgensteins critique; and because the Wittgenstein/Kimhi critique may be successful even if they are both failing to really understand Freges position. It also has some overlaps with Bannos misreading of Frege, probably because Banno is a Wittgenstenian.
The second possibility is that Kimhi rightly understands Frege and avoids Wittgensteins misunderstandings, and nevertheless utilizes, augments, and improves Wittgensteins critique.
I dont know which is true: probably some of both. Kimhi includes no mention of the historical debates about Wittgensteins interpretation of Frege that are presented by Rombout, and he certainly would have had he known about them. On the other hand, he seems to have a better grasp of Frege than Wittgenstein did. If the first possibility holds then the Frege referred to in the OP is really Wittgensteins interpretation of Frege, which is a possibility that must be held in mind. My own sense is that Kimhi misunderstands Frege along the same lines as Wittgenstein, but with some mitigation, and in a way that might not undermine his sub-thesis.
I find it a bit odd the way Kimhi places Aristotle and Wittgenstein in the same bed. If Aristotle and (early) Wittgenstein both disagree with Frege, it is for wholly different reasons. And while I find Wittgensteins alternative to Frege quite terrible, his critique is nevertheless acute and worthwhile. That critique via Rombout may be a good way to get the thread on track without appealing too strongly to Kimhi. It is found in Rombout 4.3.1, and to a lesser extent in the following sections.
(I should also say that in general it proves difficult to navigate the various logical paradigms, even before Kimhi is brought in. It is also worth checking out PI #22, which Rombout references and Kimhi does not include.)
---
I pointed out where Rombout gives context for Kimhis short quote from Wittgenstein, but the same holds for Kimhis short quote of Russell:
Quoting Rombout, 33
Rombout basically looks at Frege's judgment-stroke, and then at the ways that Russell and Wittgenstein wrestle with Frege's judgment-stroke. It is both helpful and freely available.
This is excellent, and it has everything to do with the OP. :up:
See Rombout:
Quoting Rombout, 44-5
That entire section in Rombout's paper discusses this issue, which seems central to the OP.
It's ironic you say this.
My deep dissatisfaction with everything I've read of Kimhi was precisely the emphasis on assertion, judgment (a word I've never had any use for because of its libertarian aura), and this "I" of logic.
I've been thinking a lot the last few days about the "we" of logic, but so far it's not in good enough shape for the thread I promised.
Anyway, this "I" stuff is why I'm not bothering about Kimhi anymore.
Quoting Rombout, 61
It's tricky to switch paradigms, but in Wittgenstein's paradigm the problem is that Frege has "two phases in the assertion of a sentence." Russell struggles with the same issue from a different paradigm. For Frege it is the difference between "the True" and the judgment-stroke.
To try to put it plainly: is it possible to see that something is true before going on to assert it? And does (the recognition of?) a sentence's truth require a subject? Is the syncategorematicity (in Boynton's sense) of the judgment-stroke already present in the truth-assessment?
The puzzle is explicit in Frege's requirement that only true sentences can be asserted, a requirement that is incomprehensible to, and thus not even understood by, Russell and Wittgenstein. If only true sentences can be asserted, then what exactly is the difference between calling a sentence true and asserting it? Frege has an uncommonly objective notion of truth (and also assertion) (at least as far as contemporary logic is concerned).
Quoting J
This seems cumbersome, but certainly better. And now we are correctly speaking about assertoric force rather than non-assertoric force, which was my point. Remember though that Kimhi does not think one can stop with Frege's observation. He thinks we need to go on to draw Wittgenstein's point instead of Frege's point.
Quoting J
My very first sentences in the thread:
Quoting Leontiskos
Frege will say, "There is something which is grass, and is in my backyard, and the class of things which are thus and so is not empty." He will not say, "...therefore, backyard-grass exists." He will say, "...therefore the class of backyard-grass is not empty." What is being rejected is the subject-predicate approach, such as Aristotle's where grass is a substance and "in my backyard" is an accident. For Frege it is a matter of applying two functions to a single 'argument', and the argument does not sub-sist as something independent of the functions.
I take it that Novák is required reading at this point, and is deeply related to one of Kimhi's central theses, regarding speech about that which is not.
Quoting J
Yes, I agree. I have been meaning to look at Kimhi more closely on this subject.
Eek. Not only is this part redundant but it requires classes to be objects, which pill, though bitter, even Quine swallowed for the sake of mathematics. But we don't have to go there just for this.
(It's also Quine who pointed out that names for individuals are eliminable. You just make a predicate like "Socratizes" that is satisfied by a single individual. That might not strike you as either intuitive or felicitous, but it's a typical math move, to subsume a particular problem into a more general one.)
Indeed it is so incomprehensible that I didn't even remember this was Frege's view.
Which suggests to me that "assertion" is really not a word we should be using at all here, given its modern meaning.
I may have missed it, but I suppose this applies to "judgment" as well, that you cannot judge as true what is false.
All of which points toward that favorite (never defined) word, "grasping". So it's about grasping the meaning of a proposition, grasping its truth, the difference between those, and so on.
Rombout's section on Kant (2.2.2) seems very related to this issue. Instead of trying to comment further I will await your thread (although I will say that I think something more radical than a shift to "we" is required to displace Frege's presuppositions).
But the thread fosters "thinking together" insofar as the premise is something like, "Frege says this, and Kimhi critiques it. How might we understand Kimhi's critique? What exactly is it that is wrong with Frege's claim?" That creates a common project and thinking together.
But I am now seeing the relevance of some of your earlier comments, such as those about Wittgenstein's picture theory and his emphasis on "showing."
-
Quoting Srap Tasmaner
Compare:
Quoting Michael Potter as quoted in Rombout, 61
Quoting Srap Tasmaner
This seems right to me.
-
Quoting Srap Tasmaner
I agree it is redundant. That has sort of been my point. And maybe Frege would reject it on the basis that classes are not objects, but from what I understand he vacillates on this a bit. I am not averse to the conclusion that he rejects it. That seems most consistent.
Quoting Srap Tasmaner
Yep:
Quoting Luká Novák, Can We Speak About That Which Is Not? Actualism and Possibilism in Analytic Philosophy and Scholasticism, 166
-
Quoting Srap Tasmaner
I don't find the usage beyond the pale, but I now see how it can be confusing. For example, you are certainly thinking of assertion differently than Frege in passages like this:
Quoting Srap Tasmaner
For Frege one asserts even when they are working out syllogisms in their room alone. On page 38 and following Rombout has a very interesting discussion of performative aspects of written language, such as the judgment-stroke.
Quoting Srap Tasmaner
Yes, all we are ultimately talking about is the judgment-stroke.
Quoting Srap Tasmaner
Yep!
Broadly -- I think everyone knows this, but here we are -- the two principal strands of thought about language are: language as symbol system (which facilitates thought); language as communications system. Frege is generally treated as part of the former camp, and early Wittgenstein, and the latter camp includes later Wittgenstein, Grice, et al. (David Lewis makes an heroic attempt to marry them in Convention, and admits that he cannot.) For what it's worth, I'm in the latter camp, but see the sort of analysis the former produces as a useful strategy in some cases.
But language is easy (!) compared to logic. It appears to me that research overwhelmingly supports the communication-first view, but there is no simple path from there to a similarly robust take on logic, not that I've found anyway. That's uncomfortable for me, but oh well.
And Kimhi seems to me mostly to be talking about a pretend world, or at least mistaking the simplifications (that is, fictions) we employ, like "grasping the truth of a proposition", for reality. (And note that mathematics is such a pretend world where logic runs like a champ without any of this psychological baggage.)
I'm not convinced that we have to choose, and Rombout's discussion of performative language gets at this starting on page 38. In fact I tend to wonder if Wittgenstein's irrecoverable mistake was choosing and shoehorning language in this way. For Aristotelians natural language is something that can never be fully accounted for or categorized, and I tend to think that this is essential to philosophy. As soon as you try to enforce rules on language you're screwed, even if your rules are true 98% of the time.*
Quoting Srap Tasmaner
It is said that Peirce and Frege created the same system independently, but I am curious whether Peirce's robust focus on semiotics would have produced a better logic than Frege's. Peirce also seems less invested in mathematics, which investment is another kind of rule or determination over language. Aristotle explicitly opposed the mathematization of knowledge and logic.
Quoting Srap Tasmaner
I would start with the idea that a symbol or sign is a kind of self-communication. Apparently Russell talked about the usefulness of written symbols along these lines.
Quoting Srap Tasmaner
This is where we disagree, but the disagreement runs so deep that it deserves another thread. :wink:
I may as well respond to this, even if it is better fitted to your new thread:
Quoting Srap Tasmaner
Frege is not giving a simplification or a model, and it is essential to understand this. Whether it makes sense to say that every conception of logic is necessarily a simplification (a simplification of what?) is something that I think would fit a new thread (or the old Sider thread, which was closely related to these questions).
* See, for example:
Quoting Leontiskos
Quoting Luká Novák, Can We Speak About That Which Is Not?, 168-9
That may be true, but it's been a serious point of contention in the post-Frege discussion of language.
And here I'll mention, for the nth time on TPF, the comparatively little-known view of Tarski's star student, Richard Montague, that there is no distinction between formal and natural languages, because natural languages are "formal" in the intended sense, and that linguistics is a branch of mathematics. Montague presents his analysis of the logical constants as the semantics of natural language. Certainly a maximalist take on the formal view of language.
And I guess we ought to leave this more general discussion of the underlying issues there.
On page 305 of Dummett's book:
Quoting Michael Dummett: Frege, Philosophy of Language, page 305
I wish 308 was included in the preview.
---
- :up:
A lot of this seems to revolve around the question of whether a modus ponens is conceived as tautological. For Rombout I want to say that Frege says no, (early) Wittgenstein says yes, and Russell bridges the two. P must be both the same and different if true knowledge is ever to be gained.
Quoting Leontiskos
This was your response to these questions of mine:
Quoting J
Are you saying that, because The grass in my backyard is an individual term, not "Fregean," not part of a proposition, Frege would be reduced to silence about it? Would he say, Sorry, I dont understand that term? This seems unlikely. Im deliberately asking a question about an individual term because Im trying to build up an argument about Freges views on existence.
Your response goes on to imagine what Frege would say about a different bit of language, The grass is in my backyard, but that of course is a proposition and not at issue. So I pose the question again: Given your understanding of Freges philosophy of logic, how would he account for the fact (if it is a fact) that we can understand the individual term The grass in my backyard? (Ive only put it in my backyard to avoid the appearance that Im asking about a universal term, grass; theres no predication involved. If you prefer, change it to a unique non-composite term, such as The Hope Diamond -- anything that can be the argument in a function.) And the question remains for you as well: You are not a Fregean, so what account would you give of that term? Do you understand it? If so, how and why?
Do you know Russell?
The thing about "The grass in my backyard" as a denotative phrase is that it has that "the" in it, which Russell gives a famous analysis of, claiming it includes a sort of hidden existential quantification.
Like Alice on Jabberwocky:
Not being able to say what your ideas are is death in philosophy. Or rather, it ought be; but folk do go on so.
I'm not sure which three sentences you are referring to. I was addressing 'if p then q'. Us talking about this sentence is an example of 'mention'. We are not concerned with whether it is true, and are not claiming that it is true, so there is no intentional assertion going on in our referring to the sentence.
So we can invite @Leontiskos to compare Russell's view as well -- does he (Leontiskos) think Frege would give the same explanation? Is that his (Leontiskos's) own explanation? Just to refresh us about the point of it all, it has to do with the way in which Frege forbids predicating existence; getting clear on the individual-term question is kind of Step One to making my case that Frege only means, literally, that we can't speak in Logicalese about the existence of entities or the non-existence of entities. I don't take him to mean that we can't understand the difference, or that we can only understand what can be said in Logicalese. But one step at a time.
Consider this: if you can predicate existence, can you also predicate non-existence? (Or, what is the same thing, negate a predication of existence.) And *what* would you predicate non-existence of?
I'm tempted to warn you off this whole thing -- which gets rehashed regularly -- but there is a sense in which Frege's system automatically narrows the the field of true statements to statements about real things, and that does seem relevant to Kimhi's whole invocation of Parmenides. Somehow. Not waters I like to swim in.
I'd have to agree here. I think in this sort of thing, we must work backwards and then go from there. For example, if Kimhi is saying something about logic and its connection to "thinking and being", we first must understand what his main claim is here, and then we can work to his examples in Frege. Right now we are only working with partial ideas which by itself seem more perplexing than enlightening. No one has yet explained the main premise, or in any clear manner I can discern. From what I gather, logic is something that is entailed in human thought and being. But what this means, how this is, why this matters, etc. is not explained. And thus this Frege stuff doesn't seem like its leading anywhere other than he doesn't like the little marker that says "This statement is asserted as true".
Boynton wants to compare certain aspects of Kimhis thought with Sebastian Rödls, and Im not qualified to say much about that. But a quote from Rödl that Boynton provides sets the stage very well:
You could say that Kimhis entire project and the Kimhi-inspired challenge to Frege with which I began this thread rests on this sudden realization that p is mysterious, not innocent, not something merely to be taken for granted in its philosophical employment. The first chapter of T&B is called, wryly, The Life of p, but its no joke. We have to ask, How does p appear before us, on the page, in speech, in thought? Who puts it here? Philosophy begins in wonder . . . and great philosophy often begins with questions that seem almost idiotic in their obviousness.
Freges remedy, according to Kimhi, is to introduce the judgment stroke, which has no functional role: it signifies that something has been asserted, but it remains unrelated to the content of asserted propositions.
Fine. But this removes assertoric force from any possible unity of thought and being between what is said and what is the case.
This is the best attempt Ive yet seen to get across Kimhis notion of the syncategorematic. Theres more to it for Kimhi, a fact is itself a syncategorematic unit but the basic idea is that to think about how thought refers to the world is to think syncategorematically, and thus outside the expressions of formal logic.
Boynton doesnt like the S word any better than I do he calls it cumbersome, not easily graspable, and specialized -- and in a brilliant stroke he suggests an obvious alternative: metaphysical.
These are just a few of the insights I found in Boyntons piece. I could have picked out and commented on a half-dozen other, equally insightful, passages, but you can read it for yourself. I find the essay especially valuable because, to think about Kimhis philosophy and its challenges to Fregean logic, we need a kind of vision shift, a big-picture understanding of why we ought to be dissatisfied. That can often be hard to find in T&B. I think Boynton is keeping our eyes pointed in the right direction, on the difficulties formal logic experiences when it tries to connect thought with being. The metaphysical already accompanies, is already within, our normal propositions, our everyday speech, and . . . such unity is also the unity of thought and being. The connection with Wittgenstein is becoming clearer and clearer to me . . .
It's hard to do, no question. Does the post about Boynton, above, help any?
Quoting schopenhauer1
More than a matter of liking or disliking, I would say. I can't recap all the arguments but I'm sure you can see that the need to undertand assertoric force is critical to the whole question. Kimhi claims that a strategy like the judgment stroke is inadequate to the task.
This is what and I were talking about earlier, namely the way that a declarative sentence has an inherent assertoric force even before it is asserted. For example:
Quoting Leontiskos
That line of inquiry ended this way:
Quoting Leontiskos
After a close read of Kimhi's section 2.5 I see him doing the exact same thing that Srap and I were doing. He says that both a declarative sentence and an asserted declarative sentence "display" force, but whereas the first is "a mere display" the second is "a self-identifying display." This language is odd, but he is apparently trying to make it line up with his consciousness-claims.
Yet my point gets louder and louder, "But I don't see how it intersects with Frege." Kimhi is wed to the idea that Frege's point commits Frege to the claim that a declarative sentence cannot display assertoric force. Is that really right? For example:
Now Kimhi has introduced another term, "assertoric form." The difficulty with all this hair-splitting is that Frege apparently never considered and rejected Kimhi's idea of "assertoric form," and Frege's judgment-stroke is closer to Kimhi's monism than anything we see on the post-Fregian scene.
Apparently Kimhi wants to trace truth-functional compositionalism back to Frege's dissociation between assertoric force and predicate:
I am open to the idea that the following 70% of Kimhi's book shows why it matters that Frege did not have a precisely correct representation of assertoric force, but set in isolation the point seems uninteresting. It's like Kimhi is pointing to an incredibly dull star in the night sky, and we can't tell whether it is there or not. After straining for so long, the question arises, "So what if it is there? Does it matter?"
I think Kimhi makes interesting and correct observations on many topics (and errs in others), but this point of the OP would seem to require more leverage to function as something of interest.
-
There are also places where Kimhi follows Wittgenstein into incorrect interpretations of Frege, such as here:
Frege simply does not make this error, given his constraint that only true sentences can be asserted. Kimhi appeals in places like this to Wittgenstein, and Rombout explains how Wittgenstein makes this exact same error. Along similar lines, calling Frege's distinction between truth and judgment/assertion "dualistic" seems to obscure the very close coupling between those two things in Frege's thought.
-
Edit:
Quoting Janus
It's also interesting to note that Kimhi's point can invert against himself, for if Frege did not admit that in the assertion, "If p then q," the antecedent and consequent have some sort of latent assertoric force which can be actualized in the context of a modus ponens, then he would not be able to draw a modus ponens. Put differently, in asserting, "If p then q," we are asserting something about p and q. Is the takeaway then that assertoric force is not binary? And yet, is assertion binary?
For Russell and Frege, logic trumps natural language, and is not "logicalese." This is very clear in Novak. Frege does not renege on his opposition to the existence-predicate when it comes to natural language. He does not think, "Oh, well you can't predicate existence in logic, but you certainly can in natural language."
Quoting Srap Tasmaner
That's right. Frege says the exact same thing in the second quote I gave in <this post> on page 1.
-
Quoting J
As I said, you are presupposing subject-predicate logic, which Frege explicitly rejects. "Terms" are not part of Frege's system (where term means a subsistent thing with a nature, that can bear predications).
Quoting J
No, I don't think this is true. For Frege, "The grass in my backyard," would seem to parse as I described it. "The grass in my backyard. . .," parses as, "?x(Grass(x) ? Backyard(x)). . ." Else, if you want to talk about some x apart from any function then Frege will not have it. So if you want to conceive of your "term" of "The grass in my backyard" as a proper name, then Frege will ask you to say something about the proper name. You could say something like, "[The grass in my backyard] is long," where "...is long" is the function and "The grass in my backyard" is the proper name of an object. But in common use the reference, "The grass in my backyard," already involves predication, and is therefore not a proper name. That you were able to predicate without using the word 'is' would seem to be to the point.
(The disjunctive syllogism allows us to avoid Russell's question, for "The grass in my backyard" either involves implicit predication or else it does not.)
Quoting J
I don't think Frege's positive analysis is altogether incorrect. When we predicate (apart from predications of existence/non-existence) we commit ourselves to the "existence" of the objects in question (whether vacuously, as in Frege's case, or substantially, as in the common case). I differ from Frege insofar as I have no qualms about predicating existence and non-existence, although Novak's topic is admittedly difficult.
Are you asking what your incomplete sentence is supposed to mean without any verb? Suppose you begin speaking a sentence very slowly, "The grass in my backyard..." We have a subject ("the grass"), an accidental modifier of place ("in my backyard"), and we are awaiting the verb and predication. For Aristotle the subject of a predication is basically never propertyless, and this is because substances have natures, and a reference to a substance includes its nature.
Kimhi actually makes my point for me:
A syllogistic term such as, "The grass in my backyard," must have an extension and therefore signify a concept in Frege's sense, and therefore it violates Frege's commitment, "To keep in mind the distinction between concept and object."
Quoting J
Thats fair. Its just that were stuck on this topic and you dont seem to want to take Frege at his word that he denies the existence-predicate. Im not sure how you intend to argue otherwise without adverting to primary or secondary Fregian sources, and Novak is the source that is already in play on this issue. Is the goal to show that the denial of a substantial existence-predicate is incoherent, and therefore Frege either did not hold to such a position or else held it and was incoherent? What is the thesis you are aiming at? As for me, I think it is clear that he does hold to such a position; I do not think it is incoherent to do so; but I do think it is silly and mistaken.
This goes back to what I said in my first post:
Quoting Leontiskos
This seems right. Kimhi often mentions the problem of referring to non-existents. What he doesn't seem to recognize is that Frege inoculates himself against even Kimhi's more subtle objection by saying that assertion is always tied up with truth. So Frege will say, "It is true that not-x," but he will never say, "It is false that x." Part of Kimhi's project turns on the difference between falsity and negation (or denial and negation), but like Wittgenstein and Russell he fails to understand that Frege will have nothing to do with claims of falsity per se. Now for me this gets at a different problem with Frege's system, but Kimhi is not recognizing how thoroughly the Fregian paradigm sidesteps Parmenides' koan. His argument that Frege is inconsistent is very difficult to maintain. On my view Fregians tend to be wrong but not inconsistent.
...and there is an interesting way in which Frege's decision to speak about truth but not falsity is more monistic than Kimhi's idea that truth/falsity and affirmation/negation are balancing forces (albeit with the first term receiving a primacy). But I digress.
An interesting question. "If p then q" seems to be inherently an assertion about the relationship between p and q. It is an inherently asymmetric relation: "if q then p" is not entailed.
"It is raining" has the form "x is y", just as "it is green" does, and yet they are not the same. To state that it is raining, I could just say "raining", which would seem to indicate that assertion is not always binary.
I hope I've understood your question; I'm pretty confident about working out the logic of natural language, but I'm not great with formal logic.
The first paragraph makes it clear that the intellectual predecessor here is McDowell. SO the idea is some thing like that declarative sentences are true in that they are identical to a thinkable (an odd nominalisation), securing a connection between mind and truth. Apparently for McDowell, a true thinkable just is identical to a fact. I'm not overly familiar with McDowell, but it seems to me worth noting that what a "true thinkable" is, is far less clear than is the notion of satisfaction that it appears Kimhi wants it to replace.
But again, what is going on here remains unclear. The foremost puzzle is what sort of "identity" might hold between things as divergent as thinkables and facts. So the puzzle that the identity theory of truth wants to solve is the puzzle fo what is going on on the right hand side of a T-sentence: 'p' is true iff p; and it attempts to solve this by an additional identity, between the thinkable'p' and the fact p. Now the identity that holds between 2+3 and 5 is reasonably clear; there are numbers on both sides of the "=". For an identity to hold between a thinkable and a fact, they must be the same sort of thing. I can't see how what McDowell is proposing is an improvement on the T-sentence.
Seems to me that these considerations sit with the Wittgenstein of the Tractatus. And I have noted that the quotes from Wittgenstein used here indicate more dependence on the early rather than later Wittgenstein. My "solution" to the T-sentence issue so far as there is one is that on the left, 'p' is being mentioned, and on the right, it is being used (cue and ).
And this might be why I'm not seeing much of worth in what has been said about Frege. It's answering a question already answered, and in a better way.
This seems pretty much on the money. "?p" does not follow from "p". But that's kinda the point Frege makes, and solves with his nomenclature. In setting out Modus Ponens for example, Frege doesn't write
?p?q
?p
?q
such that each is within it's own intensional bracket; he writes
?(
p?q
p
q)
The first is invalid; the second, brilliant. Again, Frege is setting aside the intensional aspect in order to display the extensional. Frege's system 'cannot account for the inference: p? A judges p? A rightly judges p."' because it is invalid. It simply does not follow from p, that A judges p, nor that A rightly judges p.
Indeed, calling it an "inference" is extremely problematic.
This goes back to my original question, what gives the assertion any truth-value in the first place? Whether you say "This person thinks X is true and judges correctly" or just "X is true", besides just a more efficient logical form, what does it matter really? How we say, "The sky is blue" in a logical form, and whether the fact that the sky is actually blue seem two separate things, the it is the latter that is the most important.
The answer, by example: if P={a,b,c} then Pa is true; if P={b,c,d} then Pa is false.
Of course this doesn't tell us if a is an element of P. That's something you will have to do, an act you might choose to perform. And something quite different to logic.
Now my response is that we as a community choose to use "the sky is blue" to set out something about the way things are (or are not, when it is overcast). But you don't seem to like this answer. I suspect you want a theory that sets out, for any given sentence, if it is true or no. That's not what logic does. Rather it is about the consistency of what we say.
Quoting Srap Tasmaner
At some stage seeking explanations stops, and we act.
And to your unanswered question,Quoting Srap Tasmaner
I think so. I baulk a bit at 'understanding is not something you usually should be described as "doing"', since we do say that he did or didn't understand... We treat it as something we do.
The way I would reply would depend on whether you meant "community" of philosophers/logicians or the general public.
That could still be either one.
But I guess the bigger picture here is that Kimhi seems to think Frege is lacking something that say, someone like Aristotle captured in his logic- some sort of active engagement of the thinker and the logic. I guess I just don't see the difference really in how Aristotle adds the "active" engagement part. As far as I see from their logical forms, they are different ways of saying the same thing. I don't see anything like "Thucydides thinks that Socrates is mortal". Rather Aristotle's example would be "Socrates is mortal". I guess I don't get Kimhi's comparison and how he thinks Aristotle captures the "thinking" part.
Oh I guess.. and this is just basic.. Because
All humans are mortal
Socrates is a human
Socrates is therefore mortal..
I guess the combining of the major and minor premise is considered the "thinking" part.. but is it really that basic? It is still proffered as if everything true and thus the conclusion is true. Still not getting the profound implication here about Aristotle versus Frege.
Well, no. "General public" might do.
But your confusion in regard to Kimhi's thesis is warranted.
Speaking roughly, there are folk who think logic is about working out what is true and what is not. Perhaps there is some historical justification for that. On this view there is a requirement that logic be the connection between thoughts and words. This might be the sort of thing McDowell and Kimhi are looking for.
But logic is more about which of the various things we can say are consistent with each other, and what that consistency might be. Science, rather than logic, is more about what is the case and what isn't, .
I don't want to get into this too much, but yes, in trying to keep conscious, attentive decoding out of it, I do make understanding sound too passive. I think the evidence is that understanding is pretty darn active (we predict the ends of sentences before we hear them, guess what the other person is going to say next, back-channel to guide their speech, and so on). It might still make sense to say that we don't choose to understand other people's speech this way, it's just what we do.
I was very impressed by Austin's claim that it normally doesn't make sense to say that I sat in the chair "voluntarily" or that I sat in the chair "involuntarily" -- as doctrinaire views on free will would require -- but each fits special circumstances which call for such an adverb. Just so, I'm resistant to analysis that treats all of our declarative utterances as deserving an "I judge that ..." or "I believe that ..." in front of them. Sometimes we judge, sometimes we go out of our way to mark what we're saying as our personal belief, and sometimes, probably mostly, we just talk.
I still don't know what this thread is about, but I'm pretty sure it starts in a place pretty far from me and goes in the opposite direction.
This is a good discussion among you, @Banno, and @Srap Tasmaner. I'll just step in to say that the quoted passage sounds like it's on the right track to me. Kimhi does think there's something important -- indeed, fundamental -- missing in Frege, and that something has to do with the role of the thinker. Here's a passage from T&B that talks about this, perhaps unfortunately in terms of the syncategorematic:
Kimhi is very blithe in his use of "hence" to arrive at the concepts of consciousness and self-consciousness. And many would take issue with the idea that philosophical logic is "called upon to elucidate" anything whatsoever about self-consciousness. But I think we can at least see what Kimhi believes his problem is about -- and the passage from Rodl, via Boynton, quoted earlier is also on point. As to whether this is reflected in Aristotle, I'm not qualified to say.
Didn't Frege believe truth is a concept that's too basic to define? It's just impossible to express a proposition without already understanding what truth is. There's no meta-cognition needed.
I just don't get what the "self-consciousness" aspect adds to it, other than a sort of call to more basic epistemological questions like "How do we even know what we know?". But I see logic as just a way to structure language so as to be clear. That is to say, the "thinking" part, according to this view, is "behind the scenes". The conclusions are then taken from the "thinking part" and put forth in logical terms so as to be clear and consistent so nothing is misconstrued. Logic is more about clarity, not necessarily the "truth". That is why I said before this whole discussion (upon what I still don't know), that the more interesting and basic question is how we decipher truth (the thinking behind the scenes), not how we present it in some logical form. That part to me is simply how to present one's conclusions so as to be not contradictory to its own argument or what it is presenting.
Thinking can be messy, perhaps non-logical.. It can be pictures, intuitions, thought-patterns. Logic puts these into consistent non-contradictory presentation to other thinkers. Thus you may have an intuition or insight that turns into a rigorous physics/philosophical/mathematical proof, for example.
Edit: Socratically arguing with myself here.. I am sure Kimhi et al. would say something like the following:
But thinking IS logical.. It is self-reflective and there is a certain way we engage with the world (I am not sure what they propose that grand theory is, but I would be interested). And this way we engage with the world is ITSELF logic.. And thus something akin to either the Stoic's "Natural Reason" or Hegel's "dialectic" might capture this "inner logic". And it is THIS process of how we interpret the world that is not captured in formal logic (like Frege's).
Edit 2:
I read up more on Frege's meta-logical theory, and it seems that he was a sort of Platonist about logical truths.. So finally, I think I see what the goal of Kimhi here is. It's not the FORM per se, but Frege's underlying assumptions of logic.. That logic is not psychological, according to Frege, but rather metaphysically real in some Platonic way... Ok, so this just goes back to an old debate about the nature of truth. Is "Truth" independent of human thinking, or is it "True" irrespective of the interpreter (or psychology)?
Edit 3:
And of course, behind all this is an old debate of "real" vs. "psychological/ideal" etc. And then this just goes right back to my initial question, "How do we discern truth"? And so for example, if Frege is a Platonist, then how does one discern the "real objects" of the abstract realm? The cat is on the mat, so is it just going back to the verification and/or falsification principles yet again?
Quoting Leontiskos
Quoting Leontiskos
OK. Evidently my choice of The grass in my backyard was unfortunate, because it looks like its grammar may confuse the logical point. Lets change the term to Berlin. If I say Berlin, I doubt if anyone would call it an incomplete sentence. Or, if you like, imagine Frege walking along a beach and finding a scrap of paper with the word Berlin written on it. In either of these cases, Im guessing the natural response would be something like What about Berlin? or I wonder why ?Berlin appears here. But what my question about comprehension is asking to you to affirm, is that in neither case would the response be What is Berlin? I dont understand this term (if youll grant that the folks involved have heard of Berlin before).
To the second quote: I do indeed want to talk about (in the sense of "mention") some x apart from any function. Ive just done so. You say that Frege will not have it. That may well be true. But again, what Im asking is, does not having it mean that Frege doesnt comprehend the term Berlin, or doesnt think that I do? Or is it, rather, that hes urging me to understand that I cant say anything about the term without its taking its place to saturate a function?
Ill drop this if the question still isnt clear. This was all in aid of trying to build up a picture of how Frege regarded existence, but there are other ways to approach it.
Yes, Kimhi calls this "psycho / logical dualism" and rejects it. According to him, neither the Platonists nor the "it's just how we think" philosophers are correct, because the dualism is all wrong.
Ok, so that is what he is against. What is the theory he is proposing. The name of the book is Thinking and Being... This reminds evokes ideas like Hegel's dialectic, or even Stoic's Natural Reason. If it's not psychological, what is it, other than some variation of "World Spirit", or Logos?
An alternate but kindred argument would be:
1. In order to express or discern a proposition, you have to understand what it means.
2. Meaning is found in truth conditions.
Therefore, communication requires understanding truth. So it isn't teachable. You can't define it in the sense of explaining it to someone who doesn't already know what it means.
I think we often frame our interactions with the world as if we're communicating with it. For instance when we're seeking something, we imagine that there is some unexpressed proposition that specifies the location of the lost object: it's located at x.
This would be a way of explaining why we sometimes lift propositions out of the domain of human speech. Sometimes it's the world speaking. There's a sort of connection there between truth and being.
Quoting Banno
You have this exactly backwards, and Rombout goes into it in detail. Frege writes the first and Russell ends up with the second. See also .
Quoting Banno
I think you are confusing '?' with Frege's judgment-stroke. You still seem to be fundamentally conflating Frege with your own approach. I suggest reading some Rombout.
Quoting Banno
This is an important claim, because you are conceiving of 'p' in a particular way. I just want to mark this out.
As I said in the earlier thread, I think J needs to distinguish between committed Fregians and non-committed Fregians. I don't think Kimhi has the horsepower to convince committed Fregians (or truth-functionalists) such as yourself. So the parts of this thread that are aimed at convincing committed (post-)Fregians seem a little bit pointless to me, but whatever.
-
Quoting schopenhauer1
One represents a functional understanding of logic, the other a "psychological." One inquires into what it means to say that something is true, the other does not. For someone who sees logic as the art of human reasoning and knowledge, the question of truth simply cannot be neglected.
Quoting Banno
Your approach is already a truth approach. "The way things are" with regard to "the sky is blue," is precisely what you rejected in your previous post, namely that "the extension is a relation between a and a fact in the world that must obtain." "The sky is blue" is not about abstract sets. As you rightly note, it is about, "the way things are."
Quoting Banno
According to what source other than yourself? You consistently conflate metalogic or metamathematics with logic.
-
Quoting schopenhauer1
I also think Frege is closer to Aristotle than Kimhi allows, but the point is that for Aristotle judgment is implied. Propositions do not exist apart from judging subjects, and logic has to do with judging subjects.
-
Quoting Banno
If you read more of that review you will see that Kimhi disagrees rather strongly with McDowell. Boynton seems to merely be saying that McDowell is a genealogical point of departure for Kimhi and Rödl, not that they actually agree with McDowell's deflationism.
Along the same lines, @J is quoting from Boynton in places where he is making a case against Kimhi, and using those excerpts as support for Kimhi. For example, Boynton's point with 'p' is that Kimhi falls prey to Rödl's critique, not that Kimhi reflects that critique (and I agree).
-
Quoting J
The "uniqueness of thinking" is the primary thing I agree with in Kimhi, and I think it is a helpful way to capture his project. :up:
-
Quoting schopenhauer1
Part of the point is that thinking occurs not only in the form of intellection, but also in the form of inference. For example, drawing the conclusion of a modus ponens requires a very odd and opaque account of how the p's in the first and second premises relate. As soon as one begins to probe inferences of this kind Kimhi's project will arise spontaneously.
Quoting schopenhauer1
According to Rombout early Wittgenstein struggled with making sense of how logic and knowledge interrelate. He saw logic as tautological and knowledge as non-tautological (and therefore in some sense non-inferential), and never the twain shall meet. Plato and Aristotle wrestled with the same problems. But if logic is supposed to reflect correct thinking, then it cannot be divorced from knowledge (of the world).
Everything I said in my last post applies exactly the same here, as "Berlin" is no more a complete sentence than, "The grass in my backyard." See especially where Kimhi addresses the exact questions you are asking, as noted in my last post.
Quoting J
Here is what Frege would say:
Does "Berlin" have extension? If it does then it is not an object. If it does not then it is an object. All you are doing is trying to have it both ways. You want objects with inherent extension, which is impermissible.
Natural language is not Fregian. I'm not sure what else to tell you. For the Aristotelian this is no problem given that grammatical subjects have inherent form.
...of course, this is not prima facie insurmountable for Frege. So "Berlin" involves a concept-function. So what?
-
Edit:
Quoting Leontiskos
Note that even in this post (and earlier posts) first-order logic creates a concept-function out of the subject. This is not controversial; it is just how first-order logic is done. That logic does not permit something like this: ?(grass)(Green(grass)). Objects do not have inherent extension.
It's more about intention than words. If you say "Raining," is your utterance necessarily either an assertion or a non-assertion? Or is there something inbetween? Srap is asking a similar question:
Quoting Srap Tasmaner
Is there then something between assertion and non-assertion?
Quoting Srap Tasmaner
I was trying to think of a way to put the exact same thing, and you've captured it perfectly. Most of the posters in this thread would say that Frege is too fat. Kimhi is arguing that he is too thin.
Unless these philosophers explain WHY thought MUST reflect reality (via "logic"), it doesn't seem to have any force to me, except as, ironically, unsupported assertions.
Plato came closest out of the three people you mentioned. Logic is somehow grounded in an abstract logic whereby our intellects are part of, and can't help but reflect. It has a hierarchy and the highest forms of knowledge are simply "knowing" the Forms in a quietist/spiritual way (no longer in concrete or even abstracted form).
Aristotle, is harder to discern how his logic reflects a deeper sense of being. I leave it to the experts of Aristotle..
Wittgenstein is the most egregious in leaving out an explanation of how logic reflects what is the case in reality. It is truly unsupported assertion all the way down. One of my biggest gripes with Tractatus is there is no "there" there as to how the correspondence holds... Vaguely we get "states of affairs" and "objects" beneath "atomic facts", but for a modern philosopher, I expect more on what justifies this.
I would say that this is the most relevant part of Boynton's review for this thread:
Quoting Boynton's Review of Thinking and Being
As I said above, I don't see Frege saying that Pa cannot display an assertion. Be that as it may, what is Kimhi trying to argue here?
Simply working from Boynton, he seems to be saying that if the declarative sentence, "The cloud is raining," does not display an assertion, then it is impossible to say under what conditions the cloud would be raining or not raining. That if "the cloud is raining" and "the cloud is not raining" do not display different assertions, then they could not be associated with different truthmakers. This looks like the same argument that Wittgenstein gives in Rombout 60-62.
Cf:
Quoting Leontiskos
Isn't it self-evident that if logic is to be meaningful then there must be some relation between thought and reality? In any case, the context here is that Frege and Kimhi accept this as a mutual presupposition:
Quoting Luká Novák, Can We Speak About That Which Is Not?, 157-8
I mean here an ACCOUNT, not just a self-evident conclusion. That seems ANTI-philosophical to just say, "Self-evident" wash one hands and make it the final word. In fact, it's the first word before we get to logic. I don't even mind if something like "evolution" is used, but I want an account, not just "because it makes sense RIGHT??!!!". I mine as well not do philosophy at all if all we are giving is "self-evident".
As a tie-in.. Apparently SIX YEARS AGO, I discussed similar issues, but tried to give an ACCOUNT. You may even be interested in the whole thread there:
Quoting Philosophical Investigations, reading it together.
An account of what? First you say, "unless these philosophers explain WHY thought MUST reflect reality..." And then you go on to speak about "accounts." They are two very different things. A necessary argument with the conclusion that thought reflects reality is different from an account of thinking.
Quoting Leontiskos
You haven't answered this question. Are you saying that logic would be meaningful even if there were no relation between thought and reality?
You seem to be saying, "Unless Kimhi gives a metaphysical proof for the basis of logic his book is not worth a dime." But that's not a reasonable challenge. All inquiry involves presuppositions, and "logic is a thing" is not a tendentious presupposition. Kimhi is saying, "We both agree that logic is a thing, but Frege's account doesn't account for this fact very well." It's not reasonable or relevant to come along and say, "Ah, but I won't grant that logic is a thing until you prove it!"
I don't understand HOW these things are not connected...
Quoting Leontiskos
Why is it? I contend this. Everything is up for questioning. How unphilosophical.
Quoting Leontiskos
I think it is precisely the issues I bring up that is missing from Frege, Witt, and perhaps Kimhi. And it is THESE questions that answer all three...
I feel like I'm stuck in an Abbot & Costello routine! If this really represents what Frege would say to me when I ask him whether he comprehends the word printed on that slip of paper he found on the beach, I could only reply, "Well, yeah, but Herr Frege, I'm not asking about extension or objects or what's permissible or impermissible in your philosophy. Have pity on a fellow beachcomber and just tell me whether you understand the word on the paper or not."
And I'll leave it at that.
There's a couple ways to read this, but at any rate, a couple obvious options:
1. Under the usual understanding of assertion -- just to get this out of the way -- it's perfectly ordinary for people to make claims the truth of which they do not know. They may indeed be aiming at truth, but when you loose the arrow, while you may feel some confidence of the result, you cannot know whether you've hit the target.
2. From the other side, once you "grasp" the truth of a situation, have you any choice but to affirm it? This would seem to be somewhat closer to the sense of assertion intended. In other words, Moore's paradox is a simple impossibility: to see the truth of a situation or a proposition is to believe it.
But I want to make a bit of a different point. On my (admittedly limited) understanding of the Tractatus, one thing a picture is entirely incapable of depicting is that it is true. A picture can show how things might be, and things may indeed be that way, but the picture cannot include itself in its depiction and vouch for its own accuracy.
Just so, my belief that a picture is accurate does not count as evidence that it is.
We have talked some -- whether we should have or not, I'm not sure --- about whether there's some sense in which propositions are self-asserting. In these terms, whether a picture at least inherently claims that things stand as it shows, even if it cannot itself substantiate that claim.
On the one hand, this seems a bit foolish. Pictures can show how things aren't, so why would they have to be claiming that things do so stand, how would they, and why would anyone care if they did: if all pictures claim to be true, you can ignore their claims. If, per impossible, a picture could show that it was the truth, that would be something to pay attention to. They can't, and claims are cheap.
On the other hand, in the wake of the Tractatus and Carnap and the rest, we got possible-world semantics; so you could plausibly say that a picture showing how things could be is a picture showing how things are in some possible world, this one or another.
The feeling of "claiming" is gone, but was probably mistaken anyway. In exchange, we get a version of "truth" attached to every proposition, every picture. Under such a framework, this is just how all propositions work, they say how things are somewhere, if not here. Wittgenstein's point could be adjusted: a picture does need to tell you it's true somewhere -- it is -- but it can't tell you if it's true here or somewhere else.
Are you puzzling over the context principle, is that it? Are you asking if Frege is literally saying a word isolated like this, not part of a sentence, is meaningless?
Don't worry about it. Frege is not that dumb. I believe Dummett's formula ends up being: "The meaning of a word is the contribution it makes to the truth conditions of the sentences in which it is used."
You can still get some straightforward compositional semantics out of that. But the approach Dummett is championing has to put sentences first: sentences have truth conditions, and words don't, so the sentence is where we start.
As for your "Berlin" example, you don't understand it. It could be a lot of things. Name of a city, name of a band, name of a book, an adjective describing a strain of flu. Without the context of a sentence -- and honestly much more context than that -- you can't know what referent "Berlin" is intended to pick out if any. You might know a lot of options, but even for a single word there are more possibilities than you can imagine.
[quote]Notice also that for Frege there is a structure literally hanging from the ?. So we have
Quoting Banno
The judgment stoke occurs once in the expression, at the beginning. It affirms the whole expression, not each individual line separately.
To this I will add:
Quoting Quoted in SEP 1879a: §2
My bolding.
Again, Frege moves the intensional judgement to the left, so that it has within its scope the remainder of the expression, and so sets the judgement aside, allowing the expression to be understood extensionally - that is, allowing the to instances of "a" to be identical.
Good point: 'raining' does not have the assertoric grammatical structure that 'it is raining' could be said to have.
No, I'm confident Frege would never say such a thing, and I was trying to get @Leontiskos' agreement on what he would say. I thought about including something specifically about the context principle, just to show I wasn't making that connection, but I decided to keep it simple.
Quoting Srap Tasmaner
An interesting takeaway from this little sub-thread: It's harder than I would have expected to come up with a individual term that will simultaneously be recognizable to (pretty much) everyone and also unambiguous. So sure, "Berlin" can be comprehended different ways. But that isn't really the point. The point is that there would be a finite number of candidate meanings, and while Frege might well say, "I'm not sure which one this piece of paper is referencing," he would not say the equivalent of "Huh? No idea what this could mean. I can't 'comprehend' any of the candidate meanings."
If this still seems not nailed down, maybe we should imagine the beach example as involving an absolutely unambiguous term -- "the Hope Diamond," say -- and just stipulate that Herr Frege has learned this term prior to his walk. Now we pose the question to him about whether he comprehends it.
Lastly, and I've said this repeatedly, this wasn't supposed to be some kind of "gotcha" about how Frege is contradicting himself about the existence of individual terms, or terms outside of functions, or whatever. I was trying to build a case, step by step, to show that we have alternatives about how to understand "existence can't be predicated." This was meant to be an early step in the argument. It goes all the way back to that thread on quantifier variance.
If you have the Tractatus at hand, do a search for "logical space" the space containing all possible propositions. Have a flick through the results. The way this appears to work is that some subsets of all the possible propositions can be put together consistently, providing a picture of reality, giving us then the task of choosing one picture of the world.
We can think that the cat is on the mat, or that the cat is not on the mat. We choose which to say is true. That judgement is distinct from the coherence of the picture in logical space.
So I am afraid it seems I, and I think others, do not see the problem.
Hence he presumes two truth values without giving any account beyond reference. 2+2=4 names the true; 2+2=5 names the false.
I'm happy to be shown otherwise.
I was a bit puzzled by this so I asked ChatGPT o1-preview the following question:
[hide="Reveal"]"Hi ChatGPT,
There is an ongoing discussion thread currently on ThePhilosophyForum titled "A challenge to Frege on assertion". It's inspired by a discussion in Irad Kimhi' recent book "Thinking and Being". I haven't read Kimhi's book yet but I have some acquaintance with background material from Frege, John McDowell and Sebastian Rödl. I also have some acquaintance with Wittgenstein's late philosophy but very little with the Tractatus.
In response to user Leontiskos who asked "...is it possible to see that something is true before going on to assert it?", user Srap Tasmaner replied thus:
'''
There's a couple ways to read this, but at any rate, a couple obvious options:
[snip]
[...] but it can't tell you if it's true here or somewhere else.
'''
I may be off the mark but the way in which possible world semantics is being evoked here reminds me more of Lewis than Kripke. If Srap Tasmaner is right in his interpretation of Wittgentstein's Tractarian picture theory of meaning, it would seem like what propositions (or "pictures") express (or "show") lack Fregean singular senses (rigid designators). On Kipke's picture, as well as McDowell's and Wiggins's understanding of Frege regarding singular senses, propositions about particulars (that are picked up by singular non-descriptive senses) can't be true of different objects (i.e. counterparts) in non-actual possible worlds. That's because they function as rigid designators. Setting aside for one moment the question whether or not McDowell's and Wiggins's understanding of singular senses aligns with Frege's own thinking, do you happen to know if Wittgenstein's Tractarian view of the picturing relations between language (or thought) and the world comport more with a "rigid" view of singular senses or rather with a more Lewisian "counterpart" view that would portray the "singular" components of pictures in covertly descriptive terms?"[/hide]
In submitting my question to ChatGPT, I first mistakenly selected the model GPT-4o rather than the new ChatGPT o1-preview. The main difference between the two models is that the second one "thinks" before answering. Here is GPT-4o's response:
[hide="Reveal"]Its great that youve drawn attention to the tension between Wittgensteins picture theory in the *Tractatus* and the rigid designator framework as developed by Kripke, and possibly McDowell and Wiggins.
In the *Tractatus*, Wittgenstein's picture theory suggests that propositions function as "pictures" of possible states of affairs. These pictures are made up of elements that correspond to objects in the world, and their arrangement represents the way those objects could be related. The truth or falsity of the picture depends on whether the represented arrangement of objects corresponds to the actual arrangement in the world.
Now, regarding your question of whether Wittgensteins view aligns more with a Kripkean notion of rigid designation or with a Lewisian "counterpart" view, I would lean towards the latter but only cautiously.
1. **Fregean/Kripkean view**: Frege's notion of a singular sense (or what Kripke later develops into a "rigid designator") implies that certain terms in a proposition refer directly to specific individuals, across all possible worlds. Kripke's "rigid designator" is closely tied to the identity of the object itself, rather than any descriptive characteristics it may possess in those worlds. For example, "Aristotle" rigidly refers to the historical philosopher Aristotle, no matter what properties he has in different possible worlds.
2. **Wittgenstein's picture theory**: Wittgenstein, in the *Tractatus*, doesn't directly engage with the notion of rigid designation or counterpart theory, but his treatment of propositions as pictures suggests that the components of a picture (which correspond to objects) can only represent a possible state of affairs without making claims about necessity across all worlds. The elements of the picture aren't inherently rigid in their reference; rather, their reference depends on how the picture relates to a possible arrangement of things. This is why some commentators see Wittgensteins view as more closely aligned with a descriptive theory of reference. The picture only tells us what could be the case, not necessarily what *is* the case about a particular rigid object.
This would seem to align with a **Lewisian "counterpart" theory** rather than Kripkean rigid designation. In counterpart theory, individuals in different possible worlds are related by resemblance, not by identity. So, Wittgensteins picture theory might suggest that the elements of a picture could correspond to different "counterparts" in different worlds, without the insistence on rigid identity. The picture doesn't necessitate that the same individual exists across all possible worlds, which contrasts with the Kripkean idea that a rigid designator must refer to the same object in all worlds where it exists.
3. **What about the singular sense in Wittgensteins view?** The key difference is that Wittgenstein doesnt seem to be as concerned with the rigid reference of singular terms in the way that Frege, Kripke, or even McDowell and Wiggins are. The *Tractatus*s emphasis is more on the structural relationship between the elements of a proposition and the world rather than on a theory of singular reference. So, his theory seems neutral or even in tension with rigid designation, given that a picture simply shows a possible arrangement and doesnt guarantee any trans-world identity for its elements.
To summarize: while Wittgenstein's *Tractatus* isnt directly engaging with possible world semantics as later philosophers like Kripke or Lewis do, his picture theory appears more amenable to a Lewisian "counterpart" view, where the elements of a proposition could be covertly descriptive and differ across possible worlds, rather than Kripkes rigid designation where they would have to refer to the same entity across all possible worlds. However, since Wittgenstein wasnt working with these concepts in the same way, its more an issue of interpretation and alignment rather than a definitive stance on rigid designation versus counterpart theory.[/hide]
And here is ChatGPT o1-preview's response, including its own summary of its initial thinking episode. I checked the accuracy of its quotations from the Tractatus and it got them right except for 2.022 that actually reads "It is obvious that an imagined world, however different it may be from the real one, must have somethinga formin common with it." The content o1-previews quoted as 2.022 is actually very close to 2.0271, which reads: "Objects are what is unalterable and subsistent; their
configuration is what is changing and unstable."
[hide="Reveal"][i]Thought for 12 seconds
-- Beginning of ChatGPT's internal thinking --
Clarifying Wittgenstein's perspective
The user examines Wittgenstein's Tractarian view, aligning it with singular sense rigidity à la Kripke, or a Lewisian counterpart theory allowing counterparts in different possible worlds.
Clarifying picture theory
I'm exploring Wittgenstein's picture theory, examining whether its components align with Kripke's rigid designators or Lewis's counterpart theory.
Sketching connections
Wittgensteins ideas about propositions and realitys correspondence resemble Kripkes rigid designators and Lewiss counterpart theory, which contrast how objects and names function.
Evaluating Wittgenstein's names
I'm thinking through whether Wittgenstein's names act as rigid designators, universally identifying the same object, or as descriptions that could denote different objects across various possible worlds. This involves analyzing philosophical perspectives from Kripke, McDowell, and Wiggins on singular senses in Frege's framework.
Clarifying Wittgenstein's view
Im piecing together Wittgenstein's notion that in the Tractatus, names consistently point to the same objects across different possible worlds, reflecting their stable reference to simple, persistent entities.
Analyzing language structure
OK, let's think it through: Wittgenstein's Tractatus uses rigid designators, consistently referring to the same objects across all possible worlds, differing distinctly from Lewisian counterpart theory.
-- End of ChatGPT's internal thinking --[/i]
In Wittgenstein's Tractatus Logico-Philosophicus, the picture theory of language posits that propositions are logical pictures of states of affairs. These pictures are composed of elementsnamesthat correspond directly to objects in the world. The structural relations among these names in a proposition mirror the relations among the objects in reality. This mirroring allows the proposition to "picture" a possible state of affairs.
Rigid Designators in the Tractatus
In the Tractatus, names function as direct references to objects without the mediation of descriptive content. Wittgenstein emphasizes that names are simple signs that stand for simple objects. For instance:
2.02: "Objects are simple."
3.203: "A name means an object. The object is its meaning."
This direct reference aligns closely with the notion of rigid designators introduced by Saul Kripke in his seminal work Naming and Necessity. A rigid designator refers to the same object in all possible worlds where that object exists. It does not pick out different entities in different possible worlds based on descriptive content; instead, it consistently refers to the same object across all possible scenarios.
Comparison with Fregean Singular Senses
Frege's concept of sense (Sinn) involves the mode of presentation of an object, which can be thought of as the way the object is given to the mind. In discussions by philosophers like John McDowell and David Wiggins, singular senses are understood as directly referring to particular objects without reliance on descriptive content. This interpretation of Frege aligns with the Kripkean notion of rigid designators.
Wittgenstein vs. Lewisian Counterpart Theory
David Lewis's counterpart theory suggests that individuals in different possible worlds are not the same entities but counterpartsdistinct individuals that resemble each other in certain respects. Under this view, a term might refer to different objects in different possible worlds, based on descriptive characteristics.
In contrast, Wittgenstein's Tractatus does not support this counterpart approach. Since names in the Tractatus are directly linked to specific objects without descriptive mediation, they function more like rigid designators. The objects that names refer to are the same across all possible worlds (or possible states of affairs). Wittgenstein writes:
2.022: "The object is the fixed, the existent; the configuration is the changing, the variable."
2.027: "Objects, the unalterable, and the subsistent are one and the same."
These passages suggest that objects are constant and unchangingthey form the substance of the world. Therefore, names consistently refer to the same objects across all possible configurations of facts.
Conclusion
Given the above, Wittgenstein's Tractarian view of the picturing relationship between language (or thought) and the world comports more with a "rigid" view of singular senses. The elements of the picture (names) are directly tied to specific objects, functioning as rigid designators that refer to the same entities across all possible worlds. This stands in contrast to a Lewisian "counterpart" view, where terms might refer to different objects in different possible worlds based on descriptive similarities.
Therefore, in the context of your question, Wittgenstein's Tractatus aligns more closely with Kripke's rigid designators and the Fregean singular senses as interpreted by McDowell and Wiggins, rather than with a counterpart theory that treats singular terms in covertly descriptive terms.[/hide]
Deciding what these terms refer to is done when one gives an interpretation to the letters.
Propositions have truth values in virtue of being names for the true or the false.
"Berlin" is not usually interpreted as a name for either true or false, so it doesn't have a truth value.
Quoting J
On this account, both "Berlin" and "2+2=4" are names. Indeed, if a proposition is considered to be a statement with a truth value, then any proposition is just the name of either the true or the false. Assuming bivalency, of course.
Frege sets up existence in terms of satisfaction - though he doesn't use that term. He uses the concavity as a version of the universal quantifier. So far as existence is defined, it is defined in terms of universal quantification. It was working through this that led to Model Theory. So there is much to be said here.
He has a pretty rigorous argument for indefinability. I think J wanted to see it too.
Just so you know, I'm not going to read that.
Quoting The Thought: A Logical Enquiry
A bit later we get Tarski's definition of truth in terms of satisfaction, getting around the recursion by using metalanguages. I'm contending that what Tarski does is a working through of the implications of Frege's system; that satisfaction is to a large extent implicit in Frege.
Edit: Satisfaction is a pretty straight forward notion. "The cat is on the mat" is true if the cat is one of those things that satisfies "...on the mat" just means that "the cat is on the mat" is true if the cat is one of the items in the group of things "...on the mat".
That's fine, but you can read merely my question to it since it's addressed to you too. I had thought maybe Witt's Tratarian picture theory of meaning could comport with a Lewisian "counterpart" view (since I'm not very familiar with the Tractatus, myself) but Frege's own conception of singular senses comports better with Kripke's analysis of proper names as rigid designators (which is also how McDowell and Wiggins also understand singular senses in general -e.g. the singular elements of thoughts that refer to perceived objects). The quotations ChatGPT o1-preview dug from the Tractatus seem to support the idea that this understanding of Fregean singular senses is closer to Wittgenstein's own early view (as opposed to Carnap's or Lewis's), also, although Witt eventually dispensed with the idea of unchangeable "simples" in his later, more pragmatist, philosophy of thought and language.
Almost everything I've posted in this thread.
There are a couple places where I was moved to think, but nothing much came of it.
Most of my posts have been pretty lazy, stuff I can post on auto-pilot. Sometimes I do this just in case I happen to know something someone else would find useful. If you asked me if I believe any of it, I'm not sure what I would say.
I like the stuff about the screwdriver. And I'm right about triangulation. Everything else was chit chat. Philosophical gossip.
You don't get Tarski unless you understand that his truth predicate doesn't mean anything. It's not the truth we talk about in ordinary language. Don't equate Tarski and the T-sentence rule. The latter has become a philosophical gadget in a variety of projects.
I think that like Davidson, you have reinterpreted Tarski for your own purposes. No shame in that.
This is the sentence in the OP that stood out to me:
Quoting J
I believe it follows from Frege's view of truth that assertion is integral to propositions. Think of the scrap of paper that says "Berlin.". Any effort to read it as a proposition will immediately conjure situations in which someone is asserting it. The mind is wired to look for purposeful communication.
When a logician separates assertion from proposition, meaning becomes unstable. The only source of stability is the potential for assertion.
"The cat is on the mat" is a string of letters. It's also a well-formed sentence in English, making it a locution. It can be used, amongst other things, to talk about the spacial relation between the cat and the mat. But it might also be used by a secret agent to give the order "Attack at dawn!". The step from a locution to an illocution requires some sort of interpretation, in which perhaps the parts are given a reference, perhaps some other sense. It might be used to say that it is tru that the cat is indeed on the mat, to assert that the state of affairs presented is indeed the case. It might also be used to ask if the cat is on the mat: "The cat is on the mat?". That it has the grammatical form of a statement does not imply that all that can be done with it is to make assertions. If it is used as something that can be either tru or false, then we have some grounds for calling it a proposition. We can consider the content of the sentence, the cat and the mat, and understand which cat and which mat, and yet not know if it is being used as a statement or a question or for something else entirely - perhaps to say that the dog, who sleeps on the mat whenever it is inside, is outside - The cat is on the mat" means that the dog is outside. And then there are perlocutions.
And so on.
All this is not definitive, nor complete, but just a list of some of the aspects that might be considered from even such a simple string of letters. It gets complicated, quickly.
Now one way of dealing with statements is to seperate out the things that are at least prima facie referred to, and to examine the structure of those references. As it turns out Frege showed how we might do this by placing the judgement stoke at the beginning of the expression, thereby separating out the extension from it's locutionary force - although he would not have described what he did in this way. Doing this allowed the development of a quite sophisticated area of investigation, that ultimately helped with developments in truth theory, Model theory, undecidability, modal logic, set theory and so on, and which is central to the workings of device on which you are reading this.
That looks to me to be quite tho opposite of "When a logician separates assertion from proposition, meaning becomes unstable".
So I don't understand your thinking here.
Forgive my extemporising.
:up:
In a way, the OP is asking about the extent to which meaning is use. In what circumstances can we drop use and still have meaning? This is assertoric force:
'assertoric force follows if a proposition expressed by an indicative clause is presented as relevant in a context made up of a subset of the hearer's factual assumptions."
You can already tell from that definition that assertion is generally going to be involved in the meaning of a proposition because you need to know context to discern what proposition is being expressed. Math is is different situation though. It has a semi-stipulated character, in part to avoid a paradox arising from Frege's work. This tells us that when we're talking about Frege, we're talking about a perspective that sees math as a matter of description, specifically of the contours of the human mind: of thinking. In the light of that, it becomes more interesting to consider his thoughts about separating sense and use.
More extemporizing.
Yes, thats how I understand it too. And for Frege, names are, in an important sense, outside logic, because logic only deals with things with judgeable content. Julian Roberts, to whom I often turn for insights into Frege, puts it this way: Logic [according to Frege] has nothing to say about anything that is not a statement [i.e.], something that can be true or false. The utterance ?house, for example [or ?Berlin in my example], is not a statement and cannot be of concern to logic.
Quoting Banno
Good. Im only vaguely aware of how Freges concavity differs from our modern universal quantifier, but I think I can still ask these next questions. The Fregean universal quantifier ranges over objects as well as formulae/functions, right? So maybe my question about Frege on the Beach (sounds like a hit song) could be phrased as: "When you comprehend the term ?Berlin (as Im going to assume you do, Herr Frege), does your comprehension depend on the universal-quantification symbol? And then, should you choose to use the term to fulfill a function, does the existence commitment change to ?x? So the idea is that ? can range over names or terms that are not (yet) part of functions. Clearly, Im trying to find a way to make a name (and its sense) a thinkable thought without violating Freges understanding of what logic can do. Does this sound at all sensible to you?
One of the best and most accessible parts of T&B is Kimhi's discussion of the four ways we can think about the relation of logic to thought (and reality). I wish I could refer you to this but I don't think it's online anywhere. He tries to develop an argument that, if successful, would answer your request. Oversimplified, here's the idea: If thought does not, necessarily, reflect reality via logic, that gives us a version of psychologism. Thought is just that -- merely thought. And logic represents the way we think, ideally. Kimhi agrees with Frege that this is a non-starter; he calls it "self-refuting":
It cannot ground the normativity of the logical requirements that underlie the objective purport of every claim about how things are -- including the claims of psycho-logicism itself.
In other words, it can't explain the very link you regard as so important -- that between logic and truth about the world. Kimhi goes on to talk about why the thought/world dualism isn't satisfactory either, but I don't want to paraphrase him to death. I hope this gives you a taste of how he justifies his views.
But that's the thing about philosophy, isn't it? I don't see the force of Parmenides' questions. But some excellent philosophers do. So I have three options: 1) I can assume I understand the issues involved, and I am right, and they are wrong. 2) I can reflect harder, assuming that Kimhi is smarter and better read than I am, and he wouldn't be wasting his time on this if there weren't something there. 3) Since the questions don't really interest me, and my time on earth is finite, I can choose to philosophize about something else.
Option 3, thus far, has worked for me.
(Do I really have to go back to the Tractatus? Whimper. OK, I'll take your suggestion.)
Quoting The Thought: A Logical Enquiry
Hmm. Does this amount to pointing out that any definition of truth would have to be true, thus opening up the regress? Or is it rather that, armed with our definition of truth, we need to use that very definition in order to decide whether the word applies in a particular case? The first option does seem circular to me. But why is second impermissible? Couldnt I just say, Yes, it is true that the characteristics that I claim define ?truth are present in this case? Showing that my definition of truth is correct is not the same thing as being able to develop and use it. Or is it? Is there something unique about truth that limits definition to correct definition?
No. It's basically that truth is integral to the act of assertion. If you give a lecture explaining what truth is, and I'm your audience, I have to already understand what truth is in order to discern what you're doing, that is, telling me the truth about truth. Therefore you can't teach it to me. It's part of my computer's BIOS. It's in my firmware.
I'll see if I can start a thread to go through it.
Maybe better than starting a thread, would you want to log into the Internet Archive and read some pages from Scott Soames' book on truth?
It's a safe website. Once you log in, you can borrow books. The pages relevant to Frege start on page 21. The previous section covers some issues about truth bearers: sentences versus propositions. That's fairly important for understanding Frege.
That seems right to me.
Quoting Srap Tasmaner
Okay, and I agree that this seems accurate.
Quoting Srap Tasmaner
That seems to be what Kimhi is saying:
Quoting Leontiskos
So that we then have:
Quoting Leontiskos
So for Kimhi it is more than a matter of possible worlds. For Rombout this is also true in some sense for Wittgenstein:
Quoting Frege, Russell and Wittgenstein on the Judgment Stroke, by Floor Rombout, 63
This is close, but it obscures the fact that "Berlin" correlates to "2+2" (or "4") and "Berlin is a city" correlates to "2+2=4." The latter two have truth values, and can be called names in reference to "the True." If I recall, in the source that Bongo Fury gave, on the pages following the citation he gave, Anscombe critiques this understanding of number.
Now does Frege think that "4" and "2+2=4" are both 0th level terms, as Banno implies? I actually don't think he does, but I suppose it's possible. He certainly understands that something which saturates a predicate like "...is a city," differs from something which "saturates" the predicate, "...is the True." He distinguishes between objects and sentences, even if sentences are objects vis-a-vis the True in a certain sense.
It can only occur once for an expression, but the question is whether a modus ponens is a single expression. What you said earlier simply does not hold:
Quoting Banno
Quoting Banno
As usual, you are failing to understand the sources you cite. "The judgment-stroke applies to the whole expression, therefore Frege does not use three judgment strokes in a modus ponens." This is a non sequitur.
Here is Rombout, building from my post <here> and Bongo Fury's insight:
Quoting Rombout, 44-5
One can speak about modus ponens in terms of logical consequence or logical inference. Both make sense in their own context, but Frege actually adopts the latter approach. For Frege a modus ponens requires three judgment-strokes.
You continue unabated in your conflation of Frege and your own approach. You are making the exact same interpretational errors that Russell and then Wittgenstein made regarding Frege.
You need context to make that distinction. If I ask you what the weirdest city in the world is, and you say, "Berlin", you have expressed a proposition. It's all about context.
Who are you quoting? Certainly not Frege. Assertoric force does not depend on the hearer.
Please quote Frege on this issue.
It is an Abbot & Costello routine. You've been given my testimony, Srap's testimony, Kimhi's testimony, and the testimony of Frege himself, but you still refuse to believe. On what grounds? Frege will not find meaning where there is no extension.
The answer here is that Frege reads the word through his understanding, and his understanding of meaning and truth has to do with the extension of predicates. It makes no sense for you to ask Frege what he would say about a piece of language without appealing to his understanding of language.
My memory of the Tractatus is that Wittgenstein also says that a picture is a fact, it's part of the world, and so to say this is a picture of that is to say that between this fact and this other fact there is a special picturing relation. And he wants to figure out what it means to say two facts are so related and how it is possible for them to be. (I'm thinking of this in part because Kimhi ends up talking about consciousness, right? So you might take consciousness as the locus of this relation, or even as constituted by it.)
The more natural move for later Wittgenstein is to say that sometimes we see something as a picture of something else, sometimes we don't, and that it is a far more flexible business than it might seem in the Tractatus. The duck-rabbit shows flexibility in what something is a picture of; the possibilities for what counts, or what someone might count, as a picture of a given thing are too numerous to contemplate. (Think of how often only a parent can understand the first indistinct words of their own child. Now consider the range of possible pictures of a dog, from that toddler's wobbly shapes to a cubist painting or an abstract sculpture, and "everything in between", photos, icons, words, pantomime, on and on. Clouds!)
I finished the Scholastic portion of Novak's paper, and I think I agree with you. It gets complicated, but I would essentially say that we can truly speak about fiction so long as the authors of fiction are genuine sub-creators (in Tolkien's sense). That is, we must say that in writing their books the authors of fiction create real truthmakers (or at least the sort of truthmaker that is proper and relevant to fiction).
That seems reasonable. Granted, I am a little bit surprised that Kimhi is so fond of the early Wittgenstein. I don't think a picture is a fact, and so I think the search for a fact-fact relation is a false start. I haven't read much where Kimhi speaks about consciousness and self-consciousness, but it seems plausible to me that he wants to move that relation away from world-facts and into the realm of consciousness. It seems clear that Kimhi accepts a logical subject in the way that (early?) Wittgenstein does not, and can thus introduce consciousness in a way that Wittgenstein could not.
Quoting Srap Tasmaner
Yes, and if this weren't true then I don't see how we would be able to err. Then: is an inferencethe thing between the lines of a syllogisma kind of picture and also quasi- or sub-assertion? If so, and if a correct inference is a logical truth, then the possibility of inferential error comes into view.
I suppose this is a somewhat new topic, but the thread is now becoming more diffuse. Are logical errors possible without [judgment, or a logical subject, or content to be judged]? Do those who fundamentally disagree with Frege's judgment-approach have any basis with which to account for logical errors?
Fiction is a minefield for discussions like this, and I don't want to derail the thread, if that's even possible, but I'll make one point.
My view is that in a work of fiction the author pretends to be telling a story, as she might tell a story about something that really happened. We pretend to believe she's telling a story. An author pretends to be telling the truth. (I think it's a pretty sophisticated thing, and it's easy to be culture-bound and miss how unusual it is.)
A relevant (for this thread) question might be: what exactly is an author pretending to do that he isn't? Can we say, there's the sentences you speak and the order you speak them in, on the one hand, and something else that makes your speaking "reporting a sequence of events" or "(merely) telling a (fictional) story" on the other?
Quoting Pierre-Normand/ChatGPT o1
Interesting (to me anyway) that this suggests a 'visuo-spatial' element to Chat GPT o1's process.
Shaky ground for me, but I don't think that's right. The alternative title for the Tractatus is "The World As I Found It". "The limits of my language are the limits of my world." There's that business with the eye, and the little picture showing how the eye is its own horizon, never included in what it can see. The issue of solipsism is addressed directly. There's a pretty strong sense of "I" at least in parts of the Tractatus, and it would probably be fair to call it "logical". -- Honestly not an aspect of the book I ever gave much thought to though, so I might be off base here.
Hmm, I'm not sure if I like the way you phrased this, but I see what you are saying. Something like, "The author pretends to be telling a non-fiction story." At the end of the day I think it will depend a great deal on what an author is actually doing, which is obviously tricky.
Quoting Srap Tasmaner
Yes, and it is interesting that in recent history fiction was thought to require a kind of disbelief-suspension-bridge (I forget the real name that is used). Some plausible device was used to connect the fiction to the real world.
Then, to take an extreme example, what did Tolkien take himself to be doing in his writings? He certainly seemed to be self-consciously involved in a less fictional act than, say, J. K. Rowling.
Quoting Srap Tasmaner
Right: Or: if telling a non-fiction story is a form of assertion, and telling a fiction story is not really assertion, then what is it? Frege talks about a similar thing in terms of the words of an actor on stage, and Kimhi considers this scenario (...in some earlier post I talked a bit about this). But what exactly constitutes the pretense in the author or kindergarten teacher who tells a fictional story? I'm not sure - haha.
Yeah that was the idea. Is assertion something added on to the words? If you can add on assertion, are there other things you could add on?
Another way to look at it: if you're not sure whether assertion is something we add on (rather than being built in), does showing that we can add something else instead of assertion show that assertion is something we add?
Add onto what? Are you thinking of a sentence or a proposition? If it's proposition, just examining what that is will indicate why assertion is integral.
And one last point -- sorry for the multiple posts -- the whole point of my view of fiction is that it is parasitic on candid account giving or reporting. If we did not already have such a practice of reporting on real events that happened to real people in real places, and so on, we could not pretend to report on events we've made up (and maybe people and places as well).
Right...
Quoting Srap Tasmaner
Quoting Srap Tasmaner
Maybe Kimhi would agree when I claim that it is strange to talk about non-intentional sentences. Supposing that assertion is one form of intentional 'force' (or simply intention), are there sentences without intention? And are there declarative sentences without assertion?
If "Berlin" makes no sense apart from context, does a sentence make sense apart from intention? If not, then it would seem that in "adding" assertion to a putatively non-intentional sentence, we are in fact either altering the intention that was already present, or else a dead structure of letters and words becomes a living form when intention is infused (an essential change occurs). It may be that in analyzing the materiality of a sentence and prescinding from intention we are doing something like examining a corpse, or at least a comatose patient.
Sentences or maybe utterances, depending on how you'd like to slice it. It's not obvious to me you can utter a sentence without uttering it in a particular way, which would include something like force.
I would love not to talk about propositions at all, so I'll leave that to you.
Frege, the godfather of abstract objects, dealt with propositions, so we're going to be mixing quiche and spaghetti if we don't talk about them.
An utterance is just sounds or marks. Literally, nothing else. A sentence is a grammatically correct sequence of words, but a sentence has no specific meaning.
A proposition is expressed by an uttered sentence. A proposition is along the lines of content.
George points to a whiteboard that has the number 2 written on it. He says, "That's a prime number.". He has expressed the proposition that 2 is a prime number. He did that by uttering the aforementioned sentence.
If this doesn't work for you, you've probably got a strong inclination for behaviorism and meaning skepticism. Frege is not your philosopher.
Yes - that is the Aristotelian realism route and I am comfortable with it. It says that fiction is ultimately a rearranging of sense experiences and memory. But a Platonic account will say that the reality that we experience in sense is a reflection of the Forms, and that we can perhaps experience the Forms directly. This is the view that fiction could be a "higher reality" via its direct participation in the Forms.
Then to bring this back down a bit, the point is that Tolkien obviously thinks he is doing something Platonic whereas H. G. Wells obviously thinks he is doing something Aristotelian. What this means is that Wells is pretending in a way that Tolkien is not, and therefore it becomes hard to give a single account of fictional intention to all fiction writers.
Yes and no ;-) I was tempted to say that ChaGPT's (o1-preview) summary of its thinking process had included this phrase merely metaphorically, but that doesn't quite capture the complexity of the issue regarding its "thinking". Since this is quite off topic, I'll comment on it later on today in my GPT-4 thread.
Very plausible. Taking down the words someone spoke leaves an awful lot behind. As musical notation is a somewhat limited representation of someone playing an instrument.
Coming back to fiction, it's probably a blind alley to think there's something added to the words in place of assertion; the pretense is that you are removing something and pretending you haven't. And the audience agrees to pretend you haven't -- to a degree, or in some particular way. ("Willing suspension of disbelief" is probably much too strong, if not just wrong, because people watch horror movies.)
A better form for my question would be, what have you removed? What's missing, that everyone kinda pretends isn't, when you tell a (fictional) story? Does it overlap with what's left out when you only have a record of the words spoken, the bare, lifeless sentences?
I agree that a picture is not capable of depicting that it is true. However, I question the practical import of that to some extent.
In my experience it can be important for me to recognize whether a picture is consistent with my observation of the way things go in the world. (My profile picture can serve as an example of a picture that is 'not consistent' with the way things go in the world.)
I think Frege would say that the fiction author has removed something from their words, whereas the fiction author would say that Frege has removed something from their words. Fiction may be inherently Platonic in that way. It may insist that it is giving more, not less, than what non-fiction gives.
Quoting Srap Tasmaner
But on the premise that fiction is less, I would suspect that an intention tertium quid is involved in fiction (though I am not sure whether it is a kind of quasi-assertion or else something with a different intentional force altogether). Does the fiction author make use of the assertoric force that the logician removes, as an ingredient in what he adds to the lifeless sentence in order to give it life? I don't know. What are your thoughts?
As an aside, my friend's child always engaged in "pretend" without any notice, as if she paid no mind to the boundaries of pretending and not pretending. My nephew, on the other hand, is very precise about where pretending begins and ends, even at a younger age than the girl. Part of the difficulty of all this is that pretending and playing is very different from the logical thinking that Frege and Russell prefer, perhaps to the point of incommensurability. Perhaps if we "knew" what we were doing when we pretend or play we would cease to pretend or play. I'm not sure if you can reduce logic or pretending to the other, and this may be because logic specifies and marshals intentionality in a way that play refuses to do.
(To ask her whether she was now pretending or not was much like asking someone to explain the punch line of a joke. Asking for illumination causes the sun to set.)
Pretending, as your examples demonstrate, is complicated, but I think it's actually very important to logic because of hypothetical reasoning (not to mention counterfactuals). I think it's very difficult to give an account of what happens when we entertain an hypothesis, but it looks a bit like pretending. When doing philosophy or mathematics, we say things like "Suppose I have an urn with 100 marbles in it..." and we could very nearly (?) say "Pretend I have an urn... " "Pretend you've drawn a red marble", and so on.
--- More to come later, but I really have to work for a few hours.
Can there even be an answer using speech act properties alone for that? The sense of nonreality afforded to fiction is surely something closer to intangibility.
"Frodo touched the ring" - fine
"I touched Frodo" - madness.
"Frodo often doubted his ability" - fine
"I often doubted Frodo's ability" - fine.
"I saw Frodo touch the ring" - a bit off, "saw" would have to be understood figuratively, as a stand in for "read". "I saw that Frodo touched the ring" would ring better.
So in a certain sense, nothing seems to be missing, besides the capacity for personal sensorimotor relations with elements of fiction. You can have beliefs and intuitions about them all you like, you just can't smell, see, taste, touch them (except figuratively).
Looks like that has a physiological/phenomenological answer to me, anyway. Probs off topic.
1. In order to assert a (declarative) sentence, I must first judge whether it is true or false
2. In order to judge whether it is true or false, it must have a judgable content
3. In order to have a judgable content, it must display assertoric force
4. In order to display assertoric force, it must contravene "Frege's Point"
The only question for me is whether (4) holds, or in what limited sense it holds.
It's fairly clear that assertion is integral to a proposition. The question is: what does it mean to separate them? By what means does Frege do that? If it's by way of a stipulated logical domain, yes you can separate them. In real life? No, you can't.
Quoting fdrake
That's close to my answer.
The obvious candidate for what's missing is belief, but I don't think that's quite it.
(I'm only indulging here because I keep seeing echoes of the actual topic...)
The main pretense in story telling, I claim, is about the story teller. They pretend to know a story they're actually making up (or that someone else made up). In early prose fiction, there's often a bit of BS at the beginning about how the writer stumbled on these letters, how he came to have this diary, or (nearby in poetry but right time period) some mad old man stopped me on my way to attend a wedding.
I think more than belief is at stake, because we judge beliefs on how they were arrived at. The challenge of someone who doesn't believe a story you're telling, even a true or at least honest one, is "How do you know that's what happened?" It's not just a question of whether the teller believes the tale, but whether their life history entitles them to it, gives them warrant to tell it. Hence the pretend warrant fiction writers sometimes display.
So yes, somewhere back in the chain of how I come to be telling this story, to be in a position to tell this story, there must be witness or even participation. I was there and I saw it, or I had it from a guy who was there. The storyteller pretends to be such a person.
This is, perhaps, a more colorful version of the Parmenides stuff.
One consequence of such a view might be that it's not really the tale we believe but the teller. We do not adopt a propositional attitude of "belief" toward the story, except perhaps as a consequence of adopting a social attitude of "trust" toward the storyteller.
--- back to work ---
Quoting Quoted in SEP 1879a: §2
Sure. What I was at pains to set out in the first few posts here is the difference between asserting a statement and understanding its content. Both involve intentionality, with the "t"; but we can understand the content of a sentence separately from it's illocutionary force. And here I am using a language unavailable to Frege, but which owes much to his work. Frege showed us that if we treat the intentionality (with a "t") of the content extensionally (without a "t") we get some very interesting results.
That's true, but I don't think that sort of hypothesizing is susceptible to formal logical analysis, as it is presupposed that the subject is doing this and I don't think formal logic can circle round itself to account for such a presupposition.
Quoting Srap Tasmaner
The historical development of how a fictional story is told is interesting, but are verification and warrant really at the center of fiction, at least in our own day and age? Or related at all? Isn't it a category error to challenge the fiction author regarding warrant?
I suppose if we want to make fiction very logical we can think of it as an experiment in counterfactuals, and of course fiction with a strongly didactic motive is intended in that way. I mostly think that because fiction is a less univocal category than logic, logic won't make sense of it. Logic can work on something which has a clear and stable intentional character, but the raison d'être of fiction (or logic) is not available to logic in this way. Like "Berlin," fiction need not be or mean one thing. I don't think all fiction authors are involved in the same sort of intentional stance towards their work.
(Out until tomorrow - take your time!)
Quoting Leontiskos
Good. Names are given meaning by being given an interpretation. For propositional logic that interpretation is just "?" or "?", something that is quite explicit in Frege. But of course there followed Russell's paradox, the controversy about Basic Law Five, the theory of Definite Descriptions, possible world semantics, rigid designation and so on. IT all became quite complicated, and very fruitful.
Yep. "Berlin" names Berlin. "Berlin is the weirdest city" names the true (!). But that's not an end to it, since we can also take "Berlin is the weirdest city" and treat of its parts, concluding that if Berlin is the weirdest city, then something is a city. And here we move from propositions to predicates, from the 0th level to the first level.
Again, it is important to note that the very same sentence may have more than one logical treatment. seems to miss this.
Quoting Leontiskos
I think these are the right considerations, although I think you can remove the assertion in "real life" too.
Quoting Leontiskos
We could look at this from a different angle: What would it mean for someone to hold to "Frege's Point" to the extent that (4) is true? According to Kimhi, it would mean that they cannot do logic, for logic requires the ability to judge and assert declarative sentences (cf. 5).
Is it plausible to attribute such a doctrine to Frege? Does he really want to divorce assertoric force from sentence to such an extent that the sentence cannot be judged true or false? If not, does he have the resources to stop short of that pitfall? Kimhi seems to say, "no."
(I agree with Kimhi that Frege's analysis of assertoric force is not "natural," but beyond that I'm not convinced that it is as detrimental as Kimhi claims.)
I haven't been able to follow this. But at the beginning of this thread I had an intuition that there was some blurring of the notion of force in Frege that has been set out in subsequent work, which is why I went to the trouble of explicating the nature of illocutionary force. "Force" here is used to talk about intentionality, about what we are doing with the words at hand. So we speak of a difference in force between "Grass is green" used as an assertion, command or question. That's illocutionary force, operating at the level of sentences. There's also a difference in using "Berlin" for a city, a person or a rock band, and this might also be called a difference in "force". My understanding is that in choosing the judgement stroke to range over the whole expression Frege removed the illocutionary force. But the "force" that denotes remained. Hence we are able to use the same letter for the same item in the expression, giving us extensionality.
Frege may well have thought that proper names relied on quantification. Russell, arguable, did just that with his Definite Descriptions. But it's no longer so popular.
My point is that first and foremost the fiction writer *pretends* to have such warrant. In early prose fiction this is almost universal (in English anyway).
Nowadays, we're used to how fiction works and it's dramatically less common to go through this little dance.
And the point of all this is to clarify how we usually offer and receive declarative utterances, so that we know what's been stripped away when we consider the bare words, as we might when playing at logic.
I *think* this is in the neighborhood of Kimhi. I'm under the impression he wants to restore the thinker to the thought, or maybe it's thinking as what links what is thought to what is. I haven't put a lot of time into figuring out what he's after, obviously.
It's not novel to say that something is stripped away when we engage in logical analysis. It's more or less the point. The question is whether what you have left, that you'll submit to logical analysis, is what you think it is, and whether the pieces fit when you try to reassemble the living use of language.
It's just that so many of the reviews take this as central. It seems these folk would scrap modality. We do think things like "what if I hadn't answered your post?". So perhaps they are wrong and there is no mystery here. That would help explain why no one has been able to set out Kimhi's argument coherently.
I've been one who is inclined to think that ChatGPT and such are not at all mirroring how human minds work, since they are in the end only picking one word after another based on preferential probabilities. I'm now entertaining the reverse view, that many human minds are indeed also only picking one word after another based on the reaction they get. :worry: Hence Trump and Trolling. And many of the replies here. And perhaps Parmenides?
That's my understanding, and how I read Frege's comment. To judge that a given definition of truth is true, one already must have a grasp of the nature of truth.
Hence Convention T, the minimum that must be the case. "p" is true if and only if p.
Can you give an example of that?
Yep. It might be helpful to add "statement" between "sentence" and "proposition". A statement is the concatenation of a noun phrase and a verb phrase. "The cloud is thoughtful". They differ in syntax from questions and commands, although these distinctions blur at the edges. "Is the cloud thoughtful?" "Make the cloud think!".
I find it useful to think of propositions as that subset of statements that take a truth value - so maybe not "The cloud is thoughtful" and maybe not "The present King of France is Bald".
What's perhaps salient here is that we can understand what a statement is about, and indeed, what it would take to make it true or false, while not knowing if it is true or if it is false, and certainly without having to make a judgement as to it's truth. There have been plenty of examples hereabouts - "the grass is green", "the cat is on the mat".
And again we have the important difference between the content of the statement and what is done with the statement.
Quoting frank
Sure. But one can utter a sentence without expressing a proposition. And without making a judgement as to the sentence's truth.
If you understand what "the cat is on the mat" is about, it's because you're providing a phantom context for it. The OP alludes to this. There just is no proposition where there is no context of utterance. You can easily invent that context though, and voila: you have a proposition.
There's a famous incident where an English colony in North America disappeared without a trace. They're called the "lost colony." The people who came back looking for them found a tree that was supposed to be used for emergency communication (in case they were attacked by the natives.) But the previously agreed upon code hadn't been used. Instead there was one word carved into it: "Croatan." Ever since then, people have tried to understand what the lost colony meant by it. Croatan was an Algonquin chieftain. Did they mean that Croatan killed them all? Or did the crops fail and they had to go live with Croatan? You see, to sort out any meaning in the communication, you have to imagine the context in which it was uttered, in other words, you have to imagine it being asserted, whether it actually was or not.
Quoting Banno
Definitely. :up:
I don't think anyone has made that claim. You probably need to understand the truth conditions, but not whether it's true or false.
Well, perhaps you haven't. Then we agree that there is a difference between what a sentence is about and what is done with it?
So it'd be neat to set up a system where we seperate out the judgement about our expressions from what they are about, so we could work through any inconsistencies in their content apart from their force.
Enter, Frege.
I might not be understanding what you're asking, but I believe that in order for a sentence to be about something, it has to be used. Meaning is found in use.
Quoting Banno
If you're talking about an artificial environment that's pimped out with a foundation of axioms, then yes, you probably could do that. If we subsequently want to bridge that to ordinary language we'll probably end up with Chomsky and an innate human language which can be identified by analysis of the world's languages (to see what words they all contain.) I figured that wouldn't be your cup of tea.
So could you not understand what a sentence is about unless it is clear it was being used to make, say, an assertion rather than ask a question? Isn't it a bit more complex than that?
Seems to me that "The cat is on the mat" is about a cat and a mat. And we at least have some idea of what that piece of paper scribed with "Berlin" might be about.
Isn't being about something just a part of the use?
So can't we understand what a statement is about without asserting it to be true or false?
Perhaps we might agree that one might understand what an utterance is about, but not if it were a question or a command... we might partially understand it... or understand part of it.
Maybe it's only important to philosophers and other such model builders.
On the other hand, I think people often tend to treat memories as a class of "pictures", broadly, that vouch for their own truth by being the kind of picture they are. And of course they're wrong.
It's an interesting question though. What was Wittgenstein trying to block by making this point? I should go back to TLP and look, but one thing that comes to mind is this: if you want to know if a picture presents the truth, you need another picture that says that. You can see where this is headed.
It seems to be a denial that there is any self-evident truth -- which would be handy for capping off the regress -- but that's not quite right; I think the claim would be that there is no substantive, we might say, self-evident truth. It's in the TLP (according to my lazy history of logic) that we get the presentation of tautology as a true statement that says nothing. And if it says nothing, evidently not a picture. So the truths of logic are something else entirely, and it is only there, among these whatever-they-ares, that we get self-evident truth.
In a raw sort of way. Maybe that's enough.
This is some rambling.
Belief in a story would be a different flavour of belief than the one in this thread anyway. Telling a story is, at least, a sequence of sentences presented with different forces and roles, and we've been dealing with single sentences with possibly a single illocutionary force.
Belief in a proposition vs belief in a story. Minimally belief takes the form "x believes that p", but belief in a story doesn't even seem to have an easy parsing as modal applied to a collection of sentences... it's hard to tell which sentences. The sentences of the story? That wouldn't do, since no one believes "Frodo went to Mordor" is true, they just believe it's true that Frodo went to Mordor in the Lord of the Rings. And it's precisely the ability to stipulate that we must evaluate the story in narrative terms which we're after, the missing mechanism of stipulation, rather than the ability to believe in the story's statements once construed as being part of such a stipulation.
The boring deflationary answer is just to say that understanding a given text as a story means just the following: belief in any presented sentence in that text is equivalent to believing that that sentence is a part of the text. Line of the story as story event. I believe that Gollum lied and cheated if and only if it says so in the book.
Suspension of disbelief works in opposition to the latter boring answer. Like the deus ex machina eagles at the end of Lord of the Rings. A flight of massive eagles coming in and saving the day, really? You only doubt it, "c'mon, really?" because you believe it happened in the story, but it could be felt to collide with the story's narrative. No one would doubt the eagles came, they just would doubt whether in some sense they should've.
Which gives an opportunity for more expansive, and more boring, deflationary answer.
Understanding a given text as a story means just the following: belief in any presented sentence in that text is equivalent to believing that that sentence is a part of the text in its context of evaluation. Line of the story as story event in the context of the story. I believe that Gollum lied and cheated if and only if it says so in the book and that seems reasonable in terms of the rest of the world and the story's narrative.
If the latter is true, it doesn't say anything insightful at all.
Just one follow-up now:
Quoting frank
I still don't see that this follows. Can't you have a mistaken or in-part inaccurate understanding of what truth is, and discover in the course of my lecture what the "truth about truth" is? You seem to be saying that you wouldn't be able to recognize the "truth about truth" unless you already had the correct understanding of what that is. But couldn't the lecture process itself provide the necessary enlightenment? i.e., in the course of listening to me, couldn't you find yourself agreeing with me and simultaneously realizing "Ah, of course, I now see why I believe this to be true"?
If this is better addressed in Soames, then no need to answer. It's just where I'm currently puzzled.
Yes, which is why I keep trying to find some better, more perspicuous ways to carve up "force." I was leaning toward believing that "force" itself should be strictly separated from both assertion and illocution -- or that, at least, Kimhi would want us to think of it that way. I'm no longer sure, based on the many interesting comments from yourself, @leontiskos, @srap tasmaner, @frank and others.
Quoting Banno
This is more or less where I was going with my hard-to-follow speculations about the universal quantifier. Russell's TDD postulates existential quantification for proper names, if I'm remembering rightly. And you had said that "so far as existence is defined, it is defined in terms of the universal quantifier." So my question was, If Frege does not accept the TDD, can we spell out how universal quantification might still give us something to think about when we think about names?
This is a good response. Heidegger relies on exactly this hermeneutic circle in everything he writes. It's prima facie a reasonable description of learning.
"make-believe" is a lovely phrase. I should have used it.
I'll post Frege's words, and the way Soames formulates it:
There's a fair amount of discussion after this this passage. This source may require a university IP.
I'm not sure: here
I think the upshot of the argument is that the concept of truth has to be innate, or that it's an aspect of communication. We can analyze it out and contemplate it, but the longer we do that, the less sense it will make.
Right. Context is just part of discerning what proposition is in play.
Here is Frege on this issue:
Frege interprets the parts in brackets as, A proper name in the logical sense, which, is a sign for an object. Ergo: if the last three words of (3) and (4) were absent we would not know that 'Berlin' is a city (because proper names are not predicative). Frege grants that (3) is unintuitive given its redundancy, but he is unperturbed.
Soon after this, Frege expresses frustration that 28 years after he introduced the material conditional mathematician and logicians continue to resist it as something bizarre! Curiously, in speaking of his conditional stroke, he claims that the relation designated by the conditional stroke is not strictly speaking something that obtains between thoughts, but rather that the sign for the conditional stroke connects sentences. This seems to indicate that he posits a non-assertoric difference between the two ps in the premises of a modus ponens.
I don't think anyone has claimed this. The point that Wittgenstein makes has to do with conditions for truth or falsity, not a decision.
Quoting frank
Yes, exactly. :up:
In those terms the question is simply whether Kimhi sees something which "displays (assertoric) force [without being a self-identifying display]" as having some kind of force. Regardless of words, Kimhi's point seems to be that Frege's Point excludes the possibility that a sentence displays assertoric force. I don't see Kimhi in any way moving away from assertoric force to some kind of general force.
Quoting J
In the parts of Frege that I have read he shows no interest in the epistemic aspect of a proper name, which is probably a credit to him. He takes it for granted that a proper name can designate an object.
A lot of what Kimhi (and Rodl) are doing is probing presuppositions of formal logic. There is a lot of magic involved in formal logic, and I suppose the question asks how much presuppositional magic is to be granted. Kimhi's broader thesis is that by adopting a Fregian approach first-order logic has merely side-stepped some of the biggest problems of philosophy, which persist as elephants in the room rather than vanquished foes.
-
Quoting J
Frege understands that prefixing "It is true that..." to a sentence both adds something and doesn't add something. It is slippery. But the odd parallel is that his judgment-stroke also adds something and doesn't add something, in just the same way.
Granted, and I pointed to the same thing early on in the discussion:
Quoting Leontiskos
-
Quoting Srap Tasmaner
Sure, but it's worth recognizing that it was never anything more than a dance.
Quoting Srap Tasmaner
Yes, that's a very good way to put it. :up:
So if we take our shears to an asserted sentence we can apparently remove the basic assertoric force. Then if we take our shears a second time we could apparently remove the grammatical aspect and achieve the result of "mere words." Then a third time, and be left with mere tokens or letters. One way to phrase the question is this: Is the "sharpness" of Frege's shears intelligible or arbitrary?
-
Quoting Srap Tasmaner
This is the tangent that most interests me in this thread: How is it that logic becomes separated from thinking, judgment, and consciousness?* Ironically Rombout seems to trace this to Wittgenstein, in which case, pace Kimhi, (early) Wittgenstein does not save us from Frege, he takes Frege to the place that Kimhi finds most problematic.
* But not construed as Banno's full-on logical nominalism, where logic is merely symbol manipulation. That is called metalogic or metamathematics and is not generally seen as logic itself. The result was not logical nominalism, but instead a sort of reification of truth as something that exists independently of subjects and minds. A kind of overcorrection of "psychologism."
This is part of what I was trying to get at when I said that fiction is much less univocal than logic. :up:
Quoting fdrake
Yes, good, and we can take this in a Platonist direction contrary to your second deflationary theory. The question of whether logic or fiction is more 'real' can be assessed according to the question of whether logical analysis or narrative is more foundational to human life. If narrative is the meta-category of human life, then any genre of story (including fiction) will be more real than logic. On the other hand, if scientia is the telos of human life, then logic has a primacy over fictional narrative. I think there is a very strong case to be made in favor of the view that narrative, not logic, has the primacy.
https://thephilosophyforum.com/discussion/comment/933474
Quoting J
What if the function, once seized upon by the sentient individual with intent to use it, becomes something essential to what exists? This because under the influence of the sentient controlling it, it acquires the property of how its being used such that specifically, that how is the sentient beings willful decision to ascribe perceived attributes to the previously empty subject.
A generalization from the above claims that sentient individuals construct reality from possibilities by willfully predicating empty subjects (possibilities) with attributes meaningful and therefore useful to sentients.
The how of predication practiced by sentients attaches perceived attributes to otherwise empty subjects. The specifics of this ascribed how is determined by the sentients natural impulses. This leads us to conclude that the conscious worlds of sentients are extensions of themselves.
Right.
Quoting Leontiskos
Right.
Quoting Leontiskos
Not using that language, but I'm struggling to find a better way of talking about Kimhi's very unusual (to modern logic) commitment to two-way capacity and the primacy of affirmation and denial over the more usual "verb says something about subject" approach. Part of my motivation for wanting to mess with this language and perhaps find a way to bring a more basic concept of "force" into play is that Kimhi is not what you'd call a term-clarifier. He's no Kant! He'll take several shots at a difficult term, but one senses he hasn't really pinned it down. I was trying to kinda help him out, but as I say, I'm no longer sure it would be removing any mud from the water, even if I succeeded.
If not assertion or illocution or denotation, then what is force? There is still no clear account of what this thread is about.
Quoting J
Quoting Roberts
If the subject is empty, the object is featureless, and the predicate is unreal, then thats a triad of zeroes, and I dont see how a function linking three zeroes can produce a non-zero product.
Quoting J
Formalizations of subject_object_predicate strings of syntax without a goal-oriented observer making public, measurable, and repeatable predications are useless and meaningless permutations of non-referential markings.
The sentient individual as observer with perceptions and intentions has standing in the world, and it goes about making predications. The predications, curved by the force of the observations, acquire usefulness and meaning through their attachment to the observer.
Quoting Banno
If the figurative use of force (as in force of personality) can be linked to physical force (as in: gale force winds), then we can start with the physical definition of force: force is a type of energy; energy is the ability to move; energy has two states: sharply bounded energy (as in the animation of a material object); softly bounded energy (as in the animation of an electromagnetic field).
We can parallel the two states of energy with the two states of sub-atomic elementary matter: a) the particle form of elementary matter; b) the waveform of elementary matter. At the scale of human experience its the comparison of a block of ice with a room filled with steam.
The binding phenomenon linking figurative force with physical force is consciousness.
The binding gravitational force (physical) linking the firgurative force of supposedly abstract language (also physical) is the consciousness of the sentient individual using language to design a plan of action to fulfill its intentions.
So, the focus of this thread, as implied by references to Julian Roberts, examines verbal and sentential logic through the lens of the gravitational force of consciousness as it links language to physical phenomena via observation. The gravitationality of language herein made explicit is implied in other posts in this thread.
The above paragraph is a compact wealth of complexity, and thus its hard to state in simple language what is the focus of this conversation.
Well, its certainly wandered off in many directions. I just reread my OP, which included my optimistic belief that we didnt have to be concerned with what Kimhi says in order to understand the question I was raising. Ha! But Im glad to have stimulated a lot of interest in Kimhi.
I think now that the challenge to Frege on assertion is just that, and probably never should have wandered into speculations about different kinds or modes of force, even though Kimhi himself often seems to do that. The challenge asks whether we have to understand all actual occurrences of p in the same way that p is understood in modus ponens that is, as a logical unit that can be handled within a formal system. The trivial answer is, No, of course not, people say all kinds of stuff. But I thought, and still think, that a much deeper question is being raised here, a metalogical one about how what we think and can say is related to our existence claims about what is. Maybe another way (not in the OP) to formulate the challenge would be to ask, "Does a strong formalism such as Frege's invalidate whatever can be said or thought about p in ordinary language?" By "invalidate" I mean "render meaningless/useless/incoherent" or, for short, unthinkable, despite what we may believe at the time about our alleged thought?
I think that in order for the critique to make sense it must be linked up to some goal of Kimhi's. Kimhi must be made to say, "This point in the OP matters because it can be linked up to my larger concern of X."
Quoting J
Does Kimhi ever directly attack Frege on that front? On the existence-predicate?
Quoting Leontiskos
The difficulty I have with Kimhi is that we are considering the foundation of his project, and that foundation seems to be based on two misreadings: first, Wittgenstein's misreading of Frege that Kimhi follows unquestioningly, and second, a misreading of early Wittgenstein. If Frege is bad then early Wittgenstein is much worse, and it is muddled for Kimhi to think that early Wittgenstein is his ally against Frege. Kimhi thinks Frege is too thin, whereas early Wittgenstein was saying that he is too fat. I see concentric circles of the "any stick to beat the devil" fallacy, where one affirms a thinker whose conclusion they desire, even if the arguments to get there do not hold up.
Kimhi is right that Wittgenstein disagrees with Frege's judgment-stroke, but he seems to have overlooked the fact that it is for a completely opposite reason than his own. And Kimhi is right that there are problems with first-order logic, but I don't know that Kimhi's critique itself holds water, at least on this assertoric front. In longer-lasting systems of thought such as Catholicism one comes to be very careful about genealogical arguments, and the OP seems to represent a poor genealogical argument. Kimhi sees a problem with first-order logic, and he wants to trace it to its root. But there is no obvious root, and in tracing it to Frege's judgment-stroke Kimhi seems to have alighted on a false genealogy.
I think Rombout gives a much sturdier genealogy: the cleavage of epistemology from logic comes from Russell and Wittgenstein's misappropriations of Frege. Is some of it Frege's fault? Probably, but Wittgenstein is the central actor here. Wittgenstein's "solution" to the foundational Meno dilemma is to have a radical divorce between epistemology and logic. This is simply a non-starter if logic is supposed to provide an account of how progression in knowledge occurs. As Rombout says, Frege and Wittgenstein have an entirely different understanding of what 'logic' even means.
...and the more Frege I read, the stronger he stands against Kimhi. To take one example, Narboux's Notre Dame review ends by pointing out a problem in Kimhi's Wittgenstenian-colored idea of propositions being understood in large part in light of negation. This is a mistake that Frege, Thomas, Augustine, Parmenides, and probably also Aristotle all avoided. Frege's understanding of 'p' in that metalogical sense seems to in fact be better thought out and more robust than Kimhi's (although if Frege did not understand the difference between denial and negation then part of this was a happy accident for him).
Here is Russell:
Quoting Frege, Russell and Wittgenstein on the Judgment Stroke, by Floor Rombout, 45
-
Ordinarily we must take something away from a statement in order to sequester the assertoric force, because the assertoric force is a natural part of a declarative sentence. In Russell and Wittgenstein's misunderstanding Frege's judgment-stroke is something added on to a proposition or "assumption," and hence becomes a symbol in its own right.
For Frege it is more complicated. For Frege it is a stroke, not a symbol. It is "syncategorematic" (Kimhi) and hence is in no way on the same plane as the symbols of the sentence. The difference between a mere horizontal and the horizontal with the judgment-stroke added is a distinction in mente, and exists for the purposes of logic and inference. The judgment-stroke is sui generis, and this reflects Kimhi's emphasis on the fact that thinking is unique. It is a bit of performative language rather than descriptive language.
If there is some problem (qua Kimhi) with Frege's judgment-stroke it is an incredibly minor and subtle problem. Wittgenstein's complaint is more intelligible, but it is a one-way ticket to a destination that Kimhi will have no part of (which is apparently why he snips Wittgenstein's critique out of its context each time he references it in his book).
I think the most fruitful framework for discussing that question would be one that starts without ontological commitments, with something like ontological antirealism.
You appear to be agreeing that we can't have unasserted propositions in real life, even if the assertion is only hypothetical or potential.
I will simply note that, yet again in misrepresenting Frege, you provide no source for your claims. Cf.
Quoting Leontiskos
I don't think this really addressed any of what I wrote by making some arbitrary functional psycho distinction. Frege/Tarski/Aristotle without the metaphysics/epistemology/psychology behind the truth values.. what does it matter? Calling their logical systems functional doesn't MEAN anything. It is just a way of expressing language.
If you find a logical system that says "The sky is blue" and the "snow is white" and all you are doing is writing expressions like, "This is a fact." "this is a true assertion".. what the duckn difference does it make if you cannot show why it's true, or how it's true?
Why shouldn't it make a difference? Is justification the only thing that matters? The only thing we can talk about? If you want a thread on justification then you should start it. This thread is not about justification.
"The first point I want to call attention to is that according to Frege, truth is a property of thoughts or propositions in the sense discussed in chapter 1. For Frege, sentences are vehicles for expressing information. The thought expressed by a sentence on a given occasion is the information content carried by the sentence on that occasion. When one assertively utters a sentence, typically one says or asserts the thought expressed by the sentence on that occasion. Thus for Frege, assertion is a relation between an agent and a thought." --Understanding Truth, Scott Soames
When he mentions the first chapter, Soames is talking about an examination of the relationship between utterances, sentences, and propositions, with the goal of explaining why the concept of a proposition is indispensable. Did you have some source that conflicts with that?
Ok, what do you think it's about? I still don't understand the point.
As opposed to what?
Exactly. I think Leontiskos and I are talking about different Freges. :grin:
Your quote nowhere says that for Frege a proposition is a thought. Do you realize that?
Quoting frank
Have you read the OP?
Quoting J
Here is IEP:
Quoting Frege | IEP
-
Quoting frank
Those who don't know what they are talking about probably shouldn't be giving lectures.
I think pretty clearly says that. What did you think a proposition is for Frege?
Again, Soames explains Frege this way:
"In general, when we want to refer to the thought expressed by a particular sentence, we use an expression such as "that S" or "the proposition that S". The use of the expression indicates that something is being said about a thought (proposition)." ibid pg. 22
You seem bound determined to be vague and ambiguous in your claims. I'll leave you to it.
Uh, ok. Thanks.
Hi! I was hoping to get some clarification from a professional. Did Frege think propositions were thoughts? Abstract objects, but basically thoughts?
Now you are getting into metaphysics, I was told that this shan't be done for this discussion.
I don't think abstract object implies any ontological commitment. It just means it's not a physical thing, but it's not a mental object like if you're picturing a flower in your mind. An abstract object is something I could be wrong about, for example if I say that 2 squared is 5.
Why would that not be ontological? You are literally discussing someone's understanding of what an object is. Pondering the nature of objects/entities seems to fit that pretty well.
I don't think those two quotes speak against the claim that Frege is equating propositions with thoughts in the specific sense in which he understands the latter. The quote in Foundations of Arithmetic seems meant to distinguish the thinking of the thought from its being true. This is quite obvious if we consider the thought (or proposition) that 1 = 2.
The IEP quotation seems to use "proposition" rather in the way one would use "sentence", or well formed formula. So, the distinction that is implicit here parallels the distinction between a singular sense (i.e. the sense of a singular term) and a nominal expression in a sentence. If we think of the proposition as what is being expressed by the sentence i.e. what it is that people grasp when they understand the sentence, what its truth conditions are then, for Frege, it's a thought: the sense (Sinn) of the sentence.
Thank you!
I get that. It's just that when I've tried to pin down the ontological significance of "abstract object", the answer seems to be that this question doesn't need to be answered. We're more in the realm of just identifying what we can't do without.
I began writing my earlier response before I read your request to me. Let me just specify that I hardly am a professional. I did some graduate studies in analytic philosophy but I don't have a single official publication to my credit. Furthermore, a few posters in this thread would seem to have a better grasp on Kimhi and on Frege than I do, and that includes @Leontiskos even though we may currently have a disagreement.
If "thought" is understood in a specialized sense then, sure, if you like. Again, my point is that these invisibly specialized senses of "proposition" and "thought" are not getting us anywhere.
Frank is just trying to uphold his idea that in "real life" we don't talk about unasserted declarative sentences, without actually going through the work of defending it.
Well that's what has become the discussion oddly. We must talk about how the logic is presented but then nothing that would ground the logic itself (thought, psychology, epistemology, metaphysics, science)? Odd. This has been a theme it seems of a lot of language philosophy. For example the Tractatus asserts atomic facts, states of affairs, and objects, but grounds them in nothing. So the whole theory of correspondence of propositions to states of affairs in the world is taken on simply taking the original assertions at face value. There are no proofs for it. There is no evidence for it.
If, for example, propositional thinking is said to be part of the human animal, that needs to be explained. I was under the impression that philosophy involves a certain amount of rigorous explanatory power, not simply various assertions.
Quoting Leontiskos
I talked about that a lot. I don't think you saw it.
I would have thought that those specialized senses of "thought" and "proposition" struck at the core of Frege's thinking about logic in general, and his anti-psychologism in particular. Frege famously conceived logic as "the laws of thought". And he understood those laws in a normative (i.e. what it is that people should think and infer) rather than an empirical way (i.e. what it is that people are naturally inclined to think and infer). We might say that Frege thereby secures the essential connection between logic as a formal study of the syntactic rules that govern the manipulation of meaningless symbols in a formal language and the rational principles that govern the activity of whoever grasps the meanings of those symbols.
---
Quoting frank
The answer here is, 'No, that's not what Russell was saying at all, whether we take your "proposition" in Russell's sense or Frege's sense.'
This thread has taken plenty of care in avoiding ambiguous language like "proposition," and this is because the language of the thread is in no way controlled by Frege's usage. It is controlled by Kimhi's usage, the publicly available sources, and common usage.
I think there are two approaches to the OP, and maybe in philosophy in general:
1. You can start with ontological biases and let those views form the limits of investigation.
2. You can start by trying to map out where you are, and let the borders remain foggy.
Both approaches have virtues. What's at stake with the concept of propositions is the communing part of communication. It's all about agreement. If we ever really do arrive at agreement, then we would say we're thinking the same thoughts. That's what a proposition is supposed to be: that thing we can agree or disagree on.
If you start with a strongly materialistic bias, you're likely to lean toward behaviorism, which says that we never really agree on anything. All agreement is really just a certain kind of behavior. If we follow this approach, we're never even going to arrive at the OP, because it's about thinking.
Where, historically, would you say that essential connection gets dissolved or weakened?
Quoting Pierre-Normand
Well, I think this avoids the force of my point a bit. Frege said, "A proposition may be thought..." He did not say, "A thought may be thought..." There are apparently good reasons why he didn't use the latter formulation, and they point a difference between a proposition and a thought. Specialized senses can "solve" this, I suppose, at least up to a point. (Nor am I convinced that IEP is using 'proposition' in a non-Fregian way, but I don't want to get bogged down in this.)
In the original German text, Frege wrote: "Man nehme nicht die Beschreibung, wie eine Vorstellung entsteht, für eine Definition und nicht die Angabe der seelischen und leiblichen Bedingungen dafür, dass uns ein Satz zum Bewusstsein kommt, für einen Beweis und verwechsele das Gedachtwerden eines Satzes nicht mit seiner Wahrheit !"
In Austin's translation, "may be thought" corresponds to "das Gedachtwerden", which literally means "the being thought" or "the being conceived." Frege is referring to the act of a proposition or thought being grasped or entertained by someone. "Satz" can be either used to refer to the syntactical representation of a thought (or of a proposition) or to its content (what is being thought, or what proposition is entertained).
If we attend to this distinction between the two senses of "Satz" Frege elsewhere insists on, and translate one as "declarative sentence" and the other one as "the thought", then, on the correct reading of the German text, I surmise, a literal translation might indeed be "A thought may be thought, and again it may be true; let us never confuse the two things." and not "A declarative sentence may be thought...". The latter, if it made sense at all, would need to be read as the elliptical expression of "(The content of thought expressed by) a declarative sentence may be thought," maybe.
In other words, Frege's text is making a distinction between the Gedanke (thought or proposition) being entertained and its being true, rather than focusing on the sentence (Satz) itself as the object of thought. (And then, the thought being judged to be true, or its being asserted, is yet another thing, closer to the main focus of this thread, of course.)
This intended reading, I think, preserves the philosophical distinction Frege is drawing in this passage between the mental act of thinking (grasping the thought) and the truth of the thought itself. Translating "Satz" in this context as "declarative sentence" would blur that important distinction, since Frege is interested in the thought content (Gedanke) rather than the linguistic expression of it (Satz). And, unfortunately, the English word "proposition" carries the same ambiguity that the the German word "Satz" does.
On edit: Regarding your earlier question, one clear target Frege had in mind was the psychologism he had ascribed to Husserl, which threatened to eliminate the normative character of logic and another possible target might be formalism in the philosophy of mathematics that turns logical norms into arbitrary syntactic conventions.
On edit again: "The locus classicus of game formalism is not a defence of the position by a convinced advocate but an attempted demolition job by a great philosopher, Gottlob Frege, on the work of real mathematicians, including H. E. Heine and Johannes Thomae, (Frege (1903) Grundgesetze Der Arithmetik, Volume II)." This is the first sentence in the introduction of the SEP article on formalism in the philosophy of mathematics.
Would you say an AI can assert a proposition? Or are we just treating it as if it can?
The notion of force being used in this thread is nothing to do with changing the motion of objects. I suspect this is misleading us.
Illocutionary "force" is not something that inheres in sentences, but what people do with sentences. Denoting is not something that inheres in names, but what people do with names. This performative aspect of language is hidden by talk of sentences having force.
Quoting J
Well, it seems that when the notion of "force" is clarified, it doesn't do what Kimhi wants. He's reliant on ambiguity. But further, he seems not to consider the developments of logic and metalogic since Frege - and they are profound.
Quoting J
There's an old adage concerning someone complaining about geneticists studying fruit fly when elephants were so much more important. But you can get more fruit fly into a laboratory, and they breed faster, so it makes sense to work with them. What is learned can then be appleid to elephants, if needed. Fruit fly simplify the process so that certain aspects can be examined in detail. Formal logic does much the same thing, but with language. It models certain aspects in a way that can be examined productively. If Kimhi wants to understand elephants, he could do worse than to start with fruit fly.
It is also a mistake to think that what Frege has to say is anything like the present state of play of formal logic. His discussion of truth is a case in point, his argument having been superseded by several generations of subsequent work.
And the discussion in this thread of modus ponens was just plain muddled.
It's hard to be sure, but there seems to be a profound misapprehension concerning what logic is, underpinning the Kimhi's work and much of the writing on this thread. I'm not inspired to go down that path.
While this issue isn't entirely off topic, and hence would be worth discussing, it also is liable to send us off into tangential directions regarding the specific nature of current LLM-based AI agents, the issue of their autonomy (or lack thereof), their lack of embodiment (and the issue of the empirical grounding of their symbols), how they are being individuated (as machines, algorithms or virtual agents in specific conversation instances), to what extend their assertions have deontic statuses (in the form of commitments and entitlements to claims), and so on. Hence, that might be a topic for another thread even though links could be drawn to the topic being discussed here. (I've already explored some of those issues, and connected them to some ideas of Robert Brandom and Sebastian Rödl, in my conversations with GPT-4 and with Claude, and reported on them in my two AI threads).
I'm not seeing that as tangential. I think it would highlight, especially for the naive, like me, the difference between a formal language where apparently there are propositions that aren't thought of as asserted in any way, and ordinary language, where the listener always thinks of what's being asserted in the light of who asserts it, or in what setting it's asserted. But I'll go with your judgment.
"But now one can ask: in virtue of what is the forceless combination Pa associated with the truth-making relation that a falls under the extension of P, and thus with the claim Pa, rather than with the truth-making relation that a does not fall under P (or falls under the extension of ~P), and thus with the opposite claim ~Pa? This question cannot be answered, since Pa does not display an assertion, and therefore there is nothing that associates it with the positive rather than the negative judgment. The association of the proposition Pa, conceived as forceless, with one of these conditions as its truth-making relation, understood in terms of the object the True rather than the other, smuggles assertoric force back into the predicative composition Paforce which Frege denies is there."
I need to give much more thought to this before I can comment intelligently but, for now, I just want to point out that the great gangsta philosopher Ali G already had raised this issue decades ago in a conversation with then INS Commissioner James Ziglar.
"Ain't the problem though that 99% of dogs can't speak English so how does they let you know who is carrying a bomb ..."
"How does you know they ain't pointing to say this one definitely ain't got a bomb in it."
Maybe I misunderstand you but I don't see the distinction between a thought being merely entertained (or grasped) and it being asserted to line up with the distinction between (merely) formal and natural languages. Furthermore, I view conversational AI agents as users (to the little extent that they are) of natural language even though the underlying algorithm processes "symbols" blindly and manipulates them without regard to their semantic content. Ascriptions of semantic content to the responses of LLM-based AI agents, and interpreting them as having assertoric force, is a matter of taking a high-level intentional stance on their linguistic behavior with a view of rationalizing it.
Quoting Pierre-Normand
I think that when you entertain a thought, you're imagining it as an assertion, even if there was no such event. For instance, if you contemplate "the cat is on the mat", in terms of thought, all you have is a sentence that could mean all sorts of things. It's not truth-apt. To the extent that meaning is truth conditions, it's meaningless. Am I wrong?
Quoting Pierre-Normand
And I think that's what we do all the time when we communicate. We rationalize. I don't think you can really see any meaning in the output of an AI unless you take it as having assertoric force. It's a reflexive part of communication.
No, I agree with you. I also tend to view the pragmatic role of assertion to be paradigmatic and central in understanding what propositions (or thoughts) are. But I haven't yet engaged closely enough with Kimhi's text (and with most contributions in this thread) to properly assess his challenge to Frege.
I agree. It relates to Davidson's constitutive ideal of rationality (which grounds language interpretation) and it also relates closely to Frege's context principle. If thoughts were merely entertained but never asserted (or denied) then they would lack content since there would be no rational ground for interpreting them one way or another.
Cool, thanks!
First of all, thanks for your helpful response.
Quoting Banno
The common misunderstanding of logic is why Im asking you to stay involved in this thread. This website is a type of public school for enthusiastic amateurs who need teachers. High aptitude for formal logic is rare, and therefore you can do much good by sharing some fruits of your gift.
Oftentimes it appears as if the nose-bleed section isnt listening to the dugout, but they are.
I would assume it does, until something stops it. Just by recognising it as a sentence in a language, you allow it to assert itself: to replicate, and produce corollaries.
The question is, do you want to allow it to proliferate unchecked into this or that discourse? Or will you, within such a discourse, impose restrictions on the sentence's self-assertion, and ensure that it appears in public only, if at all, suitably contextualised, and qualified.
Perhaps, most harshly, wearing a negation sign - thereby qualified as untrue.
Or neutered. Contextualised as the disjunction of its assertion and denial (Pa v ~Pa).
Or conditionalised, or hypothesised, or probabilised.
Or chaperoned, by speakers: asserters, who would like to assist, and deniers, who oppose proliferation of the naked sentence.
Speakers on opposite sides might resort to all sorts of (more or less democratic) means to exert influence.
If they resort to logic, though, they must allow full rights of self-assertion to the premises, and then withdraw to watch the game. Which is played out by the self-asserting sentences, unassisted.
(And I see that some of your subsequent posts pick up this theme of how technical Gedanke is.)
Both IEP and Roberts refer to this Gedanke sense, but neither give a specific reference in Frege. From the context, I'm guessing it's to be found in On Sense and Reference. I don't have time today to hunt it down but maybe someone else can.
I like the clarity of this, but doesn't it beg the question? The "other side," so to speak, would say, "A proposition is supposed to be a thing with a truth-value, something we don't merely agree or disagree on, but claim objective reasons for doing so."
Yes. You've just said what I said, above, but you said it better. I should have read this more carefully before posting -- the point has been well made.
I wouldn't sell him short. "Reliant on ambiguity" implies that he's trying to get away with something, but I think it's rather the case that he's not a very skillful writer and doesn't always realize how murky things are getting.
Your second point seems true, though. Kimhi targets Frege as if he had published the Beg. last year. He doesn't refer to many sources that are contemporary, except concerning Aristotle.
I didn't mean to say that propositions are limited to the things we agree or disagree on. We imagine there are true propositions that no one knows, for instance, the answer to whether there is life on other planets.
I was trying to show what's at stake if we decide that there are no propositions in the Fregean sense of the word. We'll have to give up the notion of agreement as we commonly understand it. I was thinking about this because I was quoting Soames and the first chapter of his book on truth explains why we can't use utterances or sentences as the basis of agreement. It has to be propositions, or the content of an uttered sentence. With regard to whether there's life on other planets, notice how we "smuggle in" an assertion as Kimhe puts it.
Quoting Banno
Could you say more about this? Perhaps the target statement ought to be this, from T&B:
I take this passage to be central to what Kimhi wants to say in the book. If you can lay out problems with it, I'd find that helpful.
Quoting Banno
It is hard to be sure. The other possibility is that it's a profound contribution to our understanding of what logic is (T&B, that is, not necessarily this thread!). But of course you're right to be skeptical and to demand clear arguments. As someone else posted above, I hope you can stay with us and at least view the path from drone height, even if you don't want to go down it.
Yes, very good. That said, I believe there is still a larger issue about the basis of agreement -- broadly pragmatic and communication-oriented, or claiming some version of objectivity? But that's a deep rabbit-hole, and as long as you're not saying that agreement is only consensual, then we're on the same page.
I'm happy exploring behaviorism and pondering whether there really is any such thing as agreement, but my home base is to imagine that I agree with billions of people I've never met on a mass of propositions, many of which I've never brought to mind consciously. :smile:
Quoting Banno
Quoting Banno
Im not thoroughly convinced your first quote (underlined) is consistent with your second quote. Your first quote, if it be authoritative, suggests a very considerable depth of experience.
Lest you be further embarrassed by what you think flattery, perhaps you can help me understand something for me basic:
Quoting J
Quoting Roberts
Quoting ucarr
In the J quote and the Roberts quote above, they seem to be establishing an interpretation of predicate logic that boils down to a triad of zeroes. That takes us to the primordial question: How existence? Well, science asks for one gimme: something spontaneously arising from nothing. After we have something, well figure out the rest, says science.
Are Frege, Kimhi, Roberts, J, et al really sourcing predicate logic back to the supernatural gimme? Im not inclined to think so, but thats how I read them as quoted here.
Im asking you to give me some tips on understanding how my reading of the quotes is fundamentally wrong.
Is it my imagination, or is Frege sounding a bit defensive here? He seems to recognize the shortcomings of his approach -- the awkwardness, the departure from ordinary language. His project, as we know, is to improve or even abandon ordinary language in the interest of clarifying logic's objective structure. So here, he's trying to confine himself to saying it's a predicament about language, not thought, and he's also saying that he's entitled to make his own stipulations about how to use terms.
My contention is that he can't confine himself to a "language predicament," because his predicate logic is claiming to do so much more than reform language. The individual-term question is merely an obvious starting-place for such a critique. And while he's entitled to withhold his agreement from Kerry or anyone else, his stipulations are also not in accord with many of our most useful common modes of expression, and in such a case, I don't think consistency is enough. Put another way: This is a high price to pay for formalism, especially when it claims to control something as basic as what can be said to exist.
(And just to pay Frege the respect he deserves, I agree with @Banno's fruit-fly analogy. There is a great deal to be learned about thought from Frege's intricate constructions, regardless of whether some of his metalogical premises might be questionable.)
For this thread, it is absolutely central, this claim of conflation.
You can consider a physical object as having properties such as mass, velocity relative to a frame of reference, and so on. The mass of an object, for instance, can be treated as an abstract object, but hylomorphism comes naturally here, and almost no one is tempted to say that the mass of the object has some existence separate from it. Nor does its velocity or any other property.
Now consider things people say to each other. You might very well find reason to distinguish what someone says from how they say it, or what someone says from the importance they attach to it, and so on. You might distinguish what someone says from the specific words they used to say it, including which language they used, so that people speaking English and German can say "the same thing".
"What he said" looks a lot like an abstract object, along the lines of mass, but for some reason many people, perhaps including Frege, have been tempted to treat "what he said" as having an existence independent of the words he used or the sounds he made.
For the issue Kimhi wants to raise, the issue would be whether you are conflating two different objects (or kinds of objects) that have independent existence, or whether Geach and Frege have conflated two different 'descriptions', I suppose we could say, two different 'qua ... ' formulations.
Does it matter what's being conflated?
I think it might for Kimhi's argument because one way of buttressing the idea that propositions have independent existence is to align them with the mental, rather than the physical. There's more, of course, but here, I think clearly, the question is in what sense "what he said" is a thought, while the actual words spoken were merely a physical "expression" or even representation of that thought.
If we take a more hylomorphic view, there may still be an argument, but it won't be this one.
Abstract objects are things like numbers, sets, and propositions. Mass is a physical property.
Quoting frank
What role does the observer play in the construction of an abstract object? To clarify what Im asking, consider this related question: Can/does an abstract object exist without an observer who perceives natural things and then constructs a composite abstraction based upon repeated viewings of similar things?
I'd have to go with Schopenhauer and say that subject and object are two sides of the same coin.
These two objects have the same mass.
These two cartons have the same number of eggs.
These two sentences mean the same thing.
You may remember that Frege wrote Thought: A Logical Enquiry, ("Der Gedanke. Eine logische Untersuchung") where he famously argued for a kind of Platonism about thoughts/propositions, and suggested that they inhabit a third realm separate from both material objects and (subjective) mental phenomena. It is worth noting, though, that he published this in 1918, much later than On Sense and Reference (1892), or The Foundations of Arithmetic (1884).
Whatever one may think of Kimhi's (or Rödl's) beef with Frege regarding the propositional unity of "forcefully" entertained propositional content, their ontological thinking is certainly less naïve than Frege's. What still remains an open question to me (even though I lean towards the Wittgensteinian quietism of McDowell) is whether their accounts of this self-conscious propositional unity constitutes an improvement over the charitable accounts, put forth by Evans and McDowell, of what Frege was trying to accomplish when he sought to individuate thought/proposition at the level of sense (Sinn) rather than at the level of extensional reference (Bedeutung) in order to account both for the rationality of the thinking subject and for the objective purport of their thoughts. See McDowell's Evan's Frege (cited and quoted by Kimhi) as well as On Redrawing the Force Content Distinction, by Christian Martin, and Wittgensteins Critique of the Additive Conception of Language by James Conant. (Both Martin and Conant have engaged deeply with Kimhi and have credited him for fruitful discussions.)
I can say we agree, and I can say what we agree on, without attributing to "what we agree on" independent existence, but instead treating it hylomorphically as an abstract object that is immanent within our agreement. "Our agreement" is another such abstraction. Does it exist independently of our agreeing?
Quoting frank
Quoting frank
Do we see from the above that mass and abstraction, like form and content*, are interwoven?
*The interweave of form and content entails higher-order perception: the perceivers perception of the perceivers perceptivity.
I was also thinking of a rejoinder along those lines. Certainly, for some purposes, there is a point in sorting numerical quantity alongside weight as a (predicative) way to express amounts of grocery items one needs to buy and therefore view them both as the same sorts of abstract objects. But there is also a principled and characteristically Fregean way to set them apart. Numbers can be viewed as second-order functors that stand in need of (first-order) predicative expressions rather than singular terms to saturate them and form complete propositional contents. On that view, the thought that there are twelve eggs in the carton can be logically analysed as the thought that, qua eggs, the objects in the carton are 12. You can't ask how many items there are in a room or refrigerator without specifying (or tacitly assuming) what kinds of object it is that you are talking about, and how they are meant to be individuated. If quantity is a "property" of something, it isn't a property of an object (such as a carton of eggs) but rather a "property" of the predicate "_is an egg" as it figures in the proposition "there are 12 x's in the carton that are such that x is an egg", for instance. By contrast, the thought that there is one kilogram worth of eggs in the carton predicates the same weight regardless of the manner in which individual eggs are individuated. This logical feature of the concept of a number (it's being analysable as the referent of a second-order functor in sentences expressing how many objects of a specific kind there are in some domain) makes them "logical" or "abstract" in a way more simple predicates such as weight are not.
On edit: There is an argument to be made, though, that weight being a concept which, like mass, belongs to a quantitative science (or quantitative way of thinking about things and comparing definite chunks of them one kilogram worth of eggs being such a chunk, for instance) also is inseparable from the (second-order) concept of a number unlike more concretely qualitative concepts such a the concept of a color.
I hope I didn't suggest that there's only one type of abstract object. Quite the contrary. Mathematics alone provides a considerable menagerie.
For purposes of this thread, the ones that would matter would be, at least, content and force.
There is a suggestion, speaking roughly and quite broadly, that a system of logic intended to deal with our utterances only as content, without force, is somehow mistaken. That may be so, but it's no argument to say that our utterances also have force if the whole point of the enterprise is to set force aside without denying it.
It might be closer to the argument given to say that Frege, in particular, does not set aside force (even if other and later logicians do) but that he brings it in in a way that is somehow at odds with the unity of force and content in our utterances. That might be a claim that it is a fool's errand to distinguish force and content (somewhat as Quine argued the impossibility of separating the analytic and synthetic 'components' of a sentence), or it might be a claim that Frege has distinguished them incorrectly, or something else, I don't know.
I've not spent as much time as I might have thinking about Kimhi's argument, but the claim of conflation suggests that there is a point you can make about content, the proposition, and a different point you can make about actual occurrences, in which that content features, but Frege, I think it is claimed, forgets what he's about and tries to make a single point about both, or tries to make a point about one that can only be made about the other, and somehow tricks himself into thinking he has not mixed up the two.
That's the terrain of the argument I'm unable quite to present, I think.
Maybe we could pursue this in a different thread. It's sort of along the lines of Plato. I'll start one if you're interested.
I think abstract objects are products of analysis. We dismantle mind and language use as if we're taking a cuckoo clock apart. We may become so engrossed in the pieces laid out in a table that we forget that.
As long as you're tuned into the fact that in this framework, propositions are content, not sentences, you're good to go.
Yes, but I would suggest that we shouldn't take the word "analysis" there to indicate a practice that stands outside the everyday use of language, as if this is only something done by a linguist examining a corpus or a philosopher examining whatever she does, arguments, intuitions and whatnot.
Instead, this kind of analysis is engaged in every day by ordinary speakers and listeners; making distinctions like what-you-said vs how-you-said-it are strategies we all use, sometimes to understand each other and sometimes for other reasons. Doing this kind of thing is as much part of being a member of a linguistic community as knowing the word for "window" or the polite use of pronouns.
I agree. I think Frege would too.
In his paper On Redrawing the Force Content Distinction, Christian Martin suggests (and purports to illustrate) that the root of the difficulty is that philosophers tend to universalise the ground of the content/force distinction, or to seek a single account that explains this distinction in all cases (e.g. negation, conjunction, the antecedent of a conditional assertion, fiction, etc.) whereas, according to him, the distinctions made in all of those cases, while proper, only have a family resemblance and must each be sensitive to the features of the specific language game in which they are being deployed. So, while it can make sense to single out the special force of assertion with the judgement stroke, it should no be assumed that the judgement stroke exemplifies a univocal concept (force) that is the same in all cases where one wants to separate force from content in the logical analysis of a thought. Consequently (or so Martin seems to argue), it may be the unwarranted attempt to providing a unified account of force that breaks the unity that force and content have in specific cases where the distinction should rather be drawn in a contextually sensitive way. I am only halfway in my reading of his paper, though, and I may paraphrase Martin's argument differently when I will understand it better, as well as the specific analysis of negation that he provides. (He provides the analysis of other logical connectives in a book that is currently untranslated from the German.)
That sounds very promising.
This is definitely a tangent, but I was just thinking of a puzzle that can arise with properties -- it's close to the distinction between in sensu diviso and in sensu composito, or maybe it's just the order of quantifiers, I'm not sure really. Suppose you have a bunch of marbles, some red and some blue, and you are asked to "list the colors of these marbles." There are two good answers: {red, blue} and {red, blue, red, red, blue, red,...} What is wanted? "Of each color, that it is represented"? Or "Of each marble, its color"?
I thought of this because if instead you were told to sort the marbles by color, there's no ambiguity -- well, not this particular ambiguity. Someone might distinguish the reds and blues more finely, but then we'd be back at the first ambiguity, which is really along a different axis, right?
I wouldn't even throw this little puzzle out there if it weren't for what Kimhi says about propositions versus actual occurrences. The options you get dealing with marbles are different from the options you get dealing with the colors of marbles.
I don't it's a case of ambiguity. You just don't have enough information to know what's being asked. You'd have to go back and get the request clarified, right?
It seems to me rather that abstract objects as artefacts of generalization are products of recognition and synthesis.
Please write the OP and Ill join the conversation.
Because it's ambiguous. I'm struggling here to guess how you understand that word.
But communication failure is not the main point here; it's that you have the option to treat shared abstract properties as singletons, but you do not have that option with the objects instantiating them.
Sorry, wasn't trying to be dense. You mean the marbles are identified separately, but the colors, being universals, can merge?
Yeah there you go.
The relevant part in Kimhi seems to be this (p. 39)
"In what follows, I shall call the correct understanding of Freges observation Wittgensteins point, and I shall call the conclusion Geach and Frege draw from itthat assertoric force must be dissociated from a propositions semantical significanceFreges point. We shall see that Freges point is mistaken. It only seems necessary if we accept certain functionalist (and more generally, compositionalist) assumptions about logical complexity. Correctly understood as Wittgensteins point, Freges observation concerns actual occurrences of a proposition and amounts to the full context principle; misunderstood as Freges point it runs together the symbolic and actual occurrences of a proposition and limits the context principle to atomic propositions."
My rough intuition about this, at this stage, is that the full context principle assigns meanings (Fregean senses) to subsentential expressions (e.g. names predicates and logical connectives) not only in the context of whole sentences but also in the context the other sentences a sentence relates to in a language game. (And this is not exhausted merely by inferential relations). This is the point about actual occurrences of propositions since, unlike propositions considered in abstracta (with regards only to linguistic form), actual occurrences always make moves in language games (be they games that we play with ourselves). Negating a proposition is one such language game, which Martin analyses in great details, and asserting it is another. It is tempting here to assume that there ought to be a common content that is being either asserted or (assertively) denied, since you may be asserting something and I am denying it. (It must be the content, and asserting it or denying it are the extraneous forces). Martin denies this, I think, but I must read him further to understand how contents are differently understood or differently individuated within different language games that warrant different ways to mark the content/force distinction (while my asserting that p is the case still logically bears on your denying "it").
Here are a few further thought regarding the Wittgensteinian full context principle and the distinct ways in which propositional contents (Fregean thoughts) are being individuated in assertion or negation.
Consider the issue that I raised at the end of my previous post: '...while my asserting that p is the case still logically bears on your denying "it" ' In order for your denial to logically bear on my assertion, the game of making assertions must bear on the game of denying asserted contents. But, surely, denying a claim made by someone else isn't equivalent to denying a claim made by oneself, which it at worst irrational and a best could be construed as a retraction. So, maybe we can say that although asserting p and denying p individuate the thought content p (as distinguished by the common linguistic form "Satz" p) differently, that is not a problem for rational engagement since the issue precisely is that there is a rational dispute regarding which move should be made (in light of evidence, etc.) in the language game with this linguistic form, and hence a dispute regarding the proper way to individuate the content of the claim (to be either asserted or denied).
Someone might still puzzle over my seemingly gratuitous assertion (which I tentatively ascribe to Martin) that, specifically, the content p, when asserted, isn't the same as the content p, when denied (i.e. when its negation is asserted). And that isn't reducible to a mere distinction in force, although it can be explained, non-reductively, as such a distinction. But indicating the force amounts to gesturing to a specific sort of language game. The letter p that is common to both therefore merely signifies the common linguistic form. Why not say that there is a common purported content (how things are, state of affairs) that is here denied and there asserted? Consider the content of the assertion "this apple is red" or "p". When one asserts that, what one thinks is that the apple is red. When you use the same linguistic form to deny that the apple is red, one says "it is not the case that this apple is red" or "not p", this can not be construed as you standing in the different relations (with the "force" of negation, say) to the same state of affairs consisting in the apple being red since, from your point of view, there is no such state of affairs in the world. So, it is necessary for you to characterise the content of your denial i.e. what it is that you deny differently. This appears to be related to the issue of object dependent de re senses where I say that this apple is red (while I purport to refer to it demonstratively) but there is no apple owing to some optical illusion. In that case, Evans or McDowell would say that the thought content one might express in other circumstance with p (when there is an apple in sight) simply isn't available to be thought, in this case.
Maybe what might further help dissolve the puzzle (or the counter-intuitiveness) in the claim that when you assert that there is an apple on the table and I deny it there isn't a common content of thought that you assert and that I deny would be to place this activity within a more fully specified embodied linguistic game of finding apples in an environment where illusions occasionally occur (or apples move around) such that our capacities to deictically refer to them, and remember where they are, are fallible. In the context of such a game, asserting that there is an apple on this or that table is the actualization of a capacity to locate apples in point of communicating to other where a particular apple is (and hence transmitting the content of a de re sense). Denying that there is an apple on the table is a move in the very same language game that aims at signifying that someone's general capacity to locate an apple on the table (de dicto) has failed to be actualized properly, owing to the occurrence of an illusion or owing to the apple having unexpectedly moved away since it had last been looked at. Within this context, it seems much more apparent how claims and denials about the same linguistic contents actually bear on distinct propositional contents (distinct Fregean thoughts) since the successfully (true) asserted contents are de re while the successfully denied (false) contents are de dicto.
I have mixed feelings.
Yes, this is the natural way to go, but I think there's a risk that it flattens communication too much. We need different levels to play off against each other, unless you intend words to drag other language-games along with them to provide the necessary contrast. (Which, okay, and I know LW talked that way sometimes, but there are several issues with that.)
The examples I have in mind are irony, sarcasm, exaggeration, implicature (and we could go on) -- none of these are at all intelligible without something that counts, even if temporarily, as the literal meaning to play off of. That could just be some "other" meaning, but it has to be something widely enough available to count as "literal" for the relevant speech community.
So I lean toward what I take to be Grice's approach: logic is all we need for the semantic connections between sentences; pragmatics can't even get started unless that analysis stands as it is. For instance, to trigger the recognition of implicature, a response has to violate the principle of cooperation if taken literally. If you assign as meaning the use being made of the sentence (the speaker's meaning rather than the sentence meaning), you undermine the whole process. What's more, the sentence used to trigger the recognition of implicature (or irony, exaggeration, etc.) has to have a particular literal meaning for it to be suitable for the job in the first place, and thus selected and uttered. (Obligatory chess analogy: being used to block check doesn't change what a piece is, only its role in this position in this game.)
Quoting Pierre-Normand
Indeed.
It seems like I'm very nearly giving content to logic and force to pragmatics, and I'm not sure that's a terrible first thought, but I'd be interested in alternatives.
And nothing I've said does much to ground or explain the content/force distinction ...
---- I'll try to catch up so we're not having two conversations, but I'm going to hold off on your post just after this one for a bit.
:up:
(my bolding)
I can't provide an adequate response to this, with appropriate citations and such, but I can say this: I am deeply, deeply suspicious of the model suggested here. It's the alternating monologues model of conversation, where the speaker simply expresses their thought out loud within earshot of an audience; language exists to mediate the connection of my mind to the world, and my audience more or less eavesdrops on my review of that relation.
I'm not going to deny the sentence I bolded, but I think this is entirely backwards. It's the other person who mediates my connection to the world, and I hers, and language is an important part of how we connect to each other, for that purpose.
Force, in particular, if we can define such a thing adequately, is meaningless absent an audience. I'm not denying that we internalize this dynamic; we very much do. But the origins of assertion, question, command, and so on, clearly --- to me, at least --- lie in our relations with others. We can play at making assertions to ourselves, asking ourselves questions, giving ourselves orders, but nothing could be more plainly derivative of what we do with others, and it is necessarily a make-believe sort of business.
(Oh, you could, if you wanted, cobble together some sense of force appropriate to our dealings with the non-minded world --- putting nature to the question, imposing your will on her, blah blah blah --- but I don't have any idea why anyone would speak a language for that purpose, since nature isn't listening.)
This doesn't directly address the scenario you described, much less provide an alternative analysis, but the starting point strikes me as completely hopeless.
I wonder if the impetus for separating content from assertoric force is related to the 'view from nowhere.'
It's language that's detached from any particular human. It's like the narrator of the novel we inhabit.
I was rather arguing for something that is very much the polar opposite of that view. I alluded in passing to the case where we assert something to ourselves (as in making a judgement in the course of practical deliberation) as just a special case, or personal use, that we can make of the resources of a language game that is essentially public. In alluding to this, I wanted to highlight that even in this kind of personal use that we make of moves of asserting and denying that are at home in paradigmatically public, embodied and interpersonal language games the propositional contents (Fregean senses) or our asserting, or judging that p, or of judging that p isn't the case (i.e. that not-p is the case) also mark out distinct contents despite both of them being linguistically expressed as "p". Showing this was the point of my elaboration of the public game we might play with apples in my last paragraph, where the aim of the game of asserting and denying is to coordinate our joint engagements with the apples, and internal monologues or private representations drop our of the picture entirely.
It may indeed be indirectly related to the view from nowhere. When arguing against representationalism, or the idea that our thoughts or the propositional contents of our utterances consist in a private inner realm that is problematically communicated to other or problematically grounded in the "external" world, John McDowell speaks of the "sideways-on view that places empirical reality beyond the space of concepts". Once we conceive of being, or of things as they are in themselves, as residing outside of the space of concepts, we indeed are conceiving of them as viewed from nowhere.
Which is what I had expected! Obviously I must have misread you.
I suppose we can leave it there for now, though I'll certainly go back through your posts.
Several posts back it felt like we were finally dealing with the central issue of this thread, so I would feel bad if we lost sight of that.
Quoting Pierre-Normand
Well put. What you're calling the charitable accounts do seem to capture what Frege wanted to do, and why (especially the desire to explain the objectivity of thoughts), but I'll have to read more of McDowell.
Quoting Pierre-Normand
I think Kimhi would accept this as a paraphrase of his thought. If we want to continue to speak Kimhian, we could replace "in a language game" with "in an actual occurrence of p."
:up:
Yes, and Kimhi wants to do neither. Hes after a unity of thinking and being. And no, I still haven't completely grasped how he gets there.
Quoting Srap Tasmaner
To that I would add a third discrimination: thought in the Fregean sense of proposition or propositional content. So we have:
- Thought as a mental event. Mine is not yours, etc.
- Thought as the content of that mental event this is the Fregean sense. Here, my thought is the same as yours, or can be.
- The language in which thought-as-content may be expressed. This is important because we need to leave room for synonymy between languages.
I often find it helpful to invoke Karl Poppers Three Worlds idea in this sort of discussion. Poppers World 1 is the physical world, the world which would exist, in a rough-and-ready way, without any consciousnesses. World 2 is the mental world, understood strictly as mental events, or brain events. Each occurs at a Time T-1, -2, etc. and is unique in the sense that no one can have the exact same event. World 3 is the world of our mental constructions, our ideas, propositions, theories, poems. As I said above, its basically the content of thoughts its what the World 2 events are about.
Quoting Srap Tasmaner
I read Kimhi to be saying that both the symbolic and actual occurrences of p are World 3 objects they are contents of thought, one unasserted, one asserted but the actual occurrences cant be understood if we strip away any connection with assertoric force/truth value and try to treat them as if they were synonymous with symbolic occurrences.
That makes sense. I read this in the SEP article on Lotze (he lived from 1817 to 1881):
"The new model of the academic researcher demands the replacement of prominent personalitiesi.e., romantic geniusesby the new exemplar of the sober scientist."
Lotze navigated a transition from German idealism to a philosophy that focuses on values and analysis. Maybe we could say the whole western culture was shifting toward an emphasis on quiet objectivity rather than an emotional idealistic view. Frege was a part of that?
We live on the other side of the 20th Century, so we know what kind of terrain that shift was headed toward: eliminative materialism, functionalism, inscrutability of reference. Complaining about the view from nowhere seems to target something that's foundational for us: scientific objectivity.
Fair enough. I misspoke, since what I have at hand is not Kimhi's book but the reports of his book found hereabouts. The ambiguity may not be his. Similarly it's the discussion of PM on this thread that I found problematic, not the account given by Kimhi. I'm not sure what to make of the paragraph you quote, in particular the conclusion: " Therefore, Geach's understanding of Frege's observation conflates the two senses of propositional occurrence: symbolic and actual." Not at all sure what "symbolic and actual" is doing here.
If I were to comment it would be to point out the benefit of treating Modus Ponens as a rule of inference. We might do well to avoid trying to work out what an "actual argument of the form modus ponens" might be, apart from one that makes use of the rule of inference.
It's common for those versed in axiomatic or ealry logics to think in terms of "Laws Of Thought", such as Modus Ponens. It's worth seeing what "Modus Ponens" looks like in the Open Logic text. There's the rule of "? elimination" for Natural Deduction,
This is understand as that if in a natural deduction you can write "?" and you can write "???" then this rule entitles writing "?". and
Quoting Open Logic, p.180
or the subsequent Deduction Theorem: ? ?{?}?? if and only if ? ?? ??. The first of these is about what can be written in ?, the second about what happens when ? is extended. In the sequent calculus, Modus Ponens is derived. Cut provides a generalisation of Modus Ponens, but the cut elimination theorem displaces it from any centrality. Modus Ponens is not any one expression, and is not always fundamental.
It's worth asking what sort of thing a "Law of thought" might be. Presumably a Law of thought must be such that it hold true in all cases. If there are such entities, then there is "one true logic", that which uses these Laws. Recent work has questioned this, asking why there could not be a variety of correct logics. And some investigation of the view that there might be no correct logics. Don't be too quick to reject logical pluralism. Given any system of rules, it is a simple question of imagination to set out what things would be like if those rules are contradicted.
But if logical pluralism is even a possibility, then the idea of "Laws of Thought" would be undermined, and with it, perhaps the psychologism that Kimhi would reintroduce into logic.
To this mix we might add more general questions about following rules. Language does not only function by observing convention, but also by rejecting convention, by hitting the nail right on the thumb, putting the cart before the hearse, or bringing your chickens home to roast.
In this regard it seems to me that Frege, Kimhi and others have a view of philosophy as seeking a closed, consistent and complete account of how things are. We know from other considerations that we can easily achieve completeness usually at the expense of coherence. I'll opt for coherence over completeness.
While I'm rabbiting on, it's worth taking a bit more. care with notions of objectivity. Einstein's great contribution wasn't to set out a view from nowhere, but to give an account that worked anywhere. He recast the Laws of physics so that they worked for anyone, regardless of their frame of reference. Objectivity is about finding explanations that work from multiple points of view; about having explanations that work regardless of where one stands, and so for the many rather than for the one. it's not about the view from nowhere, but about the view from anywhere.
Added: Frege's contribution was in this direction. By setting the assertive force aside he permitted wider agreement. Some might disagree that p is the case, while agreeing that if p were the case, q would follow. Logic allows us to examine the consequences of our options without commitment. Who was it said " "It is the mark of an educated mind to be able to entertain a thought without accepting it"?
This is commonly (miss-)attributed to Aristotle who was making a different point in Nicomachean Ethics, Book I, Chapter 3. "In the same spirit, therefore, should each type of statement be received; for it is the mark of an educated man to look for precision in each class of things just so far as the nature of the subject admits; it is evidently equally foolish to accept probable reasoning from a mathematician and to demand from a rhetorician demonstrative proofs." (Ross translation)
However, I can't fail to notice the resemblance of Aristotle's idea here bears to the "full context principle" Kimhi attributes to Wittgenstein (as interpreted by Martin)!
Quoting Pierre-Normand
Should we picture the meaning of a sentence as something we approach only asymptotically, as our comprehension of the context improves?
Suppose we go along with Frege and think of thoughts (propositions) as objective, in his sense, not the personal property of anyone.
What about judgment? What about inference?
If I judge P true, and so do you, aren't we making something we'd want to call "the same judgment"?
If I infer Q from P, and so do you, aren't we making something we'd want to call "the same inference"?
We can go further.
Suppose I forget to "carry the 1" in a piece of simple arithmetic, and so do you. Aren't we making "the same mistake"?
How far can this analogy go? Couldn't we have the same taste in music? The same fear of snakes?
Or is there some reason all of these things aren't just as objective as Frege's propositions?
If we make the same judgment, we agree on the same proposition. We aren't agreeing on a sentence or an utterance. Would you like to work through the argument that establishes that?
That post reads like I addressed @J as a defender of Frege, but it was meant to be addressed to @J as someone who believes Kimhi is making a point about Frege, but it keeps coming out as just the sort of thing we'd expect Frege to say.
[quote=Blake, not Frege or Kimhi]The truth cannot be told in such a way as to be understood and not be believed.[/quote]
As the quote from Aristotle's Nicomachean Ethics suggest (analogically) getting clear on the meaning of a sentence must rather be relativized to the context (the specificity and pragmatic point of the language game within which it occurs). Each language game furnishes a different context. But I am getting ahead of myself. Before inquiring about the nature or unicity of the allegedly forceless "proposition" (conceived as the content p that is common to thoughts that may occur with different forces), we can also inquire, with Kimhi, about the source of the unity of a propositionally complex judgement within which a simple predicative proposition occurs. In On Redrawing the Force Content Distinction, Christian Martin sets up the problem thus:
"The idea that thought is inherently forceful can only become an insight if it is concretely shown how that idea is compatible with the fact that embedded thoughts and dependent acts of thinking must do without a force of their own. If thoughts as such are tied to some force or other, while embedded thoughts (e. g. p qua part of not-p) do not directly come along with a force of their own, it must be clarified how the indirect connection to force, which embedded thoughts must indeed come along with, is to be understood. That is, it must be clarified how dependent logical acts that have an embedded thought as their content, and the overarching logical act that does indeed bear a force of its own interlock with each other such as to provide for the unity of a propositionally complex thought."
I don't want to say much more before reading the second part of Martin's paper, and I'm currently rereading the first part. I likely will need to revise substantially my tentative analysis of the content of negated propositions in the specific context of the game of locating apples that I described earlier, before drawing more general conclusions about the context dependence of force/content distinctions.
I'm puzzled by what seems an unnecessary multiplication of p's... I'd understood Wittgenstien's notion to be that understanding p and understanding ~p amount to the very same thing, but that judging p or ~p was undertaking a further step. That step I would put in terms of intent, well before the much less lucid notion of force. So proceeding the judgement of the cat not to be on the mat is the separation of cats from mats within a suitable form of life, together with the intent of representing thing in that way.
That is, I'm not seeing "force" as overly helpful here.
Just to be clear, Martin claims that when one asserts the propositionally complex content ~p, one does not thereby engage in a separate act of entertaining the truth value of p (with its own force) separate from the special force that attaches to the overarching content ~p. Rather, on Martin's account, when one claims that ~p, p is presented for the sake of rejection within the overarching negative judgment. The manner in which one apprehends p is entirely dependent on this overarching intention, if you wish.
I am not entirely sure what it is that you are driving at here but two thoughts occur to me. First, I have no issue with the idea that when we speak of propositional contents being "entertained" with special forces in thought or speech, the special forces that attaches to them reflect our intentions to make special kinds of moves in a language game.
Secondly, your apparent suggestion that judging that it is not the case that the cat is on the mat is tantamount to separating cats from mats in some special way that belongs to our form of life does make sense to me. But this form-of-life-relativity also suggests that for the cat to count as not being on the mat isn't simply a matter of the cat having the complementary "property" not-being-on-the-mat, where having this property could be analysed as having the complementary extension of the predicate "_is on the mat". This would make sense in the context of an extensional language such as first order predicate logic. Such language games, though, don't have the resources to express de re (object-dependent Fregean singular senses) thoughts such as the demonstrative thoughts about apples that were asserted or denied in my earlier example of a simple language game. Neither do predicates in such an extensional formal language reflect the asymmetry Martin notes between the predicate is-red and the (dependent) predicate isn't-red, which isn't a queer way for something's color to be related to redness that we refer to when we deny that an apple is red.
A whole different level...?
The interplay between form-of-life relativity, extensional language, and the complexity of expressing de re thoughts highlights a tension between formal logic and the nuances of how we actually use language. In formal systems like first-order logic, negation is usually understood in purely extensional terms: if "the cat is on the mat" is false, then the cat has the complementary property of "not being on the mat." This is a standard binary treatment of predicates. But this way of modeling lacks the resources to capture the rich, context-dependent, and object-dependent (de re) features of thoughts we actually have in ordinary language. The idea that certain de re thoughts, like demonstrative thoughts about specific objects are tied to particular objects in a way that extends beyond simple formal predicates seems to align with a more Fregean perspective. For Frege, proper names and demonstratives carry what he called "singular senses," which directly connect to the object being referred to. First-order predicate logic, being extensional, can't accommodate this kind of object-dependent senseit abstracts away from the individuality of objects, treating them only as elements of a domain of quantification. Moreover, the asymmetry between positive predicates (like "is-red") and their negations ("isn't-red") seems to invoke Wittgensteinian concerns about how our language practices, rooted in forms of life, inform meaning. The negation of "red" doesn't just refer to some bizarre alternative state of redness, but rather expresses a rejection of a particular way of seeing or classifying the object in question. In contrast, formal logic treats negation as purely symmetric and mechanical, but in actual language use, negation often relies on pragmatic and normative judgments about how things are appropriately described within our specific form of life. This gap between the abstract nature of formal languages and the more grounded, practice-based nature of our ordinary language practices raises a larger philosophical question: how much of what we express in language, especially about objects and properties, can ever be fully captured by formal logic? It's a tension between, on the one hand, the precise and consistent tools of extensional logic, and, on the other, the fluid, context-sensitive tools of natural language that are deeply embedded in our life practices and forms of life. Your point about first-order predicate logic is well taken. In formal systems like first-order logic, negation is usually understood in purely extensional terms: if "the cat is on the mat" is false, then the cat has the complementary property of "not being on the mat." This is a standard binary treatment of predicates. But, as you note, this way of modeling things lacks the resources to capture the rich, context-dependent, and object-dependent (de re) features of thoughts we actually have in ordinary language. The idea that certain de re thoughts, like demonstrative thoughts about specific objects (e.g., this apple), are tied to particular objects in a way that extends beyond simple formal predicates seems to align with a more Fregean perspective. For Frege, proper names and demonstratives carry what he called "singular senses," which directly connect to the object being referred to. First-order predicate logic, being extensional, can't accommodate this kind of object-dependent senseit abstracts away from the individuality of objects, treating them only as elements of a domain of quantification.
Moreover, your reference to the asymmetry between positive predicates (like "is-red") and their negations ("isn't-red") seems to invoke Wittgensteinian concerns about how our language practices, rooted in forms of life, inform meaning. The negation of "red" doesn't just refer to some bizarre alternative state of redness, but rather expresses a rejection of a particular way of seeing or classifying the object in question. In contrast, formal logic treats negation as purely symmetric and mechanical, but in actual language use, negation often relies on pragmatic and normative judgments about how things are appropriately described within our specific form of life. This gap between the abstract nature of formal languages and the more grounded, practice-based nature of our ordinary language practices raises a larger philosophical question: how much of what we express in language, especially about objects and properties, can ever be fully captured by formal logic? It's a tension between, on the one hand, the precise and consistent tools of extensional logic, and, on the other, the fluid, context-sensitive tools of natural language that are deeply embedded in our life practices and forms of life. Building on this distinction between formal logic and natural language, let's explore further how this tension plays out, especially in light of how we use language in ordinary contexts. When you refer to form-of-life-relativity, you're pointing to something crucial that Wittgenstein emphasizes in his later work. Language isn't just a neutral tool for representing facts; it's deeply embedded in the ways we live, act, and interact with the world. The meaning of a word, including how we handle negation, depends not just on abstract rules but on shared practiceswhat Wittgenstein calls our "form of life." For example, the meaning of "The cat is not on the mat" isn't just the complementary truth of "The cat is on the mat." It draws on shared background assumptions about what it means for objects to be in certain spatial relations and how we typically describe such relations. Negation, in our everyday language, often carries with it an implicit reference to expectations, norms, and contrasts. For instance, to say "The apple isn't red" is not merely to state the absence of redness; it contrasts with an expectation that apples are often red, so the negation carries a subtle but important normative dimension. This highlights the asymmetry between "is-red" and "isn't-red," as the latter is not just the absence of the property, but often signals a failure or deviation from some expected or typical state of affairs. Extensional languages like first-order predicate logic treat negation purely mechanically. When we negate a predicate in such a language (e.g., "P(x)" becomes "¬P(x)"), we're simply saying that some object doesn't belong to the extension of that predicate. But this misses the richer pragmatic content involved in how we use language. Frege himself was aware of this limitation. He drew a sharp distinction between the sense (Sinn) and reference (Bedeutung) of expressions, arguing that formal systems must focus on referencethe extension of termswhile leaving much of the richness of sense unexplained. In first-order logic, a negated sentence like "The cat is not on the mat" is true if and only if "the cat is on the mat" is false, but this ignores the wider web of meaning that comes with natural language negation, where such statements might involve expectations, context, and shared understanding.De re thoughts are object-dependent in a way that resists formalization in purely extensional terms. Frege's notion of singular senses helps capture this. When we think or speak de re, we're not just quantifying over objects but referring to them in a way that depends on our direct relation to them. For example, the thought "This apple is not red" doesn't just express a truth about the apple's lack of redness, but also depends on our demonstrative relationship to the particular apple we're referring to in this context. This is where formal systems struggle, especially with demonstratives or indexicals (like "this" or "here"). In formal logic, "this apple" is usually modeled as some constant or variable in a domain, abstracting away from the unique, context-dependent way in which we actually engage with the object. But for Frege, the sense of "this apple" is tied directly to the speakers cognitive or perceptual connection with the object. This relationshiphow we pick out an object in the world and form thoughts about itis richer than what can be captured in purely extensional terms. The asymmetry between "is-red" and "isn't-red" is important. When we use a positive predicate like "is-red," we're asserting something affirmative about the object's properties in a way that reflects a positive categorization. But when we say "isn't-red," we're not simply placing the object in the complement of the extension of "red." Instead, we are rejecting a specific classification, often against a background expectation. This asymmetry reflects the way our language and our practices of classification are embedded in a shared world of expectations. When we describe something as "not red," it often implies that theres something notable about this fact. In contrast, formal logic treats these as symmetric: "¬P(x)" is simply the negation of "P(x)," with no extra interpretative layers. But the actual use of negation in our form of life often involves rejecting a default classification or expectation, and this makes negation richer than simple complementation. Your earlier reference to simple language games involving demonstrative thoughts about apples points to something crucial: in ordinary language, the structure of these games allows for rich, context-sensitive thoughts that are difficult to capture in formal systems. In these games, we rely on shared practices for picking out objects and predicates, and our language reflects the complex ways we interact with the world. Formal languages like first-order predicate logic, while useful for modeling certain aspects of truth and inference, strip away much of the context and the interpersonal dimensions of language use. These games involve implicit understandings, normative judgments, and object-dependent references that go beyond the resources of extensional logic. In sum, while extensional logic is powerful for formalizing certain aspects of reasoning, it falls short in capturing the full richness of natural languageespecially in cases involving negation, de re thoughts, and asymmetries in predicate use. Language, as used in our form of life, is embedded in practices, expectations, and interactions with objects in the world. It allows us to express thoughts that are dependent on these contexts in ways that formal logic, which abstracts away from this rich background, cannot fully account for. This tension between the two highlights a key philosophical problem: how can we reconcile the precision of formal systems with the expressive flexibility and context-sensitivity of natural language? The limits of extensional logic reveal the need for other approachesperhaps more dynamic or pragmatically oriented systemsto better reflect the way we actually think, speak, and live.
Called in the nukes. Cheers.
ChatGPT o1-preview is a bit more conversant with carriage returns.
[hide]
You raise a possible objection to Martin's claim about the force of negation and the role of embedded content in negative judgments. Let's delve into the objection, examine Martin's position, and explore your tentative response to see how these perspectives interact.
---
### **The Objection Explained**
The objection can be summarized as follows:
- **Uniform Assertoric Force**: When one asserts either **p** or **not-p**, both assertions are made with the same **positive assertoric force**. The act of assertion is uniform across both affirmative and negative propositions.
- **Role of Negation Operator**: The negation operator **'not'** functions to invert the truth conditions of the proposition **p** to form **not-p**. It modifies the content but does not alter the assertoric force with which the proposition is presented.
- **Embedded Content Retains Force**: The embedded proposition **p** within **not-p** retains its propositional content and force within the overall assertion of **not-p**. Thus, **p** is still considered to have force, even when part of a negated statement.
**Implication**: According to this objection, there's no need to posit a special force of negation or to claim that the embedded thought **p** lacks force in the context of **not-p**. The distinction between force and content remains clear and unproblematic.
---
### **Martin's Position on Negation**
Christian Martin, in his analysis of negation, argues that:
1. **Inherent Force in Thoughts**: Thoughts are inherently tied to a force. When we think or judge, we are not merely entertaining propositional content but are engaging with it forcefullyasserting, denying, questioning, etc.
2. **Embedded Thoughts Lack Direct Force**: In propositionally complex judgments like **not-p**, the embedded proposition **p** does not carry an assertoric force of its own. It is presented **for the sake of rejection** within the overarching negative judgment.
3. **Negation Involves a Unique Force**: Negative judgment is not simply the assertion of a negated content but involves a unique force**the force of rejection**. This force differs from positive assertoric force and cannot be reduced to merely inverting truth conditions.
4. **Avoiding Regress and Absurdity**: If the embedded **p** in **not-p** had its own force (especially a negative one), it would lead to logical regress or absurdities, such as requiring an infinite chain of negations within negations.
5. **Unity of Complex Thoughts**: The unity of a propositionally complex thought like **not-p** depends on understanding how the embedded content and the overarching force interlock without each component having a separate force.
---
### **Your Tentative Response**
You suggest that:
- **Validity in Formal Languages**: The objection is valid within formal extensional languages like first-order predicate logic, where the separation of force and content is clean, and the negation operator functions purely to invert truth values within assertions of uniform force.
- **Different Language Games**: In other language games, especially those closer to our ordinary practices (involving de re references and object-dependent singular thoughts), the separation between force and content is not as neat. Here, the force is intertwined with content in a way that reflects the complexity of our linguistic and cognitive practices.
- **Asymmetry in Property Ascriptions**: As per Martin's example, denying that an object is red (saying "The rose is not red") is not the same as ascribing a "non-red" property to it. The act of denial involves presenting the object in a certain way to exclude a possibility, which cannot be captured by simply inverting truth conditions.
---
### **Analyzing the Objection and Your Response**
#### **1. The Nature of Formal Languages**
In formal logical systems:
- **Separation of Force and Content**: Formal languages are designed to abstract away from pragmatic aspects like force. Sentences are evaluated based on their truth conditions, and the logical operators function to modify these conditions.
- **Uniform Assertoric Force**: All statements are treated as assertions with the same force. The logical operators (like negation) operate on the content to produce new truth values without altering the assertoric nature of the statements.
- **Negation as Truth-Functional**: The negation operator simply inverts the truth value of the proposition. If **p** is true, **not-p** is false, and vice versa.
**Implication**: In this context, the objection holds because the formal system is designed to treat force uniformly and focus on truth-functional operations.
#### **2. The Complexity of Ordinary Language**
In natural language and everyday communication:
- **Interplay of Force and Content**: Force (asserting, questioning, denying) is an integral part of how we use language to convey meaning. It's not merely an add-on to propositional content but shapes how content is understood.
- **Context and Pragmatics**: The meaning of utterances depends heavily on context, speaker intentions, and pragmatic factors. This makes the separation of force and content more complex.
- **Negation as a Speech Act**: Denying a proposition involves more than asserting a negated content. It is an active rejection, which carries a different force and engages with the content differently.
- **Object-Dependent Thoughts**: In cases involving de re references (directly referring to objects), the existence of the object affects the content and force of the thought. For example, asserting "This apple is red" involves a direct reference to a specific apple, which may not be present in a formal logical representation.
**Implication**: In ordinary language, the neat separation of force and content found in formal logic doesn't hold. The force with which we engage propositions is intertwined with the content and cannot be simply abstracted away.
#### **3. Martin's Asymmetry in Property Ascriptions**
- **Affirming vs. Denying Properties**: Ascribing a property to an object ("The rose is red") is not symmetrical with denying that property ("The rose is not red"). Denial involves a different kind of engagement.
- **Rejecting Possibilities**: Denying a proposition involves rejecting the possibility of ascribing a certain property, not merely asserting the presence of some "non-red" property.
- **Logical Force of Rejection**: This act of rejection carries its own logical force, which is distinct from the assertoric force used when affirming a proposition.
**Implication**: The act of negation cannot be fully captured by inverting truth conditions within a uniform assertoric framework. It involves a unique force that affects how content is presented and understood.
---
### **Reconciling the Perspectives**
Your response effectively addresses the objection by:
- **Acknowledging the Validity in Formal Systems**: You grant that within the confines of formal extensional languages, the objection is warranted. The design of these systems supports the view that force is uniform and that negation operates purely on truth conditions.
- **Highlighting the Limitations of Formal Logic**: You point out that formal systems are abstractions that do not capture the full complexity of natural language use and cognitive practices.
- **Emphasizing Different Language Games**: Drawing on Wittgenstein's notion of language games, you suggest that different contexts and practices have different rules and conventions. In some language games, force and content are deeply intertwined.
- **Supporting Martin's View in Ordinary Contexts**: In language games closer to our ordinary practicesthose involving de re references, object-dependent thoughts, and the nuanced use of negationMartin's claim holds. The force of negation is unique, and the embedded content does not carry its own force.
---
### **Further Considerations**
#### **A. Speech Act Theory**
- **Illocutionary Acts**: According to speech act theory (Austin, Searle), when we make utterances, we perform acts like asserting, questioning, commanding, or denying. The illocutionary force is an essential part of the utterance.
- **Negation as a Different Act**: Denying something is a different illocutionary act from asserting. It involves rejecting or refuting a proposition rather than presenting it as true.
#### **B. Cognitive Perspectives**
- **Mental Attitudes**: The mental attitude we hold towards a proposition (believing, doubting, denying) affects how we process and communicate it.
- **Embedded Propositions in Cognition**: When considering embedded propositions, our cognitive engagement with them differs depending on whether we are entertaining, asserting, or rejecting them.
#### **C. Pragmatic Enrichment**
- **Contextual Implications**: The context in which a negation is used can add layers of meaning that are not captured by truth-functional logic.
- **Conversational Dynamics**: In discourse, negation can signal disagreement, correction, or contrast, which involve pragmatic forces beyond mere truth inversion.
---
### **Conclusion**
Your response effectively demonstrates that:
- **The Objection Has Limited Scope**: While the objection is valid within formal logical systems, it does not adequately account for the complexities of natural language and thought.
- **Martin's Claim Is Contextually Appropriate**: In contexts that reflect ordinary language use, Martin's assertion that negation involves a unique force and that embedded content lacks direct force is more accurate.
- **Force and Content Are Intertwined in Practice**: The interaction between force and content in negative judgments cannot be fully understood by treating them as separate entities, especially in contexts involving de re references and object-dependent thoughts.
---
### **Moving Forward**
To further address the objection and strengthen your response, you might consider:
- **Providing Examples**: Illustrate how, in everyday language, negation operates differently from mere truth inversion. For instance, show how denying a proposition can involve rejecting presuppositions or implications that are not captured in formal logic.
- **Exploring Other Language Games**: Analyze additional language games where force and content are intertwined, such as irony, sarcasm, or metaphorical language.
- **Engaging with Counterarguments**: Acknowledge potential counterarguments and provide reasons why Martin's view offers a more comprehensive understanding of negation in ordinary contexts.
[/hide]
Quoting Banno
I think what Kimhi means is: A symbolic occurrence would be when p is used as, quite literally, a symbol, such as when we show the modus ponens inference. It is not "spelled out" but is understood to stand for "any well-formed proposition." The actual occurrence would be "p spelled out," an actual sentence in some particular context of assertion/mention/belief etc.
Quoting Banno
But then there's the other sense of "law" which refers to something that doesn't necessarily hold true in all cases, but ought to. Kimhi says that this normative sense of "law" is characteristic of a dualistic understanding of how thought relates to being. Using the PNC as his example, he argues that if non-contradiction is supposed to be a principle of being, a statement about how things are in the world ("either A or not-A"), then the psychological version is "a normative requirement: that one should not contradict oneself." He doesn't think it has to follow from the ontological version. Which is part of why he rejects the whole dualistic model.
Quoting Banno
I like this. I think Nagel would point out the following: Even something as abstract as a "view from anywhere" implies that someone, some consciousness, is going to step into that place and attain the view. But built in to the "view from nowhere" is the (very abstract) notion that something remains the case regardless of anyone's viewpoint. But the two views can be made quite similar if we just say that the view from anywhere is strictly hypothetical as regards a viewer. If anyone steps in, then their view will be the same as any other "anywhere-stepper."
Rejection being irreducible to asserting a negation in some contexts is fairly straightforward as an idea right.
A) An extensional analysis of rejection regarding a statement p( x ) must rely on the following claim: asserting the statement ¬p( x ) is equivalent to rejecting p( x ).
B) The equivalence in ( A ) requires that an asserter of p( x ) would commit themselves to all and only the same claims that a rejecter of ~p( x ) would.
1) The analysis spelled out in A and B must apply in all contexts, some contexts or no contexts.
2.0 ) Assume it applies in all contexts.
2.1) Then there is no example of a rejection which is not also extensionally equivalent to affirming a negation in the sense spelled out in B.
2.2) If Bob rejects the claim "Alice believes that snarks fly" that does not commit Bob to asserting "Alice does not believe that snarks fly" or that "Alice believes that snarks don't fly", Bob can simply fail to commit to either in this rejection. eg maybe Bob believes Alice has no beliefs regarding snarks.
2.3) 2.2 is an example of a rejecter of a claim not committing themselves to all the same claims as an asserter of that claim's negation.
2.4) Discharge 2.0) - the analysis in A and B does not apply in all contexts.
3) Conclude: the analysis in A and B either applies in some contexts or no contexts.
Regarding 2.2, I believe it is mistaken to analyse this as follows:
"Bob believes ¬(Alice Believes that snarks fly)" as equivalent to "Bob rejects that Alice believes that snarks fly", the reason being that Bob can be taken to reject it makes any sense at all to associate snark related beliefs to Alice. Formally speaking, Bob could reject that Alice was a type of entity that the predicate "believes that snarks fly" could be affirmed or denied of, much like "is prime" and "is not prime" could not be asserted of the operation +.
Less formally, an example where A,B clearly applies: Two mathematicians arguing over whether the set {apples, oranges} consists only of fruit, where "...is a fruit" is a predicate defined on that domain. Rejecting the claim that the set consists only of fruit just means believing that there must be an element of the domain which satisfies ¬"...is a fruit".
With regard to generalisation, one source of rejection being irreducible to assertion of negation is that rejecting a claim can proceed on the basis of rejecting a framework that the claim relies upon. Like whether it makes sense to ascribe beliefs about snarks to Alice.
To illustrate the variability in the rejecton, consider rejecting the claim "There are three angels dancing on the head of this pin". If I reject the claim "There are three angels dancing on the head of this pin", I do not thereby commit myself to the claim "There are n angels on the head of this pin with n?3". That rejection occurs on the basis of it being trite to think about angels on the head of a pin at all, not on the basis of believing a different number of angels reside on pinhead.
Rejecting a claim can carry, therefore, a rejection of the expected conditions under which that claim is expressed rather than forcing a commitment to the negation of the rejected claim on the speaker. I believe that is the kind of non-logical factor Martins was referring to.
I believe what marks this flavour of thing as a "non-logical" factor is that it is "extra-logical" to implied context of an assertion. One rejects the rules of the implied game. Rejecting the pin-angels claim comes from rejecting the operations of thought and expression - language use, deduction, informal reasoning, gut feelings - that would enable its expression in the first place, rather than negating it in its assumed context of expression. One rejects the it-makes-sense-to-think-about-angels-on-pins-to-begin-with rules.
One could also reject a claim like "abortion is a sin" in a manner which believes in sin and a manner which does not believe in sin. The former could say that of the set of acts which satisfy the predicate "...is a sin" does not contain abortion. The latter might disagree with the Christian framing of it and think abortion's a-ok, even if eg "abortion is morally permissible" is not a negation of "abortion is a sin" (maybe there are morally permissible sins etc etc).
I think we'd want to call it "the same inference" in some contexts and not in others. Bad reasoning might infer Q from P, and good reasoning might infer Q from P, but bad reasoning is not good reasoning. The means of inference may need to be the same.
At least the same type of mistake, a carrying the 1 related error. But one could compute 12+9 incorrectly as 11 in virtue of adding 2 to 9 and forgetting the relevance of the tens column, and incorrectly as 11 in virtue of adding 2 to 9 correctly then forgetting to add the 1 to the 1 in the tens column. Both of those ways forget to carry the 1, but the means for addressing them in a student would be different, right. The second's probably simply forgetting to do it, the first is probably a more fundamental misunderstanding.
Insert gesture here toward family resemblance identity.
The thing is, this thread is about what sort of thing the judgment of a proposition is. I mistook it, for some time, to be about "assertion" in a speech-act or language-game sense, because of the phrase "assertoric force", and because my memory of Frege is a bit hazy. But it's about judgment. Kimhi wants to show there is no "logical gap" between P and "We who think P are right".
We all know the status Frege assigns to propositions; it seemed to me the same considerations would apply to the judgment of P. For the case when P is true, I think Frege might very well consider judging P true to amount to following a law of thought. (If P is the case, you ought to judge P true.) As the thought P is not your personal property, not just a psychological fact about you, so judging it is also not just a matter of your personal mental behavior, but is already marked down in Plato's great hall as right judgment or wrong judgment. Thoughts aren't psychological facts, and neither is your comportment toward them (in judgment) or handling of them (in inference, for instance).
This had not occurred to me, though it might be obvious to the rest of you. And I think it's very much in Kimhi's neighborhood. The judgment he wants restored to its rightful place is not some subjective thing, but third-realm just like propositions.
The problem is, the reasons for seeing judgment and inference as objective would apparently vouchsafe the objectivity of just about anything.
You cannot have a tidy little special-purpose platonism just for logic and mathematics, which have kind of an "eternal forms" vibe to them already. You both seemed happy to pick and choose which things get Forms and which don't, but I think you'll be stuck with a Form for "disappointment with the last season of Game of Thrones".
What have I said which has given you the impression that I like the forms? I don't mean that in an accusing or rebuking manner, I legitimately don't understand how I've committed myself to that.
My impression of the thread's argument is that:
Every proposition has a bunch of gubbins associated with it. Some of those gubbins can be treated as separable from the proposition's nature, some of them can't. Frege's allegedly arguing that whatever the judgement stroke represents can be separated from the content of a proposition that a judgement stroke is applied to. Kimhi's arguing that whatever the judgement stroke is supposed to represent, it cannot be separated.
There's then a lot of quibbling about the type of gubbins that everyone involved is talking about, and whether that's an adequate representation of Frege. A subset of the gubbins quibbles are as follows:
1 ) Whether the flavour of force Kimhi's talking about is related to illocutionary force.
1.1) Is that illocutionary force something... mental? Does it mean that you have to grasp "the assertoricity of the proposition" in order to comprehend it at all? Does it make sense to call such a mental thingybob part of a speech act at all?
2 ) Whether the flavour of force Kimhi's talking about is related to Frege's judgement stroke.
2.1) Kimhi's force seems... mental, and not reflected in propositional form. Whatever it is is to be found when examining expressing a proposition. Namely, as a part of what it would mean to be in a state of expressing that proposition and none other.
We probably have to agree that there's some proposition flavour thing in an assertion or a rejection to get going, even if we end up saying the proposition flavour thing is inextricable from some of its associated gubbins. I think that equating the proposition flavour thing and its inextricably associated gubbins with the composite of its logical form, the judgement stroke, and an extensional interpretation of its contained terms is what's at stake. So we've repeatedly embarked on a voyage of gubbins demarcation, often by example.
So I'd situate my remark above in 2.1, specifically talking about "what it would mean to be in a state of expressing that proposition and none other", where a state of expressing a proposition was a rejection or assertion of a claim.
If it turned out that the propositional doo-dad in the rejection of a claim and the assertion of a claim didn't work the same in both cases, then it'd be an example of some of the gubbins associated with expression intermingling what can be thought of as the proposition and how it is expressed/presented/display/considered/grasped/entertained.
I've not read the Kimhi in the OP, I've just read the Martins paper and a fair chunk of the thesis @Leontiskos linked earlier.
Quoting Srap Tasmaner
Could you give me some more words on that please, or a link to where you've previously spelled it out?
Can we think of an example where no amount of precision can create a genuine synonymy between, say, two mistakes? If the precision is only about the object of the mistakes, then yes, I think so. Here's one that occurs to me offhand as a candidate: Jack misidentifies a note in music as a G# (it's really a G natural), Jill misidentifies it as an Ab. As you may know, G# and Ab refer to the same note, under different music-theoretic circumstances, rather like Morning Star and Evening Star. So have Jack and Jill made the "same mistake"? Arguably, no amount of precisifying about the note itself is going to resolve this, since Jack and Jill are making their respective mistakes for different reasons. But then again, they're hearing the exact same tone and being wrong about it with the same result. I want to say it's two different mistakes. This is perhaps a cousin of the "carrying the 1" example.
It's from Kimhi's book. I don't know if anyone has posted that quote. If not I can do it tonight.
Quoting fdrake
Oh! Nothing. No no, I'm not accusing you of platonism.
Roughly, I suppose I'm claiming that nothing in this discussion makes sense at all without a pretty robust platonism. It's Frege. We're arguing over which version of platonism is most satisfactory in whatever sense. I'm suggesting we own up to that.
And where's Kimhi? There's something about bringing psychology and logic back together, so he's messing about with the core of Frege's worldview, his platonist anti-psychologism. Does he bring them back together by ditching the platonism? That's not the impression I've gotten but I don't think I've stumbled on him addressing it either way.
I just think we should quit throwing around 'proposition' and 'judgment' and 'inference' in ways that allow people to give those words their preferred reading. Frege is a Laws of Thought guy. I don't think you get to tweak his position by pulling in a little "social context" here and there, for example.
Either Kimhi is underselling the rigidity with which Frege's system excludes psychology, or what he Kimhi means by 'psychology' might not be what people think.
Yes, assertion in the sense of judgment, but I wouldn't blame yourself much for any confusion. My OP didn't discriminate, because I hadn't taken on board the point you're now drawing our attention to. And as we've seen, Kimhi himself can be hard to parse. In any case, the various sub-threads concerning other senses of "assertion" have been valuable, at least to me.
Quoting Srap Tasmaner
Yes. This is what drives him crazy -- how can we unify what appears to be a hopeless gap between the psychological and the formal? How can we bring "I judge p rightly" into some kind of entailment relation with what is the case about the world? Kimhi believes that Fregean logic doesn't permit the inference (1) S is F; (2) A thinks that S is F; (3) Thus, A truly thinks that S is F.
Lemme see if I get this right. Trying to pick it apart to understand it.
The note is G.
Jack identifies it as G#
Jill identifies it as Ab.
G# and Ab are the same frequency.
Since G# and Ab are the same frequency, they're extensionally equivalent in terms of sound frequencies.
The note will be identified mistakenly when and only when it is not heard as G.
The thing that would let you see Jack and Jill's mistake as the same is the final principle there, right - the fact that the note will be identified mistakenly when and only when it is not heard as G.
I think there's a way of mucking with it. I'm not sure why I'm mucking with it at this point though. If Jack always identified every enharmonic equivalent in the sharp form, and Jill always identified every enharmonic equivalent as the flat form, the means by which they make the mistake would be a little different. Even if they choose the same wrong note. I think this is similar to the way I muddied the waters before with Bob's criticism of Alice's snark related beliefs - focus on the agent involved's expression rather than the claim.
Quoting Srap Tasmaner
Quoting Srap Tasmaner
That makes sense. Martins argument references (what seems) a fairly static typology from Kimhi. This is Kimhi quoted in Martins:
I get the impression that two things are at play, related to your following remark:
Quoting Srap Tasmaner
The first thing at play: the role "the laws of thought" in Frege plays, Kimhi keeps an analogue of it, but they're less ironclad logical laws and more tight constraints on thought sequences/acts of thinking. I don't know what their nature is, or how they work, but Kimhi seems to want to notice expansive regularities in them. That might operate by positing a Platonic Realm Of Thought Laws (tm) which doesn't resemble Frege's, or it could be something far woolier. My intuition is that it's woolier, based on the second thing at play.
The second thing at play: dispositions, interpretations, acts of judgement also seem to be within the scope of Kimhi's "laws of thought" analogue concept, but they're... somehow external to a context of pure abstraction. They picture something like events - judgements, logical moves, presentations, mimicry. They're don't seem to quite be speech acts, as they're not necessarily enacted "outside the head", but they have a kinematic and dramatic air to them. As in "if you think this, then you must judge that", as if entertaining a proposition, grasping a proposition, presenting a propositional form all do something in a nascent quasi-mental, quasi-logical regime of expression.
What I'm imagining is at stake in Kimhi's assault on Frege is whether you can cleave off the bit Frege did from the "laws of thought" Kimhi is concerned with without mutilating them. Hence what look like bits of textual analysis on the logic symbols and rules Frege uses, but not following the rules Frege's stipulated.
I'm thus inclined to think some of this ambiguity regarding force, expression, and how it relates to Frege is coming from Kimhi (and Martin's) critique of Frege allegedly severing something from this nascent woolier collection of coordinating regularities in thought and expression. So the words are a bit wooly because Frege's allegedly made a model of something wooly that has no wool in it, and our fellow travellers are seeking and analysing the wool.
Couldn't it just be that the force of an embedded thought is a phantom context from which meaning can be drawn? It's not that we're imagining an actual assertion. It's that our worldview grew out of one in which the world is alive. There's some sort of divine narrator.
Right.
Quoting fdrake
I don't think this would get you to "the same mistake." They're both failing to hear it as G, and they're both identifying the note mistakenly, but the question is, whether the way each describes what they (mis)hear is just a preference for different enharmonic spelling. Which leads to . . .
Quoting fdrake
This may be true, but we'd need to hear more about what "the means" represents. Anyway, the case I had in mind involved more than spelling. I'm imagining a case where Jack has an understanding of a particular musical passage that would entail the G# spelling, not just cos he likes sharps better than flats, but because that would be the correct spelling on his analysis. Same for Jill, in reverse. And sadly, they're both wrong, not at a theoretical level at all, but plain old faulty ears.
Quoting fdrake
Agreed, let's stop! It was just by-the-way.
Part of what makes their nature hard to grasp is that Kimhi insists on linking them with the laws of being. Or rather, he's trying to get us to think outside that dualism. The psychological PNC and the ontological PNC are not "two different principles. In the end the monist will say neither that they are two, nor one. Or rather: that they are the same and different. " (31). To anticipate your question -- no, I don't know what that means either.
I find reading Kimhi pretty unpleasant, so a lot of what I say is kind of half-baked because I'm trying to avoid *studying* him, but that's what it takes. That said---
This is the main thing, near as I can tell.
My last few posts are trying to express my shock when it occurred to me there is a non-psychological sense of 'judgment' and this is probably Frege's sense.
I can't quite wrap my head around something like "impersonal judgment". It's not a movement of mind, not inferential. Maybe intuition? (Or revelation!) A mind and a thought just are related correctly or incorrectly.
And in trying to make sense of this, it keeps sounding like exactly what Kimhi wants, and that he says is *not* on Frege.
You can go ahead and accuse me of platonism if you like! In this sense, which circles back to what you're saying about the World 3 nature of propositions: Plato's Forms were a somewhat amazing (given the time and place) attempt to find "the view from nowhere." Intelligible objects are shown to any and all of us, requiring only the Good to illuminate them. If Plato had had the word, I believe he would have called them objective. 3,000 years later, we're still on the same hunt. Frege wants his Laws of Thought to reveal a specifically platonic world of numbers, but you're right that it can go much farther than that. And:
Quoting Srap Tasmaner
I'd offer that as a nutshell description of the canyon that loomed between Analytic and Continental philosophy in the last century. If just about anything can be presented as a World 3 thing, accessible via the view from nowhere, then we have a real problem about subjectivity and interpretation. New OP called for, clearly .
. .
Quoting Srap Tasmaner
I think that's close. For Kimhi, the key concept is affirmation and denial, not positive or negative predication.
Quoting Srap Tasmaner
I have gotten so frustrated with Kimhi over the past month that I've literally screamed, trying to untangle him. But I insist it's worth it.
Which has a weirdly moral ring to it. You're either right with God or you're not. You affirm the truth or you deny it. It's your soul that's at stake.
Quoting J
Whereas I think it's all horseshit, but it's an opportunity to explore what I find so ridiculous about this way of doing philosophy.
I do find it curious that I reached for hylomorphism right before identifying the magnitude of the platonism at issue. The old war still rages, and an enemy of my enemy is a friend.
Are you like, presently in a dungeon on trial for heresy?
Have a glance at SEP's article on psychologism. Some curious stuff there I haven't really absorbed.
I may come back to some of your other points tonight after work.
Interestingly, on page 54, Kimhi considers Critical Fregeanism, which he ascribes to Gareth Evans, as an alternative non-dualistic proposal to accommodate Frege's point about the criterion for distinguishing the senses (Sinne) of different sentences within a quasi-Kantian treatment of object-dependent thoughts. But he claims this account to be incoherent on the ground that it turns out to be incompatible with Frege's spatio-logicism, which is the thesis that "the subordinate propositions in a compound are treated as logical building blocks" (p.48). Now, I am unsure why Evans would be committed to this atomistic thesis or to take it to be an indispensable feature of an extension of Frege's notion of sense as applied to object dependent thoughts. So, I don't quite understand what motivates Kimhi's rejection of Evan's account.
However, Kimhi proceeds to develop his charge against dualism through considering the (psychological) "requirement on thinkers not to hold together a triad of judgments of the form: < p ? q, p, ~q >". This is useful because it ties up his criticism of dualism with his proposal to account for the unity of complex propositions by means of distinguishing the "display" and the "manifestation" of p as it might occur as a component of such a complex proposition. And this is where his account differs from Martin's. So, now, I'm considering not only whether Martin's criticisms of Kimhi's appeal to the merely "displaying" function of embedded propositions in accounting for the unity of complex propositions are on target, but also whether Martin's alternative proposal elucidates (and/or is elucidated by) Evan's Critical Fregeanism.
Although I must give this much more thought, I am hopeful that it does since, in the wake of Evan's Fregeanism (and of Sellars' Kantianism), philosophers like John McDowell, David Wiggins and John Haugeland have developed fairly successful accounts (on my view) of the monistic "constitutive rules" of language that serve the dual function of making the behaviors of language users intelligible by placing them within the game of giving and asking for reasons, on the one hand, and of making intelligible (and thinkable) the objects that we talk about inasmuch as our existential commitments to them are of a piece with our commitments to the rules of our languages games in which they are inextricably involved ("constituted").
I wouldn't try to alter your philosophical convictions -- there's too much of that already on TPF -- but I truly don't think platonism (including Fregean platonism) needs to be anyone's opponent. That is, unless one takes a very rigid view of it as talking about Objects Called Forms that have some kind of otherworldly existence. Perhaps that was Plato's belief, though I doubt it, but it needn't be ours. It doesn't sound as if your thoughts about hylomorphism would rule out talk of abstracta in a less reified way.
This is also the view McDowell once expressed, if I remember, and to paraphrase very loosely, that Plato himself, when taking about the form of the Good, for instance, and of our actual conceptions of the goodness only approximating or being the shadow of that "form", was speaking metaphorically to make the point that arriving at a clear conception of goodness, in particular cases, is a difficult intellectual achievement, and not that we are approaching "it" asymptotically. On that view, forms are ideal in a normative rather than a reified sense even in Plato's own conception.
No no, of course not.
We don't have to continue this here, or anywhere. Roughly, I'm just carrying the flag for population thinking versus essentialism. --- The bit earlier in the thread about loose and tight coupling, that's a suggestion that hunting for the essence of assertion, for example, is misguided.
Maybe some other time, though I really hate talking at this level of generality. Everything I say sounds like hand-wavy bullshit.
I think the answer to your question lies in the first line Kimhi quotes from Evans, which begins: "The sense of a sentence, which is of course a function of the sense of its parts . . . " (my itals). Kimhi is probably reading this to mean that Evans accepts the building-block account of propositional meaning. I'd need to read more from Evans to decide if I agree that he does, but I'll bet that's what K is objecting to.
K's specific argument about "taking different attitudes to p" is pretty good, don't you think? If you can use your building blocks to build a statement like "p & ~p" without violating any spatio-logical rules, then it does seem to invalidate the previous, psycho / logical criterion for what is thinkable, for what can be a thought. And I especially like footnote 40. (Have you noticed how much important stuff is in the footnotes that might just as well have been promoted into the body of the text? Having been an editor for many years, I can tell you that this is a sure sign of a confusing ms. receiving a heavy edit from someone trying to give it structure.) Kimhi talks about "pragmatic contradiction" as the reason you can't attach a judgment stroke to "p & ~p"; if you use the stroke, you show that you know what it means to understand a logical expression. This is very similar to Habermas's "performative contradiction" -- sounds like material for a good paper.
There's something quite amiss in this, to do with the absence of a clear account of "force". One simply can attend to the cat and the mat, and understand the predication, entirely without making a judgement as to the truth of "the cat is on the mat".
And second, the circumstances in which not being on the mat counts as a property of the cat would be, shall we say, quite extraordinary. Talk of cats and mats is what we do. Talk of properties is philosophic wordplay. Point geing that you seem to be tying a nice philosophical knot for yourself.
I appreciated 's "gubbins". Here's the thing: It remains very unclear what "assertoric force" is, and for my part I remain unconvinced, as the kids say, that "It is a thing".
Despite that it remains that we use names to denote, we use sentences to command, question and state, and we can understand what a statement says without making a judgement as to it's truth.
Note the careful absence of "force" in that last paragraph.
My point was in part to show that "modus ponens inference" is not singular; it's at best a group of loosely related activities which are not fundamental to logic.
Isn't it apparent that treating logic as imperative is a consequence of, and motivation for, logical monism? That's @Leontiskos' game - who else is playing? (He hasn't been around for a few days - hope all is well).
The view from anywhere differs from the view form nowhere in an important respect: while the view from nowhere solipsisticly centres on the self, the view from anywhere is eccentric, looking to account for what others say they see, while seeking broad consensus. It's a variation of the Principle of Charity: we make maximum sense of the words of others if we interpret them in such a way as to maximise agreement. It replaces a focus on "I" with a focus on "Us". It acknowledges that what we are doing here is inherently embedded in a community and extends beyond the self.
Quoting J
The God's eye view is sometimes referred to as the view from nowhere. I think it would be more aptly understood as the view from everywhere (and everywhen). I also like the relativistic non-omniscient notion of a view from anywhere. It could also be called 'the view from nowhere in particular'.
Quoting Banno
I don't see it that way. The self-centred view is the view from somewhere, not the view from nowhere.
I appreciate the style here. Yes, in an extensional context, ?~p ? ~?p, so far as I can make out. And belief is not an extensional context. So for beliefs, ?~p ? ~?p.
Quoting fdrake
Yes, the first being within the "judgement stroke", the second outside it, and the whole not being amenable to extensional analysis. This is Frege's contribution, to see that setting the judgement stroke to the side permits extensionality. And keeping in mind, extensionality is what makes 'p' the very same thing in the various expresions within the scope of the judgement stroke. So in your example, the protagonists are not talking of the same thing in using the word "sin".
Isn't it apt to be true, or perhaps false? Couldn't it be true, or perhaps false, in suitable circumstances? What more could you want?
Exactly. You need context to turn a sentence into a proposition.
On your account, a proposition's truth value must be fixed by context. I submit that there are propositions for which the truth value is unknown, and yet these count as propositions. Consider "There is life on other planets". I take this to have a truth value, but not one we know. I count it as a proposition. Do you? Is it only a proposition if one specifies which planet?
How can it be truth-apt if we don't even know which cat it is?
What do you think "apt" means?
It means it can be either true or false.
...given the right circumstances.
Exactly. The only way I can make sense of Frege's idea of a proposition (a thought) that is disconnected from assertion is to imagine that we're looking at humans as if they're robots and we're examining the programming to see where the meaning is coming from. That's wild.
Quoting Banno
Sentences aren't usually considered to be truth-apt. There's a good SEP article that explains why.
I agree. Wild. But is this anything more than an odd piece of of biography?
If you are incapable of entertaining a statement without deciding if it is true or if it is false, then you and I are different. I can.
Quoting frank
You keep saying this in spite of protests from both me and Leontiskos that no one has claimed this.
You misunderstood. I have never said that.
This could indeed be a special case where Martin's account of the unity of propositionally complex propositions with the form ~p applies. Again, his account, roughly, is that in judging (asserting) ~p, one presents p for the sake of rejection within the overarching negative judgment. The reason why one presents p for the sake of rejection could indeed be that one rejects the rules of the implied game (whereby p is presented as a content that is a suitable target for truth evaluation).
Likewise, in the example I had suggested where p can be expressed demonstratively as "this apple is on the table", and the singular content purports to express a de re sense, the rejection of the claim might present it for the sake of rejection on the ground that there is no de re sense available to be thought (since the presence of an apple is merely an illusion).
In this case, however, unlike the pin-angels case, it is unclear that there is a common content expressible as (some) linguistic form p that is asserted in one case and presented for the sake of rejection in the other. What would it be? While I may understand what it is that someone who falls under the illusion that there is an apple on the table means, in denying the truth of their claim on the ground that there isn't an apple for them to refer to, I can't express my denial as "~p" (i.e. "It is not the case that this apple is on the table"). So, in this case, my suggestion doesn't appear to be a specific application of Martin's proposal. I'm rather attending to the function in a specific language game where the denial is meant, not to present the content of a thought for the sake of rejection (for whatever reason), but rather to deny that the putative thought being expressed is a thought at all (and hence deny it having so much as a content). My denial rather consists in presenting the overarching "act" of the asserter as a failure to actualise their general capacity to refer demonstratively to specific apples for the purpose of communicating their locations.
@frank's beef is different. I think he is simply wondering about the manner in which the singular term "the cat" functions in the sentence such that a statement being expressed by means of this sentence (on a particular occasion of use) doesn't leave it indefinite what cat is at issue. Now knowing what cat is being talked about isn't the same as withholding judgement regarding what is said about a determinate cat.
Quoting Pierre-Normand
To be clear - are you saying that there is common content between the assertion and rejection but that this common content is inexpressible as (some) linguistic form p, or are you saying that there is no common content between the assertion and rejection which could have been expressed in any linguistic form whatsoever, in virtue of there being no common content between the assertion and the rejection?
I suppose strictly speaking you are expressing uncertainty regarding one of the above claims, rather than committing yourself strongly to either.
Am I right in thinking that you are construing that in order for an expressive thingybob containing a singular term expressing a de re sense to count as a thought, the singular term expressing a de re sense must be a successful act of reference to the entity associated with the de re sense - in this case the apple? And you are rejecting the claim "this apple is on the table" distally because there isn't an apple on the table but proximately because the singular term with the de re sense doesn't successfully refer as it is desired to, since there is no apple on the table?
I am committing myself to this claim in the cases where unproblematic demonstrative references can be made to ordinary objects and identifying illusory cases (of reference failure) is likewise clear. The pin-angels case is less certain because it depends to what extent we are willing to grant some intelligibility to the idea that there is a way the world could possibly be such that there are determinate numbers of angels dancing on the heads of particular pins, in order to grant that someone who "thinks" this about some particular pin is entertaining an intelligible thought content at all.
Quoting fdrake
That's a very nice way to put it. The content of a thought ought to specify its truth conditions. Hence, the content of a simple predicative thought must have a referent to its singular term such that its truth or falsity depends on how things are with the referent.
To be clear, Frank seems to be saying that since we do not know which cat is being spoken of, "the cat is on the mat" is not an example of a proposition. Might be OK to think of "The cat sat on the mat" as a variable ranging over propositions.
Natural enough. For a lot of cases, we usually say we need two elements for assertion: what we're talking about (to be picked out by a referential expression) and what we're saying about it (the predication).
Two small points about this though.
1. If you think of this in terms of communication, there's a fairly clear sense of "picking out" or "specifying" available: you negotiate until you agree on the subject; enough for your audience to know what you're talking about is enough for you to say what you want to say.
There is no standard as clear that doesn't consider communication. If someone is just expressing their views in language for fun, speaking their beliefs to the universe at large, what standard do they meet to count their referential expressions as successful?
Negotiation can be really one-sided. Suppose you tell me you have to take care of something and then we can go; I wait by the car and when you arrive I ask, "Did you take care of it?" If you say, "Take care of what?" all I have is "Whatever you told me you had to take care of!" I take myself to be talking about something that only you can pick out.
2. Principally for descriptions (with a bound variable) but even for names, we can sometimes choose -- to use the programming language terminology -- between early binding and late binding, between fixing reference at "compile time", when we first speak, and at "run time", which can vary.
Consider a direction like "Don't forget to put your tools away after". The tools that are already where they should be can't be put away, so the intention is to pick out whichever tools are out at the time you're carrying out the directive. That can also be expressed as a conditional --- something like, "For all members of your tools, if it's out then put it away." The variable is singular now, but it's still not going to be bound until run-time, and then a number of times, also not known until run-time. Same thing.
This example is similar to the example in the first point, but one person gives the criterion and the other applies it; together they fix the reference, but not immediately.
---
Both points are intended to cast a bit of doubt on the presumption that our propositions are always referentially determinate, and thus their truth conditions too, at the time of our choosing, or that they need to be. (And I didn't even mention vagueness.)
There are similarly open-ended options for predication.
None of this matters to Frege or Kimhi, I'm sure. I don't know if it helps with @Banno's cat.
I quite appreciate your examples. In The Varieties of Reference, Gareth Evans discusses the case where someone who overhears other people talking about "Nicole"(?) (or some other name) and who isn't acquainted with Nicole and isn't either already party to the practice of referring to this person as Nicole can think about her rather in the way you can make reference to this "it" that I needed to take care of without knowing what "it" is under any other description than whatever it is that I had in mind when I mentioned "it". Reference functions because you effectively defer to me for fixing the referent of your thought. Likewise the compiler can defer to (i.e. can have the function to enable the processing of) data only available to running instances at runtime. In offering to explore varieties of reference, rather than offering a unified theory of what what it is that the activity of referring to things consists of in all cases, Evans was very sensitive to the Wittgensteinian warning Martin also pays heeds to: "against a 'craving for generality' and a 'contemptuous attitude towards the particular case' as a source of philosophical confusion." But Evan's overarching theme, which seems relevant to Frege (and Kimhi's) preoccupation, consists in situating our referential practices within the activity of individuating the things being referred to in ways that are quite inconsistent with representationalist assumptions that seek to connect thought with the world in ways that make the world "external" and ready made.
That's damn cool.
Putting this discussion in terms of thought rather than statements or propositions is problematic in all sorts of ways, to do with the sort of issues you raise here, and mostly avoided since the first half of last century by talking about language rather than thinking. Seems a retrograde step.
If you express a proposition you just need to be pointing to some state of affairs. Precision isn't really the issue.
I guess you could read my examples that way, but it wasn't my intention.
It's a little harder to show collaborative thought, but I expect most of us have had an experience like this: you're trying to express or even explain something you don't quite have a grasp of, and the person you're talking to puts it in such a way that it clarifies your own thinking for you. (I've already posted elsewhere Fry & Laurie's "That's It!", so only a link this time.)
Well I suspect not just our language use but almost all of our thinking is just as collaborative as in this example, it's just usually harder to see. "I think ..." "I judge ..." Bullshit. Tens of thousands of years have gone into every thought you've ever had, every word you've ever uttered.
Very good. Would you agree that both the VA and VN are attempts to capture some concept of objectivity? (read "intersubjectivity" in the case of VA)
Quoting J
At this point I very much want to know what motivates you to have faith in Kimhi. Or more precisely, "Suppose Kimhi's arguments fail. How would you try to salvage his project, and what would the aim be?" What's the target here, for you?
-
- This is informative and helpful, but I am still curious about the question I asked, "Where, historically, would you say that essential connection gets dissolved or weakened?"
-
Quoting Srap Tasmaner
Quoting J
And I would say that Kimhi is not occupying the Platonist position; Frege is. Kimhi is offering the Aristotelian alternative, or at least attempting to.
Note too that the starting point for Aristotle is that we do know things and we do grow in knowledge (i.e. learn things). For Aristotle logic is simultaneously an explanation of how this is possible and a roadmap to learning. By the time we get to Wittgenstein it is not. Frege is somewhere inbetween.
Quoting J
I still maintain that <this thread> is a great testament to Kimhi's point here. It is living proof of the deep problems that arise in a truth-functional context.
-
Quoting Pierre-Normand
Yes, good. :up:
-
Quoting bongo fury
:up:
-
Quoting J
He is, and that makes sense in context, for he is responding to a criticism similar to yours. Still, it's a good question whether one can be more than defensive in such a situation.
-
Quoting Pierre-Normand
Right.
-
Quoting Srap Tasmaner
I think so. :up:
-
- Good posts, and we spoke about the difference between denial and negation earlier. Kimhi (and Wittgenstein) accuse Frege of flubbing this distinction, but Rombout points out that Frege never did, since he allows negation but not denial (i.e. not judgments of falsity at the level of the judgment-stroke). What's curious is that, if I am right, Frege didn't understand the difference between denial and negation and sort of "got lucky" insofar as he thought denial would be superfluous.
-
Quoting Srap Tasmaner
Yep. :up:
-
Quoting J
I don't think Kimhi appreciates the objectivity of Frege's judgment-stroke, and therefore this critique seems misplaced. I think that inference holds for Frege, it's just that he may not want to draw out such metalogical implications.
-
Quoting fdrake
:up:
I was revisiting Newmans Grammar of Assent on Anthony Kennys recommendation, and it got me to thinking about modus ponens. One point Newman makes is that while inference can be purely formal, with no concrete content (he gives the transitive property of identity as an example), assent requires such content. Assenting to some proposition requires an actual proposition; just p will not do. In his review Boynton quotes Rödl, . . .the letter p. There is an insouciance with respect to this fateful letter. It stands ready quietly, unobtrusively, to assure us that we know what we are talking about. . . As I noted earlier in the thread, this is a criticism of Kimhi. Kimhi tries to critique Frege from a Fregian point of view, and because of this his critique has no force.
Like p, modus ponens is a very odd abstraction. From the perspective of concrete judgments it seems to say nothing at all, and Wittgenstein is here instructive:
Quoting Frege, Russell and Wittgenstein on the Judgment Stroke, by Floor Rombout, 57
(Rombout points out that Wittgenstein is interested in the consequence-relation and not inference, and although this is true there is nevertheless a way in which modus ponens seems to lend itself to a consequence-relation framing, which looks to be a problem for Frege.)
To some extent Wittgenstein is right. Put bluntly, modus ponens is not a form of reasoning so much as a form of post hoc reasoning or rationalization. It is an ad hoc response to the problem of the Meno. How did you get to B from A? By holding that B follows from A!
Rombout argues that Frege, Russell, and Wittgenstein have different conceptions of what logic is, and the problem here may be that Kimhis conception of logic is too close to Freges to critique it. The deeply Aristotelian response to modus ponens is to reject the form, not to quibble about the assertoric force of different ps. Follows from is the meta-form of all logic, not a rule of inference. For Aristotle, logic is supposed to say why B follows from A, not that B follows from A. This critique of Kimhis therefore has more to do with modus ponens than Frege.
Quasi-subjective moves are not at home in logical systems which favor consequence over inference. Freges judgment-stroke or Kimhis self-consciousness dont make any sense with respect to p, because p was not made for such quasi-subjective moves. p is just a true/false abstraction. Theres nothing there to judge.
(What Kimhi is failing to recognize is that his subject-predicate predilection cuts against the things like modus ponens and not just Frege, even though modus ponens was central for Frege. That whole approach deviates from the act of thinking which so interests Kimhi.)
()
Good find. This is an important paper for this thread: link to Martin's paper.
-
Quoting On Redrawing the Force Content Distinction, by Christian Martin, 184
This is the point I made to @Srap Tasmaner earlier:
Quoting Leontiskos
Before reading Martin I hadn't noticed that Kimhi falls into this himself.
Incidentally, Newman uses 'assent' rather than 'assert', which clears up a lot of the mud that Srap in particular was traversing. I think it also helps address the public/private counterargument.
Quoting On Redrawing the Force Content Distinction, by Christian Martin, 186
The same problem came up in a recent pm with Bob Ross, where he was tripping over the difference between a species of intentional act and a particular intentional act. Apparently what Wittgenstein sees as context Aquinas would see as intention, where intention is essential to an act and not truly separable from it. Thus a mimetic act and a non-mimetic act are two different kinds of acts.
This question about having faith in Kimhi perhaps illuminates a significant difference in how we approach philosophy. I said in the OP that I was unsure whether Kimhi was raising a plausible challenge to Frege on assertion. I was pleasantly surprised to find a number of us willing to do some deep diving, in order to explore this and related questions. But l remain unsure about the Kimhi-inspired challenge, and whether Kimhi's entire project is solid, or whether he's someone who can raise excellent questions but not provide arguable answers.
But there it is . . . I wasn't reading Kimhi in the first place in order to find some truth that might settle some important controversy. I don't believe, at this extremely deep level of meta-philosophy, that such truths exist. I read K in order to better understand the questions, and to work on interpretation (in the hermeneutic sense) of why the protracted antinomies here are so persistent. And here, if you like, my "faith" in Kimhi has proved justified: For all the difficulty attendant on reading him, my insight into the underpinnings of predicate logic, and the many other questions that have arisen, has sharpened, and generated a host of other fascinating (to me) issues. That's why it's worth it, despite the screaming. (His inadequacies as a writer come with the philosophical territory, I would say. Most philosophers aren't good stylists.)
Robert Hanna, in that T&B review that I otherwise didn't like, stood up for a similar outlook:
[quote="Robert Hanna, "On Irad Kimhi's Thinking and Being""]To begin at the end, my overall judgment is that although Thinking and Being is indeed a
first-rate and perhaps even brilliant piece of philosophy, and although it has genuine
historico-philosophical import, in that, in my opinion, it effectively closes out a 100+
year-long tradition in modern philosophy, namely, the classical Analytic tradition,
nevertheless, all its central theses are false. [/quote]
I'm figuring that such a conclusion might be incoherent to you -- how could Kimhi be brilliant and important if he gets it all wrong? My outlook is even more modest than Hanna's: We're not yet sure whether he gets it right or wrong, and whether the kinds of things that worry him are in fact solvable. It's too soon, the grist hasn't gone through the mill yet. This happens whenever an important work appears, and has nothing to do, in my opinion, with bringing some controversy to a conclusion. I don't believe philosophy settles questions in that way. Nor will K's brilliance be burnished or tarnished if we never do reach consensus.
I guess that's the target you asked about.
The point here is that this thread lacks a concrete thesis or question: we aren't at all sure what we are doing. I thought that if you knew what you were doing as the author of the OP it might provide us with a direction. It's not a trap so much as a question, "What's your motivation for asking the question?" (How to Write an OP).
Quoting J
Hmm? What I got from that post was, "There is no target, so grab another arrow and keep shooting."
It's not at all clear what "classical" analytic philosophy might be, nor what the argument(s) against it might be, and certainly not that they succeed. Nor is it clear that there is any substantial point here against formal logic as it now stands, nor what any alternative might look like.
And it remains unclear what sort of thing "assertoric force" might be.
In the end I remain unimpressed.
I find this whole thing opaque in the absence of some clear motivations about where Kimhi wants to take us, what is at stake, etc. And I am not even particularly attached to the tradition that Kimhi is targeting! I think the sub-text needs to be brought to the surface.
If the thesis is false, then there is a thesis. But, what is the thesis?
Since "assertoric force" remains obscure, it remains unclear what the problem with "assertoric force" might be.
Right, or it's that we have a proximate thesis but no remote thesis:
Quoting Leontiskos
One should apply the context principle to arguments and theses themselves. The meaning of a thesis can only be grasped in relation to the deeper conclusion it is meant to support. So we have Kimhi's proximate thesis: Frege mucked up assertoric force. But what hangs on this? What is the import? What does it matter if Frege did or did not muck up assertoric force? Until we understand this more remote thesis we can't even really understand the proximate thesis.
What is Frege's notion of assertoric force, and how was it mucked up, and did subsequent developments of the notion of "force" not address those problems, and how is any of this so central to "Classical" analytic philosophy that it undermines it?
Frege's notion of assertic force is to do with the judgment stroke, it was further developed in different directions by model theory and Oxbridge linguistic philosophy, both of which became ubiquitous. It remains unclear what any problem with "classical" analytic philosophy might be.
I've never thought of logic as normative. Have you? I've always thought of it as if the mind is a landscape that's just there, that we're inside. Logic is part of the boundaries of it. What do you think logic is?
I can't quite figure out if you want to claim that the notion of assertoric force is so obscure and muddled that we ought to entirely dispense with it or if you rather want to claim that it is so clear and well understood that you can't fathom what the problem might be with it.
On edit: Myself, I would say that, yes, we have a fairly good idea regarding what it is but our attempts to make the notion explicit and/or formalize it leads to puzzles regarding its relation to content. (And diagnosing the source of a philosophical puzzle, in general, can be instructive).
Nor can I. If it is just the illocutionary force involved in making an assertion, then it seems reasonably clear, but then what is Kimhi worried about? and if it is something different, then what? A force involved in denoting - what's that, then? Or something else?
You seem to treat it as fairly transparent. So what is it?
(Reminder: Parmenides puzzle number one is, how can we think what is not the case? Number two is, how can we talk about what is not the case, even to say that it is not?)
Here's most of the footnote on pages 9 and 10. This is not an argument per se, but does lay out pretty well what Kimhi takes himself to be up to in relation to early-ish analytic philosophy.
(1) no objection
(2) also fine
(3) an eyebrow is raised
(4) a fateful decision
(5) and this is the result
(6) which we decry
TL;DR Kimhi is a proposition skeptic.
He is not the first. Quine was a proposition skeptic, and his issue was indeed with the "propositional whole"; he concluded that our beliefs face the tribunal of evidence en masse. The atomic proposition, Quine argued, was a myth. (Quine effectively declared the end of early analytic philosophy here, and suggested his new "logical empiricism" was in the tradition of American pragmatism.)
Kimhi's proposition skepticism is different; he objects, so far as he indicates here, not to atomicity, but to forcelessness. It is the force / content distinction, he says, that allows philosophers to attribute to propositions independent existence.
This would be an interesting choice. Who believes in atomicity anymore? It's been on the outs for half a century. What might Kimhi find attractive about it?
If it turns out Kimhi is not committed to atomicity, then the proposition is already dead and does not need killing. Perhaps he is not convinced by the previous reports of its death.
Read and re-read part (4) up there. That's the heart of it (but y'all were talking historical context, so you got it).
(4) says not that there are no atomic propositions, but that their existence is "conferred upon" them by the veridical use of "to be", that is, by what we have been calling 'judgment' or 'assertion'.
This does indeed look like the hylomorphic claim that "what you say is the case" exists only immanently in your saying so, not independently as we all suppose Frege to believe. (As variously Aristotle, @Leontiskos and I have suggested.)
In a sense, this claim alone solves the Parmenides puzzles! Or at least the second one. By speaking, we can bring into existence an atomic proposition; we need only say that something is or is not the case. There is no reliance on anything else here, nothing that would be needed to support the existence of our atomic proposition (no "negative fact" for instance, no missing truthmaker). It is entirely within our power.
(He will say something similar about thinking, not relying on anything external to itself.)
What do we think about Kimhi's in-the-moment atomic propositions?
Is that something worth having?
Is it something we will get to keep, or will the various arguments against atomicity sweep these away too?
I don't think it's transparent at all (although I might have thought that it was fairly unproblematic prior to getting engaged in this thread). One issue arises when we seek to abstract away the content of a proposition as something that is common to all the acts involving this content regardless of their illocutionary force (or the mental equivalents of such forces when propositions are entertained by individuals). Propositional contents "specify" ways for the world to be such that we can allegedly assert, question, imagine, doubt, etc., that the world is that way. In the case where the language at issue is formal and extensional, the problem is less acute. However, in the case of natural languages, the objects, properties, relations, etc. being talked about, aren't merely being stipulated to exist prior to our engaging with them referentially with our speech and mental acts. Their natures and individuation criteria are caught up in the norms of the language games within which we engage with them. (Think of Sellars's material inferences like <'A is located east of B' iff 'B is located west of A'> as a rule that is partially constitutive of the meanings the relational predicates 'east of' and 'west of'). Those norms govern, among other things, what circumstances warrant producing mental acts (or speech acts) with this or that illocutionary force, but they also contribute to determining what those contents are. Hence, the contents of such acts can't always be neatly separated out from their forces.
This Aristotle bloke is in good company ;-)
"...having its own existence..."? So in what way does a proposition "exist"? I can make sense of it's being treated as the value of a bound variable, "There is a proposition such that it has as it's subject the cat and the mat". Looks like it could be treated extensionally, too.
What problem? The sort of thing addressed by free logic or possible world semantics? But then it would not be fair to say it was ignored...
Still puzzled.
Don't think so. At least at first, Kimhi says nothing to suggest that you do anything by saying that things stand thus-and-so.
Quoting Banno
Only as an abstract object, immanent in an actual use. What I think so far.
Quoting Banno
He defines three sorts of problems related to non-existence: (1) empty predicates; (2) vacuous singular terms; (3) problems that implicate the whole proposition, not just its parts as in (1) and (2). The third set includes the Parmenidean problems: how do we think, falsely, that the world is how it is not; how do we say, truly, that the world is not as it is not. His examples come from Wittgenstein, one from the early Notebooks, one from the Blue & Brown books.
@Banno @Pierre-Normand
I was thinking (surprise). This is about how to ground force "in" the territory of a proposition understood as a set of equivalent truth conditions.
It seems generally comfortable, hereabouts, to conceive of propositions as that which is shared between the expressions _snow is white_ and _schnee ist weiß_. One way of fleshing out what is shared is that both expressions have the same truth conditions. Moreover, that both predicates "is white" and "ist weiß" have the same extensions and that "snow" and "schnee" can be used to denote precisely the same entities and type of entity.
What makes the first paragraph an account of what is shared between the expressions? The account finds that every relevant facet of one expression would apply to the other, it does this by grasping a facet and comparing it to some idealised use case. When assaying the two expressions for their content, no one cares that plenty of humans exist now who believe snow is white but not that schnee ist weiß, in virtue of not speaking enough German - this is allegedly ephemeral, and so it is abstracted. I think it makes sense to call this discrepancy ephemeral because what one speaker would do with the expression "snow is white" is (purportedly) exactly what they would do with the expression "schnee ist weiß".
But you can note that they share other things - when someone judges that snow is white, they would also judge that schnee ist weiß. When someone would reject that snow is white, they would also reject that schnee ist weiß.
I need to take a step back into the characterisation I gave of an extensional account.
Asserting and rejection in the above claim are in fact placeholders. A and B can be modified to refer to an arbitrary pair of relations to p(x), R and S. Each of them need a mapping that applies to p( x ) so that being in relation R to s(p( x )) is equivalent to being in relation S to r(p( x )). That criterion takes a predication, and says that being in relation R to it is equivalent to being in some relation S to some mapping of it.
Previously:
R=affirmation
r=identity
S=rejection
s=negation
With that generalisation, ( B ) spells out the equivalence in terms of "commitment to the same claims" under some transformation of the judged statement. However, recall this paragraph in this post:
The normative machinery in ( B ), "commitment to the same claims", also applies to the judgements regarding snow being white and schnee being weiß - acceptance, affirmation, rejection, rebuking... . Ergo, the same machinery that sets up a criterion for extensional equivalence can also be used to set up a criterion of equivalence that assesses whether two expressions would commit you to the same judgements.
NB, the machinery which allowed us to assay the sentences and refine them into their propositional content with the extensional criterion is also allowing us to assay the sentences and refine them into a flavour of content which includes judgements. I think this heterogenous, but still orderly, collection are the forces we're speaking about. They're baked into the expression like the truth condition is alleged to be.
Whereas the illocutionary force concept is not baked into the commonalities between sentences whose factual content is equivalent. It operates on sentences with a given factual content. Forces seem aligned with the conditions that allow us to grasp an expression's content - content as affirmation, content as rejection. Illocutionary forces are means of operating on an expression's content, content as factual, rejection as practical.
Another aspect of this, which I've thought through far less, is the connection to "being" as Kimhi would have it. But I have an inkling of a way in. If propositional content has a privileged relationship with what is the case - that is, what is - then force would be aligned with what is using the same machinery as above. There is a duality in the illocutionary force concept - content as factual, act as practical - which the force concept avoids. Nowhere near comfortable enough with the thread's material to make that connection well yet though.
I see you already made roughly the same point as I did here with less words.
This is all fairly trivial. Kimhi's idea of the normative applies when a philosopher, noticing the Ontological Law of Non-Contradiction ("both A and ~A cannot be the case"), also notices that it's possible to say contradictory things, inadvertently or on purpose. This philosopher then claims that we shouldn't do this. We ought to fit our thinking to the way the world is. (But again, Kimhi himself is certainly not that philosopher. He won't countenance the dualism.)
You ask what I think logic is. Basically, I agree with you that logic describes one of the "boundaries of the mind." But this boundary is peculiar in two respects, both hinted at above. One, it's a boundary that applies somewhat hypothetically: If we wish to talk sense and not nonsense, we're going to keep within logic's boundary. And two, our reasons for trying to respect it -- to refrain from talking nonsense -- seem all bound up with the OPNC, with our desire to think correctly about the way the world really is.
Schrodinger's cat: Unclear if it's alive or dead
Banno's cat: Unclear if it's referentially determinate
Kimhi's cat: Must be paired with a non-cat to make sense!
:yum:
There's more, but let's stop here a moment.
Extensional complex propositions are truth-functions of their component propositions, but intensional complex propositions are not. That means that p occurs in an extensional complex on the expectation that it can be given a truth-value contributory to the truth-value of the complex; but when p occurs in an intensional complex, its truth-value makes no difference to the truth-value of the complex. So yes, those ways of occurring are different, maybe even "radically" different.
So how does that lead to "in and of itself true or false"? I think it's just the claim that for p to work in an extensional context it has to be ready to provide a truth value. In particular, that truth value cannot depend on the truth value of any other proposition, so --- atomicity.
Which we had *some* reason to think Kimhi was into, but he has a specific issue here, something about the "logical unity of p and ~p" and he doesn't want to say you can consider p without considering the complex ~p.
That matters because what occurs in an intensional complex like "A thinks p" is the very same proposition that's in ~p, which means we get to consider how p works in these intensional complexes. And any A that affirms p denies ~p. (I'll have to check tonight when I can look at the text, but I think this is one of those self-evident, non-inferential things for him.)
In short, if you take this detour through intensional complexes, you get a specific failure of atomicity, which extensional complexes just require.
Why is this the fault of the extension / intension distinction? I think it's sort of a revenge pattern: yes, the truth-value of p doesn't matter to the truth of "A thinks p", but there's still an exclusionary relationship between "A thinks p" and "A thinks ~p" that the usual view cannot account for, precisely because it blinds us to the p in "A thinks p."
Quoting fdrake
From the viewpoint provided us by Srap, I think this is right, thanks.
*
Heres a somewhat related question arising from the many discussions about assertion on this thread, and also from Rombouts essay/thesis on the judgment stroke as understood by Frege, Russell, and Wittgenstein. (A really helpful work, if you haven't looked at it yet.) How we answer it may shed light on assertion in general.
Consider these two statements:
(1) ?It is true that p
(2) ?Someone asserts that p is true
In ordinary language, its plain to see that they dont mean the same thing. (1) makes a truth claim, while (2) describes some act of assertion, the subject of which may or may not be true. Compare ?Its true that the sky was cloudy today and ?Pat asserted that the sky was cloudy today. In the first case, the subject is the sky, in the second were talking about an assertion of Pats. Pat may well be wrong, but I can still truthfully say that she made the assertion.
Whats going on here is a game, if you like, about how the word assert is used in English. Most competent speakers would have no trouble explaining it. We would say, ?Assert can mean ?say something that is true, or it can mean ?say something purporting to be true. It depends on the context, and usually its clear which meaning is intended.
Which meaning does Frege have in mind with the judgment stroke? Show your work. :wink:
I see what you're saying. I just don't think anyone other than a few stray mystics is ever truly illogical.
The person who is being admonished to be more logical is being asked to think it through again. Statements of logic, like the LONC, are indubitable. You don't really have any choice in that. If you speak in contradictions (outside of mysticism), you're spouting nonsense, right? You're asserting p's that can't be true. The fault is in failing to take note of what you're bound to think.
As for an ontological LONC, how would we establish that? To nudge Hume, even if it's been true up to now that contradictions don't happen, that doesn't mean it won't start happening tomorrow. The ontological LONC is really an expectation rooted in logic. Double slit experiments cause stress for decades. No one ever makes a credible case for dispensing with the LONC. We're stuck with it.
Am I missing the point here?
Its an interesting point. Would you agree that its possible to be illogical without knowing it, or meaning it? If so, then plenty of folk besides mystics are frequently illogical. I think what youre saying is that, once we become aware of the logic/illogic in a statement, we dont have a choice about which is which. We can no longer think in the way we formerly did, in our confusion, and still claim to make sense. That may well be true.
Quoting frank
Not at all. And if you regard Either A or ~A as a Humean generality, then your view of the connection between logic and the world would fall under Kimhis category of psycho / logicism -- Either A or ~A is how things look to us given that OPNC is only an expectation rooted in logic. There may be some version of reality, beyond our ken, in which "The cat is black" and "The cat is not black" happily coexist. (Not talking fuzzy logic here, of course.) His category of logo / psychism flips it the other way round now its the world that is indeed displaying logical structure, and if logic as thought does the same, that is an application of the OPNC, not a new principle; we think logically because the world is logical.
Cool. Logo / psychism is basically stoicism.
Quoting Srap Tasmaner
Yes, I think this is right.
Quoting Srap Tasmaner
Yes, but why are we to think that Kimhi is committed to "atomicity"? That's what puzzled me about your first post. I am also unconvinced that Kimhi is a "proposition skeptic," although it is an interesting idea.
When I started reading Kimhi I received the impression that he knew what he was doing or where he was going. The more I read, the less sure of that I am. I think it was Boynton's review which questioned whether Parmenides was central to Kimhi's argument or more tangential, and that is one example of the difficulty. It is worth remembering that every single secondary source we have examined thinks Kimhi is wrong in significant ways, with the exception of Boynton who thinks he is wrong in a smaller way.
-
Quoting Srap Tasmaner
It is in our power, but I think most parties are agreed that in order to assert ~p there is a "reliance" on an understanding of p. This is the focus of Martin's paper, which seems to be very much on point.
---
Quoting J
Rombout points out that Frege is not merely attributing a belief to a subject with his judgment-stroke, and that Wittgenstein fails to recognize this (72). Kimhi seems to follow Wittgenstein in this. Indeed, Kimhi seems to be simply wrong when he says that the argument is inaccessible to Frege that, "She asserts p, therefore p is true" (where 'asserts' refers to Frege's judgment-stroke).
That's my reading too -- he's not using the judgment stroke merely to mark a purported truth. But how shall we characterize what he is doing? This is where the problems start to crop up . . .
All these problems have been dealt before by the ancients and then by the Kantians. Parmenides asserts the world is ONE but we falsely perceive it as a multiplicity. A is ~A here. The hard part for Parmenides (and other like him) is getting how A is ~A. Schopenhauer, for example, said that this is because (taking from Kant), the world is Ideal, and thus the mind is structured from manifestations of the ONE (Will). I don't think he quite threads the needle... However, the point being that psychology (aka "psychologism") structures the world such that A is ~A, but we cannot see but the metaphysical reality is thusly obscured. It is the same with Buddhist's Nirvana, etc. Reality and illusion is at the heart of much of early philosophy. Analytics seem to just want to clarify the phenomenal reality and to do so, want to provide basic rules to communicate what our psychology tells us. The minute you don't ascribe it to psychology, you are making a METAPHYSICAL claim and not an epistemological one. Schopenhauer had four volumes on his metaphysical claims. Platonists/Neoplatonists also had such writings. There is generally a lack of such claims in linguistically-based analytic philosophy. The problem I see here is that the metaphysics has been detached from the claims. Perhaps Kimhi is decrying this.
This is fairly important. Kimhi does somewhat attempt to provide an alternative, but Martin demonstrates rather quickly that Kimhi's alternative falls into the exact same problems that he attributes to Frege's conception (184...).
Thus:
Quoting On Redrawing the Force Content Distinction, by Christian Martin, 194-5 (my emphasis)
What we need is a constructive alternative, and this is what Martin claims to provide.
Quite the opposite. I'm just forcing myself to try to understand the damn book. Although maybe you're right, in the sense that I'm just picking out the bits that seem to address The Tradition.
Quoting Leontiskos
That was an hypothesis: if he doesn't attack the "atomic" part of "atomic proposition" (which is what Quine did), maybe he's okay with it.
Quoting Leontiskos
I believe Kimhi wants to say these are the same thing, in the following sense (although there's some labor over it): extensionally, ~p is a complex proposition dependent certainly for truth-value but perhaps also for sense on p; intensionally, to consider p at all is also to consider ~p, to think or judge or say one is also to take a position on the other.
Another way to get there has been discussed earlier in the thread, but I don't know if it's Kimhi's way or equivalent, and that's to deny that ~p is a component of an intensional complex like "A thinks ~p", and construe this instead as "A thinks-not p" or "A denies p".
That would be a pretty Fregean move, like saying "A is" is not a component of "A is red."
Let's go back to my statement (1). To say it, all Frege needs to do is put a judgment stroke in front of it. Does this mean that Frege is the subject, in the sense of "the one who is acknowledging the objective truth"? Is this really what he means? Or is it closer to a Kantian transcendental subject? I'm trying to imagine Frege replying, "Yes, every proposition I've prefixed with a judgment stroke is one I know to be true." Wouldn't he be more likely to say, "These are for purposes of example"? But now we're back to purported or believed or proposed truths.
If I've missed a specific bit in Rombout 2.2.2. that addresses this, I'd be happy to have the reference, but even happier to hear your thoughts about it.
Well, I am really looking for any kind of "bigger picture." Kimhi's bigger picture, J's bigger picture, or philosophy's bigger picture - in that order. Understanding the book requires the first.
Quoting Srap Tasmaner
Okay.
Quoting Srap Tasmaner
Right, and Kimhi gets subtle here in saying that they co-implicate each other even though p has a primacy over ~p.
Quoting Srap Tasmaner
I also forget Kimhi's exact position, but I know he considers such ideas. He is trying to get away from such atomic or compositionalist approaches, and if Boynton is right then Kimhi follows Frege in attributing "syncategorematicity" to the whole of a judgment, such that it becomes a single whole.
I have a thought about this, which almost made it in an earlier post.
Kimhi says that existence is conferred on propositions by the veridical use of 'to be', so that's judgment or assertion.
Frege wants propositions to be the object of thought, but he also wants them to have independent existence. It's almost as if he half accepts Kimhi's position, but then confers existence on his propositions in perpetuity by borrowing the veridical use of 'to be' and tacking it right onto the proposition. There! Fixed!
But this is worse than doing nothing in Kimhi's view because this is a complete sham. Propositions exist only in the judgments of thinkers; the veridical use of 'to be' no more stands *on its own* than propositions do, so you cannot just rip it from a thinker's mouth and solve the problem of the independence of propositions.
(This turns out to be the other side of my realization that Frege probably means 'judgment' in some strangely objective sense.)
Yeah I haven't gotten to that stuff yet.
It's painful reading. I know a lot of that is just me, that I'm out of practice, but I never felt so frustrated reading Dummett or Sellars, writers many people dislike. There's something disorganized about Kimhi's writing, that nothing he says makes sense on its own, without all of his other thoughts. But you can't say everything at once; as a writer you have to impose some structure, if not lemma-theorem-corollary, then at least something pedagogical, building it up. Wittgenstein struggled with this and found not one but two solutions! Kimhi doesn't seem to have.
Quoting Leontiskos
On page 17 I argued that Kimhi is too bound up in a Fregian paradigm to overcome Frege. The challenge for the anti-analytics is to make an argument that is both sound and coherent, for in opposing analytic philosophy one wishes to oppose the method and not merely the content, and given that the method of analytic philosophy is exceedingly clear, the anti-analytic is moved in the direction of obscurantism, seen most obviously in a thinker like Heidegger. They do not wish to engage analytic philosophy on its own terms. This is understandable, but it makes it harder for those of us on the ground to separate the wheat from the chaff.
I have only found thinkers who are deeper in history to be capable of overcoming modern antinomies, such as that between analytic and continental philosophy.
I consider the jury decidedly out on this.
Quoting Leontiskos
I don't know the contemporary landscape well, but I think the dominance of something recognizable as analytic philosophy was already slipping in the 70s and 80s. Rorty, Stanley Cavell, Annette Baier (I think also of the Pittsburgh crowd) and others seem distinctly post-analytic.
But Frege and Husserl, this is the last moment before the split. So if you want not to join one side or the other, you might go back to the most recent common ancestor. (Without just taking Kant for another spin.)
But I think it's pretty uncommon to see anyone who isn't doing ancient philosophy or Heidegger talk about "the unity of thinking and being". That's pretty out there, but again I don't know the scene well anymore.
That's true.
Quoting Srap Tasmaner
Well, yes, but that is one of the things that I find so odd about Kimhi: he reads Frege in a purely analytic direction. I am convinced that (a particular flavor of) Wittgenstein must be the key to understanding Kimhi's approach. When J was initially posting about Kimhi I wasn't recognizing that Wittgenstein is Kimhi's central source.
Yeah there are certainly hints, and that alone makes him an outlier these days.
I will revisit that section when I get a chance, but in this area there is an inherent danger. Kimhi is right to say that thinking is unique. It is also mysterious, and ineliminably so (in large part because it is unique). Frege's judgment-stroke reflects this mysterious nature of thinking. For example, as says, Frege wants to have it both ways. So does Kimhi when he says things such as, "It is both x and not-x." It seems that we are just bumping up against the mysteriousness of thinking.
The danger then is something like "mystery swapping." Kimhi wants to construe the mystery in a different way than Frege does. At such a point we need to be very clear about what constitutes a better construal or account of a mystery. When someone says something about a mystery it is very easy to contradict them, and much harder to say something profitable oneself. The question of a target enters again, because if we have no target about what constitutes a better mystery-account and what constitutes a worse mystery-account, then we are up a creek without a paddle. As Martin's paper bears out, it becomes very difficult to recognize the parameters that a suitable account of, say, the content-force distinction, will adhere to.
...along these same lines, I often opposed those in the thread who said, "Frege is just giving a model, so who cares if it's a bit off?" Of course he is not giving a model, but there is still truth in such an objection. I would phrase it as something like, "Frege did not give a perfect account of the mystery of thinking, but it is not a bad account, and in order to critique it we would need to get much clearer on what should be thought to constitute a better account."
Ahem.
Quoting Leontiskos
I absolutely think he is, even though he didn't think so. Newtonian mechanics? Pretty damn good model used appropriately, within certain limits, but its author thought it was Truth. And he was wrong. Doesn't matter what he thought he was doing, the model he left us is useful.
And so it is with Frege.
Btw, Timothy Williamson tells a story about explaining the Gettier cases to an economist, who was mystified by the importance philosophers attach to them. "So there are exceptions. So what? All models have exceptions." And Williamson -- who's been doing just fine in the current regime -- thought, maybe we really have been going about this wrong, and has become an advocate for at least incorporating the modeling mindset into philosophy.
Yes, that's the nub of the question I was raising with my statements (1) and (2).
Quoting Srap Tasmaner
And (1) tries to do just that, hence my question -- who here is thinking this? It goes back again to those provocative lines from Rodl about the "life of p":
Part of our unearned insouciance is this story we tell ourselves about how p can, of course, "stand on its own" in some obvious way.
Quoting Srap Tasmaner
If we decide that he's talking about actual rather than purported or exemplary judgments, then yes, the strange objectivity arises because he's committed to vouching for their truth. This connects with what Rombout speaks about when he says, "In order to judge, one really has to do something. Judging is not a capacity but an act."
OK, maybe I'm a bit previous here! Admittedly, we could be spending all the time we're spending on Kimhi because we want to figure out if he's got anything worth contributing, not because we already know he does. And as I was saying to @Leontiskos earlier, of course the jury is still out, we don't yet know what other 1st class philosophers are going to do with him. All I can say is, after a lot of years watching flavor-of-the-month philosophers come and go (ah, remember Paris fashions?), Kimhi feels like the real deal to me. We'll see . . .
Yes and no.
You've played with this stuff, right? You write down "P" and that means P is a premise; it's *treated as* true. In essence, all symbolic logic is hypothetical. You just see how things work out *given* certain premise and inference rules. (And natural deduction systems have additional ways of doing this.)
What I think is unavoidable is vouching for P as a truth-bearer, and for its availability. That is, that it is a proposition.
Quoting J
The book has been out what since 2018? I don't know how many articles have been updated since then, but he gets not a single mention on SEP. (I haven't checked his Google scholar or PhilPapers rankings.)
Isn't it because the world is supposed to stand on it's own, and true propositions are states of the world?
If you read a textbook on anatomy, you aren't supposed to think of it as being asserted by someone in particular. It's like das Man, except with the textbook it's the scientific establishment.
Both your responses allude to the difficulties I see here.
Quoting Srap Tasmaner
Right, and why would anyone question that? Except that Kimhi and perhaps Rodl (I don't know much about him, apart from the citations in Boynton) are saying, "Wait a minute, not so fast. Then what is the judgment stroke supposed to be doing? Does it import or ratify actual truth somehow? Who has acted thus upon p? What exactly would it have meant to 'treat something as true' without the judgment stroke?" Such annoying questions, but are we sure how we should answer?
Quoting frank
Indeed, and the use of p in a logic textbook isn't meant to invoke a real human subject doing the writing. But here again: Someone did write the anatomy textbook, and if it ever came to a question of accuracy, who that person was and the status of their ability to assert truthfully would be very much at issue. It's much worse with logic, because of the self-reflection involved. "Someone" is offering us statements and perhaps judgments that purport to be true, and they are about what purporting to be true is, in logic, which includes the vexing question of assertion. We want to say that this is "innocent" at the level of p, but does Frege's own understanding of what a proposition is, allow us to do so?
This may be where the uniqueness of thinking, a la Kimhi, starts to make itself felt. A thought simply cannot be separated from a thinker, on this view.
I'm not sure about any of this, but it's pretty clear that Kimhi wants us to question every assumption about how we're entitled to do logic -- even if we only wind up reinstating the assumptions.
Quoting Srap Tasmaner
OK. I assumed from the Martin and Conant cites that T&B is being taken seriously. Maybe not.
https://thephilosophyforum.com/discussion/comment/935118
Right. That's the first thing that occurred to me about it. Frege's propositions must reflect context of utterance. I was thinking there might be some sort of phantom assertion to it, something generally understood as with the textbook. "One observes...". instead of "she observed.."
When was the force stroke supposed to be used?
Ok, this might be informative. Firstly, there is a large body of literature for these issues, so it is not the case that these are ignored by logicians and others. Secondly, there are ways of dealing with these issues, indeed, many for each. It might be argued that there is no consensus, but why should there be? To think that there is one right way to deal with such things is to adopt logical monism, and there are good grounds not to do this.
Quoting Srap Tasmaner
Well, we don't. It's a confused notion. One response is also from Wittgenstein, and is close to Frege - that to understand (the content of) a statement is to understand what would be involved in it's being true as well as it's being false; to understand the difference between the cat being on the mat and the cat being on the lounge. There's a fair bit in the Tractatus on this, and it is one of the ideas carried into his later work.
Quoting Srap Tasmaner
That's not what I am asking. Sure, propositions are abstract, for some notion of "abstract". But what does it mean to say they exist? Following the usual analytic approach, we might ask the contrary question, "what could it mean for a proposition to not exist?". I hope you see this as problematic. And if this latter question is problematic, so is the former. We might do something analogous to Quine's "to be is to be the value of a bound variable", using a second-order logic ranging over propositions, and here it might be clear what it is for a proposition to exist, but that does not seem to be the question being asked. And hence we might do well to approach the notion of propositions existing with some scepticism until it can be made clear what a non-existent proposition might be.
Last night turned into an early morning, so I am somewhat weary, and havn't been able to follow your point closely. But it seems you are pointing out that in order to say that snow is white, is the same as to say that schnee ist weiß, extensionaly, we would need the entire paraphernalia Tarski brings to his discussion of truth. We can't just take "schnee" and "snow" to meant he same thing; we have to show that they are extensionally equivalent, employing something along the lines of
...so that the metalanguage is talking about the same things as the object language. Where one arrives is at some variation of Convention T, that "schnee ist weiß" is true iff Snow is white.
Now it is not clear to me that we have made a judgement here as to whether snow is white, or even schnee ist weiß... Rather all we have succeeded in doing is setting out what would have to be the case for "schnee ist weiß" to be true. The judgement remains something further, something outside this logic.
Real life calls. I'll try to return to this later.
I don't think the "modeling mindset" is an improvement, and I think the main reason approaches like Frege's turn out to be useful is because they were intended to be more than just models. I was actually hoping that you were going to write your new thread on this topic.
But my point seems to stand intact:
Quoting Leontiskos
It sounds like it, but of course it would require more research into Frege to know for sure. Along the lines of my other response, realists arguing about the nature of knowable objective truths is a lot of inside baseball. Every theory is a bit unwieldy, if only because objective truth is unwieldy, and to adjudicate between them is a difficult task.
Quoting J
For me 18 pages with little to show testifies against Kimhi. We have produced very little fruit in the way of understanding his argument, and the prima facie conclusion now says that there is not much to be understood.
It is true that the tangents have been interesting. Working backwards, we have Pierre and fdrake attempting to show Banno why illocutionary force is different from assertoric force; then the point from Pierre about what precisely Frege might mean by the term proposition, etc. There have been a lot of forays into Kimhi where we attempted to strike for gold, but each one seems to have come up short. It will be interesting to see what @Srap Tasmaner makes of the book. I thought the thread was out of gas on page 11, but then @Pierre-Normand came in and breathed new life into it, particularly in providing Martin's paper.
For me the secondary sources were most interesting and informative, including Narboux's book review, Boynton's review, Novak's paper relating to the Parmenidean puzzles, Rombout's paper on the judgment-stroke, and Martin's paper on redrawing the force-content distinction. Threads could be made on any of these related topics, and I hope @Srap Tasmaner finishes the thread he began to write.
Regardless of Kimhi's merits, the thread and topic are interesting. Depending on your target, there may be others who are better archers. Martin gives a slew of folks who have worked on this exact same topic of Frege's force-content distinction, and I'm not sure that Kimhi engages any of them. Indeed, the way that Kimhi fails to engage the existing scholarship on the issues he pursues is part of the reason why my faith in him has flagged. If I had to give someone the ball of the OP to run with, it would certainly be Martin and not Kimhi.
Nowhere that I've noticed in Frege or Kimhi is there any recognition that ordinary people, who do most the thinking and asserting (and working and paying, and living and dying), also think about what they're doing, not from off to the side as philosophers, except maybe sometimes, but in the midst of doing it, because thinking about how you're speaking, for example, or how someone else is, whether they mean what they say, whether there's something else implied by what they say or the way they say it, whether you might be giving the wrong impression, all of this matters tremendously to understanding each other (or manipulating each other, etc). This kind of theorizing is not optional, but an important part of everyday thinking and talking.
And the kind of theorizing people do everyday is my kind, not Frege's or Kimhi's, and I would call it modelling because people know that most of what they think is only true "for the most part" or "usually" or "depending", and that you have to be willing to adapt and adjust, and the strategic choices we make in thought and speech and action don't have guaranteed results, just chances. My sort are for this kind of probabilistic modelling because it works.
There are a number of different issues at play in such a post. I think they are better fit for a new thread because they are topics of general interest. But to take one: must philosophy be accessible to the masses, or address issues that are "not optional"? I don't think so, but I can see why such philosophy is more interesting and appealing. Nevertheless, throughout the thread I have been asking about what larger implications Kimhi's thesis is supposed to have, and I assumed that this matter of 'relevance' was going to come up. "Kimhi's critique is important/relevant because..." I certainly grant you that the thread has remained very abstract and remote from considerations of relevance. That's a fair point.
Quoting Srap Tasmaner
So are Kimhi and Frege then opposed to partial truths, or do they think that it is inappropriate to be willing to adapt and adjust, or that all of our strategic choices have guaranteed results? I don't see why one would say that. But I am not yet convinced that the two do not intersect. If Kimhi or Frege are correct then everyday theorizing is bound up in their account.
Curiously, my friend who teaches high school philosophy was complaining about Aristotle's logic in the same sort of way, and I tried to explain that Aristotle's logic is very flexible and broad, and is even meant to include reasoning based on such caveats (e.g. in the Rhetoric Aristotle explicitly speaks about the way logical forms interact with non-"deductive" kinds of argument). ...But that's a tangent of a tangent. :grin:
I guess the response here is that Frege and Kimhi are interested in speculative knowledge, not practical knowledge, and classically speculative knowledge is thought to undergird practical knowledge. On this classical account we never carry out practical activities without also engaging in speculative knowing. For example, if you want to eat an orange you must first be able to recognize it and see that it is edible, nutritious, desirable, etc. If you can't possess that kind of knowledge about it then the question of eating it will never come up.
I actually thought it was you who was talking about the way that these more complex social-practical assessments presuppose the building blocks of assertion (or really assent), but maybe it was someone else? For example, one cannot lie before they know how to assert.
Let's leave it.
There was a point there that was intended to be near the subject of the thread. If it gets close enough, I might bring it up again.
"It is often felt that there is some conflict between the sense in which sentence-meaning is primary and semantic atomism. The most concise refutation of this which I know is Quine's ("Russell's Ontological Development," in Bertrand RusselI, Philosopher of the Century, ed. R. Shoenman, London, 1967, p. 306): "The unit of communication is the sentence and not the word. This point of semantical theory was long obscured by the undeniable primacy, in one respect, of words. Sentences being limitless in number and words limited, we necessarily understand most sentences by construction from antecedently familiar words. Actually there is no conflict here. We can allow the sentences a monopoly of full 'meaning' in some sense, without denying that the meaning must be worked out. Then we can say that knowing words is knowing how to work out the meanings of sentences containing them. Dictionary definitions of words are mere clauses in a recursive definition of the meanings of sentences."
By "dealt with" do you mean "resolved"? Surely not. If you only mean "recognized and discussed," then Kimhi, for one, would be the first to insist on this.
Quoting schopenhauer1
I want to understand this, but can't quite. Could you elaborate? I would have thought that psychology strutures the world so that A is not ~A.
This is fine, as long as we expand what a "sentence" is to include ostensive gestures and other "non-linguistic sentences." Anyone who's watched a toddler learn words, knows that it starts with an adult pointing to the target and then saying the word. But I'm happy to consider the pointing as a sentence of sorts: "That's a ball!" Indeed, such a sentence is often uttered along with the pointing.
Quine believed in semantic holism, right?
Kimhi says that the proposition "The orange is good to eat" has existence conferred upon it by someone affirming or denying that the orange is good to eat.
That seems to leave knowledge in a somewhat precarious position. "The orange is good to eat" needs to be available as a proposition that can be known, but on the hylomorphic reading I have suggested, it is only available in a judgment that the orange is good to eat (or not), as "what is asserted," the content of the judgment. But then you would have to judge that things stand thus-and-so (or don't) even to be capable of knowing that they do or don't. Sounds like a cart and horse situation.
All of the propositional attitudes will face this problem if there are, as Kimhi says explicitly, no forceless truth-bearers.
This problem remains even if we make some obvious improvements to my reading. When Kimhi says "conferred" there is some ambiguity. You could think of a judgment as an event, and "what is thought" as persisting only for the duration of the event.
But we often use such locutions in the past tense -- "what Frege thought," "what Kimhi said." That suggests that "conferring existence" might have some staying power, so thinking, judging, or saying P brings it into existence --- and leaves it there, for others to think and judge and say. I get to say that what Frege said is right or wrong.
If that's so, Kimhi might be offering an interesting philosophical just-so story about where propositions come from, assigning priority to judgment over wondering, wishing believing, hoping, guessing, knowing, doubting, and so on.
Except that he explicitly says that P does not persist as a truth-bearer with no force, and that seems to deny its availability for being governed by the other propositional attitudes that might come along.
But does it? Or does it only say that propositions *only* appear governed by a propositional attitude? If I wonder whether P, there's P as "what I wonder". If I guess that P, there's P as " what I guess."
What propositions never do is just hang out bearing truth or not.
So Kimhi is an anti-realist.
The bolded.
Quoting J
Sorry yes, that's what I meant :). Thus.. the rest follows here:
Reality and illusion is at the heart of much of early philosophy. Analytics seem to just want to clarify the phenomenal reality and to do so, want to provide basic rules to communicate what our psychology tells us. The minute you don't ascribe it to psychology, you are making a METAPHYSICAL claim and not an epistemological one. Schopenhauer had four volumes on his metaphysical claims. Platonists/Neoplatonists also had such writings. There is generally a lack of such claims in linguistically-based analytic philosophy. The problem I see here is that the metaphysics has been detached from the claims. Perhaps Kimhi is decrying this.
Edit: Furthermore, Kimhi may also be alluding to various forms of computationalism. That is to say, there might be a sort of fundamental "mentalese" underlying language. Logic is an extension of this perhaps, and thus the assertion stroke makes it seem as if written logic is separate from the "mentalese logic" of the human mind. I don't see the problem with this gripe though. Mentalese would have to be understood through various linguistic analysis, cognitive psychological studies, and such, and would be very hard to actually determine. I would imagine we would have to consult various studies on how we inference, integrate new concepts, calculate, process, and the like. But none of that to me matters to the assertion itself regarding a fact of the world.
I can't help but wonder if you are reading things into Kimhi with this "proposition skepticism." To take one example, where does Kimhi say that, "the proposition [...] has existence conferred upon it by someone affirming or denying [it]"?
Quoting Srap Tasmaner
As I read him, Kimhi is saying that if we strip away the assertoric force from a proposition, then it will not be true, false, or even meaningful. His argument is very similar to Wittgenstein's argument that Rombout presents in 4.3.1. In fact it is almost identical except for a mild upgrade.
Imagine someone saying something like this about numbers:
"What numbers never do is just hang out quantifying trees."
How would you respond to that?
Thought I had quoted it somewhere, but no. I'm away from the book, but it's early, coming off the discussion of the veridical sense of 'to be' and into the syllogisms of thinking and being. I take the veridical use of 'to be' to be 'assertoric force'.
Here are some places where you got close:
Quoting Kimhi, Thinking and Being, 9
Quoting Srap Tasmaner
-
Quoting Srap Tasmaner
Yes, and this is where it gets tricky. For example:
Without wading into this too far, the word "displays" is doing a lot of work here. So we can say that this veridical sense of the verb pertains to assertoric force, but at least here Kimhi is not saying anything about assertions ("self-identifying displays") or people making those assertions. (See section 2.5 regarding "displays")
Yeah I did quote that. Thought so.
I'll take a look at displays.
But unless you're reading "use" creatively, he does say what I said he did.
I don't see it.
One can oppose Frege/Geach without adopting the consequence. I think there is more than one reason why, but in general it is key to understand that Kimhi is making a distinction, not taking the surface-level contrary position. Specifically, he is saying that assertoric force is not limited to assertions. It is also present in what we have called declarative sentences. It's not that propositions have no existence (apart from assertions). It's that their existence is bound up with assertoric force, and is not separable from it. ...Unless he goes farther than that and actually takes up "proposition skepticism," but I don't think such a thing is in evidence early in the book.
(Like Wittgenstein, Kimhi seems to take care in what he doesn't say, and one wishes he had been bolder and said more.)
(One can see here why @J came under the impression that a non-assertoric force was in play, with the help of Banno; and why @Banno wanted to push assertoric force and illocutionary force together.)
Huh.
Well, I'm not about to claim his writing is crystal clear on this point.
What do you make of his use of the word "existence" in the first quote?
I suppose "allowed them to construe" is ambiguous. I took it as a rhetorical denial of the claim that truth-bearers have some existence besides what is conferred upon them by judgment. Do you read that differently?
- Kimhi refers to TLP 4.063 at least three times in his book, and that is the key to understanding these sorts of claims. Rombout looks at that exact passage in greater context:
Quoting Leontiskos
-
Quoting Srap Tasmaner
Yes, I would replace "judgment" with "assertoric force," and this has to do with Kimhi's distinction between an assertion and something which merely displays assertoric force. Once that is in place "conferral" takes on a different sense, for then the verb and not the speaker is what confers on the proposition its existence and nature or meaning. In my own words: the integrity of a proposition is bound up with assertoric force and the veridical use/sense of the verb.
"Existence" feels clumsy in that sentence, but Kimhi may be trying to speak in more general terms in this introductory part of his book. But I don't want to get bogged down in this one sentence. I am interpreting that footnote in relation to later context, and in particular, "Frege's Point."
(Sorry - I edited these posts about a million times)
Do you mean that we (or some philosophers) are making claims about metaphysics without realizing that they are in fact only claims, from someone's point of view -- thoughts, in other words? I can sort of see how this might connect to Kimhi's insistence on uniting what he calls the ontological and psychological explanations of logic. He doesn't think the "detachment" can happen at all.
I see the edits now.
Quoting Leontiskos
Then it does turn on what is understood by "use". Is there a real sense in which a word is just there in a sentence -- and thus "used" in it -- without someone "using" it in a sentence? What can a verb do on its own?
"Display" something seems to be the answer -- and I will look into that -- but there's another way to take that too, that this only means it is by this use of this verb that one indicates or expresses or shows forth or even represents their judgment that ...
Does a Fregean formula like "Fa" display the independent existence of a thought or a state of affairs? Or is it a judgment?
I was hoping this would help, "In my own words: the integrity of a proposition is bound up with assertoric force and the veridical use/sense of the verb."
My sense is that Kimhi thinks there is a veridical use of the verb and also a non-veridical use of the verb, and here he wants to talk about the veridical use of the verb. That doesn't entirely solve the puzzle, but I'm not sure this single sentence can bear the scrutiny we are applying.
My read is that at this early stage in the book Kimhi is attempting to distance himself from what will eventually become "Frege's Point," but without yet saying anything overly specific.
Quoting Srap Tasmaner
For Frege Fa prefixed by the "horizontal" represents an assertable proposition, a thought. It is not a judgment.
For Kimhi Frege's Fa displays assertoric force and therefore is not independent of it. It is not a judgment, but "displays" one. As I said earlier in the thread, I am not convinced that Frege would disagree with such claims. There is a possible equivocation on "assertoric force."
As to the question of the ontological status of a proposition, I don't find Kimhi taking a stand one way or another, and although I am told that Frege is a Platonist on this issue I haven't read him myself to know the specifics. I don't know that this question of the ontological status of a proposition is central to Kimhi's case, but it may come in later on in the book. And it could be argued to be central in one way or another. I just don't see Kimhi attending to it.
Fair. The thing about existence surprised me, so I took it seriously.
I have been doing some dot-connecting and reading between the lines in these recent posts.
I think we do have a tendency to treat every word as a term of art, with a specific technical meaning. Hence I have been treating as equivalent 'assertoric force', 'judgment', and 'assertion'.
Until I'm convinced Kimhi means these consistently differently.
(The man will put in parentheses "a thought, a sentence, a state-of-affairs", so that's not an invitation to split hairs or take these all in distinct technical senses, at least not for his point.)
Quoting Leontiskos
This is starting to get hair-splitty, but yes, I would still say that an "assertoric force not limited to assertions" is either incoherent or, in some sense or manifestation, also non-assertoric. But the nomenclature doesn't matter so much. Better terms could have been chosen, starting with Kimhi himself.
The problem is, thats not all Kimhi says about what the veridical to-be does. Maybe this is only Kimhi's reading of Kahn, but he says in the footnote on p. 9 that the V2B is what "confers existence" on "that which is true/false or is/is-not the case". The Analytics, he says, want to believe that the force/content distinction allows them to regard propositional content independently of the veridical. But the explanatory parentheses about what's covered by the V2B is alarming: "(e.g., a thought, a sentence, a state of affairs)". So its not just that, as you say, existence is conferred on propositions by the V2B. Evidently, the V2B makes no distinction between a psychological event (thought), a statement (sentence), and something non-linguistic in the world (a state of affairs). Even if Kimhi (or Kahn) is using "thought" in the Fregean sense of "proposition," this is still hard to swallow. How do you understand the V2Bs connection with states of affairs, which are generally considered to be the subjects of propositions, not the propositions themselves? Is this still a type of judgment or assertion?
If we were strictly talking about propositions, then I think this would be right.
I think what he's going for there with the "whatever is true/false, is/isn't" is every kind of theory out there about truth. Philosophers have tried all kinds of formulations, and placed the emphasis in different ways, but it's all about the same thing. Think of the ambiguity of the word "fact". True proposition? Or state of affairs that "obtains"? --- That last word there, that's typical philosophical shop talk, right? (Like "grasping".) No one knows what it means. No one defines it. But we all know what you're getting at. States of affairs (more shop talk) only show up as the counterpart of true propositions. It's all the same stuff.
Yes, that's basically it. If someone like Frege is saying, "The cat on the mat" is not just something that is an epistemological claim then it seems to be a metaphysical one. That is to say, which is it? Making an "assertion", either means someone "knows" something, or is describing "what IS the case" (more than one's psychological understanding of what's going on but what IS ACTUALLY going on). There is a whole set of assumptions that the audience would not be privy to simply by looking at symbolic logic. Frege, for example, if I read this right, was a sort of "Platonist" regarding propositions. So, that's a HUGE worldview that is not connected to the logic itself, and perhaps should be connected to indicate what we mean by the "assertion stroke".
If this is so, then Kimhi is using "proposition" for what others call an "assertion".
And his argument reduces to his inability to distinguish what the sentence is about from what is being done with it. He is claiming that one cannot understand what a statement is about without deciding if it is true or false.
And here he is just wrong.
We can understand what it would take for a statement to be true or false, without assigning a judgement to the statement.
It would be interesting to ask him about how questions are to be understood. How does "Is that orange good to eat?" exist? Not by being affirmed or denied. How will he account for questions without admitting some alternative? How do questions differ from assertions in his account?
I had written a response to you that I then feared might not quite do justice to Quine's thesis of the indeterminacy of translation. I rephrased my response as a question that I submitted to ChatGPT o1-preview, who thought about it for seven seconds before providing an answer that undermined my attempt to cast Quine as a semantic internalist somewhat like Searle. ChatGPT also helpfully reminded me that Quine was more of a behaviorist (which, to be fair to Quine's opponents, still threatens the normativity of thought and language in a different way).
[hide]
Here is my question to ChatGPT:
"Quine famously said in Two Dogmas of Empiricism that "our statements about the external world face the tribunal of sense experience not individually but only as a corporate body". He had a problematic view of what episodes of facing this tribunal consist in, though. He tended to talk about physical stimulations of nerve endings as the locus of our cognitive contact with the world (in World and Object, for instance). Having thus relegated people inside of their heads, might his thesis of the indeterminacy of translation apply not only to the relationships between distinct public languages (e.g. English vs French) but also between the "idiolects" of each human being, thereby dissolving the very idea of a public language? That is, might not our languages become "private" in the sense Wittgenstein was arguing against? I understand that Quine's pragmatism intended to explain how language can be useful in spite of the indeterminacy of translation (and Davidson's idea of radical translation might be seen as an attempt, among other things, to salvage this Quinean insight). However, in a post-Quinean philosophical landscape, (after Sellars, Brandom and McDowell, for instance), might it not be possible to credit Quine with the good insight of meaning holism but disentangle this insight from the bad conception of the indeterminacy of translation between "private" languages? Or maybe I am misunderstanding the latter thesis."
And here is its response, which seems to me reasonably hallucination free.
[/hide]
Quoting Srap Tasmaner
I think this is a fine way to read Kimhi. As I recall he will consistently talk about displays of force/judgment/assertion and self-identifying displays of force/judgment/assertion. I find that way of speaking unhelpful. Without digressing, I sympathize with all of the things you're running into!
Quoting J
See:
Quoting Leontiskos
I suppose it would be more technically correct to say that, rather than there being a possible equivocation on "assertoric force," Kimhi's distinction occurs as display vs. self-identifying display (of assertoric force). But it is worth recognizing that Kimhi does not make use of a non-assertoric force.
As to @Banno's question about what assertoric force is, following the "Frege-Geach point" (Martin) or "Frege's observation" (Kimhi), assertoric force is the thing that separates an asserted proposition from an unasserted proposition.* Then the question comes: does that definition stand or are Kimhi, Martin, et al. tweaking it as they go? Again, Martin's paper is very helpful with regard to the OP.
* For example, in a modus tollens the antecedent of the conditional premise does not possess assertoric force, whereas the same 'p' in the second premise does possess assertoric force.
That was fascinating. The answer was that Quine would say I have a unique connection to the world, but I also mind-meld with my community so that my language isn't private.
If I can mind-meld with my community, why can't I mind-meld with individual people? Or maybe it's that there is an innate primal language from which all languages emerge?
Food for thought. Thanks!
(Note too that Martin uses the same language of "declarative sentences" vs. "assertions" that Srap and I developed earlier in the thread. This is much better than "displays" vs. "self-identifying displays.")
and spoke to this, but the problem with phrasing it that way is that it closes the question that is supposed to remain open. The question is, "Is it possible to detach the assertoric force from an assertion and still be left with an intelligible declarative sentence?" The illocutionary force approachwhich I am not overly familiar withpresupposes that you can remove the force and be left with an intelligible sentence. And presumably everyone is in agreement that you can remove the illocutionary force, without being in agreement on whether you can remove the assertoric force, which in itself shows that the two are different. Illocutionary force is apparently meant to be something superadded, whereas critics of Frege think that assertoric force is not superadded in the way that Frege supposed.*
The question is subtle. It asks whether an (unasserted) declarative sentence has some kind of latent or dormant assertoric force which is inseparable from the sentence itself. Presumably no one is wondering if sentences have latent or dormant illocutionary force.
* And I suppose it is crucial to note that Frege's distinction between assertoric force and predicate was not intended to be merely stipulative. He thought he was saying something that was both true and previously unattended to. He thought that his recognition of the clean separability of the two, via the judgment-stroke, was an advance. For example, see his quote <here>.
Could that be becasue the question is muddled?
Quoting Leontiskos
Not everyone. Very few, I suspect. To remove the "assertoric force" is to remove whatever it is that makes a declaration into an assertion. And that is what the illocutionary force of does.
Quoting Leontiskos
Indeed. To the point of invisibility.
Let's consider your cat, and the mat he is sometimes on.
How did you learn he was a cat? Or that what lounges upon is a mat?
Perhaps someone pointed at him, or a picture of one of his brethren, and said "cat" or "This is a cat", and did something similar for the mat.
To explain the preposition, a picture (or a reality) of the cat on the mat, accompanied by the sentence "The cat is on the mat" would be typical. (The finest treatise on English prepositions I know is Go Dog. Go!. It sounds like it will be primarily about verbs, but it devotes considerable attention to prepositions. Interestingly, many of the "captions" dispense with the copula, and just say "A blue dog on a red tree," or "A dog out of a car," like so.)
Now it's true that even if no one ever taught you, in so many words, "an apple in the mailbox" or "An apple is in the mailbox", you can still understand what would be going on if that were so.
But you can imagine learning English without anyone ever having resorted to veridical descriptions of the situation shown in a picture or plainly visible to you?
Could you substitute "imagine a cat" for the demonstration with the picture or with the cat?
Sure. Could be.
Martin racks up a lot of different folks who have claimed that there is something wrong with the way Frege separates out assertoric force, and if I have time I may read his paper more carefully to get a better feel for the nature and gravity of the difficulty. Wittgenstein was obviously one of them.
---
Quoting Srap Tasmaner
This is close to Newman's distinction between real and notional assent.
So what is the force in assertoric force? Is what you are claiming that the assertoric force is how "The cat" denotes the cat? Than it's about denotation, and fine. But that's not 's "some kind of latent or dormant assertoric force which is inseparable from the sentence itself." It's picking stuff out.
I don't think the notion of assertoric force is clear enough to be understood, if it is something different from denotation or illocutionary force.
For Frege, isn't it about the "judgement of a statement as true".
"It is true that the sky is blue" would be an example of something with assertoric force.
Assertion does NOT equal denotation.. "The cat" is a reference to something "in the world".
All of this goes back to various things I've asked earlier and no one cared to pick up (i.e. the nature of "truth", how it is related to the judgement of a sentence, metaphysics and epistemology, and all that).
Edit: For Frege, for example, it is good to know he is a Platonist about propositions metaphysically. It is good to know how he viewed epistemology in how we can judge a proposition as true, etc. etc. It would be even better if we knew how he connected reference to words (thoughts?).
But at first -- and what I was pointing out -- there's a lot of someone else using it, and using it in, so far as I can tell, in one particular way. It's hard even to imagine an alternative.
(Interestingly, there's been some work on how this continues as the child gains competence. By 3 or 4 or 5, depending on who you ask, children distinguish between an adult expressing a personal view and an adult speaking pedagogically, speaking for their community.)
For Austin, assertions are one specific kind of illocutionary acts. When one utters the the sentence "p" with assertoric force, they thereby also perform a locutionary act that may be likened to presenting the content of the utterance. So, Austin also has available to him a notion of the content of an utterance with the force removed (or abstracted away) from it. One significant difference between Frege and Austin, though, is that Austin conceives of illocutionary speech acts (such as assertion) primarily within a speaker-hearer framework. Judging that p (e.g. through making up one's mind that p is the case), or asserting it out loud while, unbeknownst to one, nobody is there to hear and understand the claim being made, would need to be understood derivatively from the primary case where a move has been made in a language game. I view this as a virtue of Austin's pragmatic account of language since it secures its connection to the public norms governing the use of a language and to the pragmatic significance of our language games.
This is just an application of the classical analytic "What do you mean by..."; but is there a satisfactory answer?
Quoting schopenhauer1
And of the illocution of making an assertion. So how does assertoric force differ from the illocution of making an assertion?
Illocution is the intent behind the statement. "The sky is blue" might be intended as a poem, a riddle, a question, etc. It may be an assertion, but not necessarily.
Assertoric force would be one that is a type of illocution relating to the judgement of a statement being true.
The SEP says this about Frege's view of assertion:
" It is in the force of an utterance that the step is taken from the content to the actual point of evaluation. This view has been stated by Recanati with respect to the actual world:
"[ ] a content is not enough; we need to connect that content with the actual world, via the assertive force of the utterance, in virtue of which the content is presented as characterizing that world. (Recanati 2007:". here
The act of assertion pins down the meaning of a thought so it becomes truth-apt. How do we know which cat is supposed to be in the mat? We need context. The context is revealed in the time and place of the assertion. It's about indexing. That's what I've been assuming anyway.
Well, obviously I don't know. If I knew, I wouldn't still be trying to figure it out.
Think about the peculiarity of being taught the word "cat". When mom says "This is a cat," would you describe that as her telling the little one it's a cat? Kinda. But don't you have to already know what a cat is, to find out that something is a cat? And for a similar reason, it wouldn't make sense to describe mom as claiming that it's a cat. What could that mean to the little guy?
Anyway here's these sentences people use, that look kinda illocutionary, kinda assertoric, but aren't quite that. Austin doesn't have a category for these, does he? Maybe "instructives." That's a pity. I can't help but wonder what he would say.
And it's a curious fact that these peculiar utterances constitute a lot of how we learn language, and how we learn to learn more, and when it's our turn we talk the same way to teach new little ones.
And the connection to the topic is that these sentences, and sentence substitutes (which I'm disinclined to call elliptical sentences, but maybe they are), don't just have a certain form; they have to be veridical.
I don't know if it's any help. But it's curious that this is how we transmit our linguistic knowledge to the next generation.
This is a related analogy, but is not exactly what is going on in the thread. Kimhi's forces aren't quite illocutionary forces, we're not talking about speech act theory, by my reckoning we're closer to talking about logic - like a natural language Conceptual Notation but written in natural language. A formal kinematics of thought in its relation to the world. Treat this as an invitation to engage with the thread topic on its own terms. I also don't know precisely what the forces are, I'm just opening another door for them.
I think the muddle between force in thread and illocutionary forces comes down to never seeing a free floating proposition out in the wild. The proposition is largely a philosophical construct you get from distilling sentences down to what makes them true or false. You then call this the propositional content of the sentence. You take inspiration from declarative sentences and apply it to non-declarative uses of language.
To do that distillation in the latter case, you first neglect the use case. You find the content first. You then "analyse" the use back in by notionally associating some force to the propositional content. And finally present an IRL speech act as a pair {illocutionary force, propositional content}, and that's the end of the analysis. Finally the couple {illocutionary force, propositional content} is notionally equated to the analysed speech act, and they're treated as equivalent.
If you want to use this style of analysis, and see the thread through its terms entirely, you're going to remain confused. Since traditionally if you write down an argument like "if p then q, p, therefore q", you're definitely not thought of asserting p in the first conditional, and you're almost certainly not thought of asserting p in the quoted argument[hide=*](its writer is at best stipulating it, but there's no stipulation operation in the language, you don't say "I stipulate", you just write down p)[/hide]. You can look at logic as a flow control system for propositional content to other propositional content, and never have to care about force at all when you're just shunting about the symbols. [hide=**](Though Frege cared about force and judgement it seems, so the more formalist presentation I've made here is also inaccurate!)[/hide]
Except it behaves like a model and a guide for IRL reasoning, argument and thought, and when you write down logical operations (and syllogisms) on propositional symbols, they mimic assertions, rejections, stipulations etc. Even ones you make in your own head. Which is a bit odd when you think about it, since you're supposed to be dealing with things that have no forces... but there they are in the logic.
You could also notice that when you're playing around with propositions in logic, no one needs to actually assert them or reject them for the logic to work. So you end up with a system of symbols that apes and embodies speech acts of assertion and rejection, with formal connection rules that ape conclusion and consequences and inference, that allegedly has nothing to do with the forces associated with conclusion, inference, affirmation, rejection and so on. Which itself suggests that notionally manipulating these things behaves like a real argument, no? Forces and all? Right down to the level of the propositional symbol?
That should really give us some pause about the adequacy of the distillation procedure. Our real life use cases bled through into how we interpret the complexes and single propositions in the logic. They're also designed to guide and reflect how we think.
Consider:
p=>q,
~q
------
~p
vs
Alice) "We're getting cheese at the shop!"
Bob) "We're not going shopping"
Alice)"Then we won't get cheese"
You can maybe imagine the translation exercise between the latter and the former as two way. The assertions in the latter map onto the propositions in the former. Even introducing p=>q or p onto a line plays into that - you introduce a p, you stipulate it somehow, you assert it.
-
- Really loved that post. Among other things, it puts flesh on my Humpty-Dumpty quip.
---
Quoting Banno
I think illocutionary force maps fairly closely to the basic definition I gave, but the sentence that followed is important, "Then the question comes: does that definition stand or are Kimhi, Martin, et al. tweaking it as they go?" Or in other words, Frege might see assertoric force as an illocutionary force, but I don't think Kimhi would, because for Kimhi the force comes from the sentence and not just from the speaker.
I think the elephant in the room for @Banno is Kimhi's reliance on Wittgenstein. If Kimhi's critique is vacuous, then was the critique of Wittgenstein upon which it is built also vacuous?
Quoting Rombout quoting Wittgenstein, 60
(The bolded quote is what Kimhi comes back to again and again in his book.)
Is early Wittgenstein as confused as Kimhi?
(See also Martin's section on Wittgenstein, beginning on page 190.)
---
Quoting Banno
Maybe we could say that assertoric force is that in virtue of which an assertion is realized, qua assertion. For Frege this consists only in judgment or the judgment-stroke. For others it also includes the inherent capacity of the declarative sentence to assert, which is bound up in the meaning and shape of the sentence. In presenting a determinate (truth)-option a declarative sentence has already asserted itself into a kind of possibility space, if that makes any sense.
(Note that this isn't the way Kimhi would describe it, but I think it may work as a gloss on Kimhi.)
Of course for Martin the crux is to map the force-content distinction, such that assertoric force is the complement to logical content. For Martin it is about a relation between the two.
Yeah, agreed, but it covers much the same territory. Instead of talking of illocutionary force we might talk of propositional attitude. What's at issue is the supposed difference between an attitude towards a proposition and an attitude within a proposition; Kimhi, on the accounts given here, thinks there is an force that is somehow a part of the content of the proposition, and not of what is being done with it.
But even that is unclear, and depends on which of the various versions one listens to.
My purpose here has simply been to set out how illocutionary force, propositional content, and propositional attitudes are usually seen, in the hope that it provides some background against which @J or someone might set out the issue.
As for engaging with the thread topic on its own terms, I don't see that those terms have been established to anyone's satisfaction.
J explains it pretty well in the OP.
p is the proposition that the sun rises in the east
q is the proposition that I will see the sun above my barn
If p, then q.
Frege was saying that the above propositions haven't ever been asserted. His focus is on how one thought follows another, and thoughts which have never been asserted abound in the processing of the mind.
Kimhe says this way of thinking about propositions disconnects thought from the world as if there's some inner sanctum where they dance around isolated from the world of time and space.
He says that the act of assertion, which pins the meaning of a proposition down to the actual world, is secretly there: "smuggled in.".
To me, this is kind of blatantly obvious. This is part and parcel of what a proposition is.
Queue my point :D.
The key is that a declarative sentence is an assertion secundum quid, a kind of privative reality. In 's language, it is not "in the wild." It is in some sense artificial or contrived. But if you want to see someone who is waist-deep in non-assertoric forces, check out Martin's paper. :grin:
Martin demonstrates by example how difficult this project is, beginning especially with section 4 of his paper. None of us have really been willing to shift into first gear and get into it in the way that he does, and for good reason. It is not at all clear that the river in question is swimmable, and presumably that is why everyone (including Kimhi, but especially Banno) keeps such a distance from the water. Martin does a great service in leading the way by diving in and swimming. Even if he doesn't make it, others will learn by his example.
An example of this is 204 where Martin examines ¬p and argues that, "Deviating from what Frege thought (cf. N: 355356), negation amounts at the same time to a logical force of its own." He will end up saying that unlike a positive judgment, a negative judgment or negation has a negative logical force that is non-assertoric. Be warned that Martin is using words with more precision than Kimhi, such as the word "thought."
The merit of this sort of inquiry is reflected in what fdrake said:
Quoting fdrake
Martin shows that there are forces in the logic itself, and that logic is not separable from a process of temporal human acts. How we ever managed to lose sight of such an obvious fact is a mystery to me, but clearly the reminder is salutary.
To make this a bit more apprehensible, some of us may remember Michael's recent project of denying that promises exist by denying that one can bind themselves to a future course [hide="*"](e.g. here)[/hide]. Martin shows that logic and assertion have everything to do with binding oneself to a future course, according to true constraints such as the principle of non-contradiction. This makes sense to me, and it makes sense that we live in a world where promises and syllogisms are dying the same death. We have somehow managed to forget that the machinery we have created requires human subjects carrying out human acts, whether that machinery is logic or the banking system.
(Out for a few days)
That's not what he was saying.
Some of the issues you raise I'm partial to because I have tried to raise them as well! I'm going to attempt a similar overview with a different emphasis, and try to show the relevance of my recent posts. All at once! (And I'll try to be a little less cagey.)
1. Can force be separated from content?
Yes. It's the whole point of logic, and until proven otherwise, it is clearly successful at doing so. If Frege didn't think so, he was confused.
2. When you separate force from content, have you shown that everyday speech has (at least) two components?
No. In the sense of "not necessarily."
I believe it is perfectly coherent to claim that making this distinction is a strategy employed not only by philosophers, sometimes with the intent to do logical analysis, but by ordinary speakers of a language in the course of their day.
Logic is that strategy deployed wholesale, rather than ad hoc for particular, often exigent, purposes.
3. What does it take to separate force from content?
Depending on how you take the question, the answer is many thousands of years, or a few years.
It is perfectly clear that there's something small children understand before content, if for no other reason than that they are born without a lexicon. There is also a longish period when they understand speech they cannot quite produce, and this includes a babbling period, when children practice making what Frost called "sentence sounds". You can hear young toddlers having entire pretend conversations that just happen to lack distinct words.
But words do come. There's even some research that purports to show that dogs recognize some individual words and do not just respond to tone of voice.
Words and then sentences arrive for children in a world that already includes tone of some kind, though it's not perfectly clear this is the same thing as force, and I assume something similar is true of human history.
And I think the way we teach children words probably bears some resemblance to the initial steps of language for humankind. Simple descriptions, simple reports, little if any grammar. (I think Strawson somewhere speculated that the initial step would be "feature identifying" in this sort of impersonal way that persists in idioms like "It's raining". "It's tiger-ish here," "It's Mom-ing here," that sort of thing.)
And force? Some kinds of force are clearly, I think, a bit more recherche than others. Toddlers don't understand irony, and it takes a while to be clear on what an imperative is! People aren't born knowing that certain ways of talking to you mean you have to do something, while telling you what. People aren't born knowing they're expected to answer questions, and just staring or repeating your desire (that one comes so early) for juice seems reasonable.
So what do we start with? There's clearly something that would later count as declarative in how we teach children, and in what I assume is early speech. Is that a force? A proto-force? Does it make sense to call it a particular force if there are no others to distinguish it from? Just as interesting as the question of how we first spoke is how we first asked questions, or tried to give commands, or expressed wishes for the future.
Sophisticated stuff, which appears to require a pretty robust linguistic foundation to get started. And we have to be careful not to assume that's already in place when considering how that foundation is laid.
It is not yet clear to me that force, in its many varieties, is foundational, rather than an elaboration.
Contra my first claim ...
Quoting Leontiskos
I guess I'll have to have a look at that.
Just speculatin'.
One point I think I left out: everything to do with language use has to be learnable, and it has to be usable even with only partial mastery. One of the things in my mind as I wrote that was, how do children learn force in all its variety? (Related to what I did mention, in human history.) There are some well known steps in concept acquisition, for example, but I don't know the research on force (although I think the point I made earlier about pedagogical force fits here).
I also didn't come right out and say that the way logic handles language and the way we do when teaching children has a sort of family resemblance, and that's the other reason I was thinking about it. Not sure where that leads, if anywhere.
Yes, understood. But you do know what "the sun rises in the east" is about, as much as "the sun rises in the north" or "the sun does not rise". These are not disconnected from the world, isolated from time and space.
Forgot to point out that I agree, and "can" there is the point I've been making, that it's a choice, a strategy. Trump has this indirect sort of Mafia speech style, so the literal meaning of what he says is at odds with the message he is clearly sending. We don't have to be taken in by this, treating the literal content as the more genuine, more fundamental aspect of speech. When we do that for logical analysis, it's a choice.
You're providing the sentences involved with that connection, though. You do this by providing context, although in this case I'm guessing it's fictional.
Well, yes. What of it?
We have the propositional content and we have the propositional attitude. Folk here say Kimhi thinks there is a "force" not captured by either of these. I'm asking what that force is.
Quoting frank
Secretly in the content? But you understand what "the sun rises in the south" is about, without asserting it's truth. If all that he means is that to understand "the sun rises in the south" is to understand what would be the case for it to be true or false, then yes, I agree.
I develop propositional attitude by analyzing the context of utterance, specifically in the case of an assertion. It occurred to me all of the sudden that we may not all be the same in this. It may be that habits that I have to use to understand propositions aren't necessary for you. I've been assuming you're doing the same thing I am, but you're just not as conscious of it. Maybe that's bullshit. Ha! :grin:
From my first post
Quoting Banno
I get that. In terms of propositions, we could say it works this way:
p is the proposition that the grass is green. The part that follows the word that is the proposition. It is not a sentence nor an utterance. It's a truthbearer. It's an abstract object. This proposition can be expressed by the utterance of a sentence. An utterance is usually marks or sounds. A sentence is a grammatically correct string of words.
The questioner has asked if it is true that the grass is green. She asked if it is true that p.
The answer that came to the questioner was that p is true.
The command doesn't contain a proposition.
Well, yes... that was kinda the point. The grass will be green in the case in which being green is satisfied by grass. It's a conditional, and hence "grass is green" is not asserted.
Truth is defined in terms of satisfaction, and hence is not asserted.
The idea is that for a command to be obeyed, the person to whom the command is addressed must see to it (by their actions) that the truth conditions of the proposition that (allegedly) figures as the content of the command are fulfilled. In other words, they must see to it that p.
They have to make p true. I see.
The same for "Is the grass green?". But consider "What colour is the grass?" where part of the propositional content is missing...
I see what you're saying. The way I've been thinking of it is that to understand p, I have to know what it would mean for it to be true. The way I do that is to imagine someone saying that p is true. I look at that setting. I suppose you don't need to do that. I don't really understand how you're doing it.
If you understand that, you understand what it would take to satisfy the proposition "grass is green".
Now we can add to that, "Grass is green" is true IFF grass is one of the things that satisfies "...is green". Adding truth is a step further.
Extensionally, that's all there is to understand in "Frank posts on PF". Of course, there are other things that can be said about both Frank and PF, many of which are interesting and informative, but they are by the by. Whatever else might be understood, "Frank posts on PF" just means Frank is on the list of PF-posters.
Nothing here about truth.
But we might add, if we want" "Frank posts on PF" is true IFF Frank is on the list of folk who post on PF. Now we are talking, not about Frank and PF so much as about the sentence "Frank posts on PF"
I think this is trivially true.
Well, it's trivial, yep. And it can give you an idea of what you are doing when you say something is "true" - you are talking about sentences, at least as much as about how things are.
Tarski?
Just to be sure, the reason I introduced talk of illocutionary force into the discussion was to give @J and others something by way of context against which they might develop whatever notion of force they see in Kimhi. I said explicitly that I would "go over my own understanding of the Fregean account and subsequent developments".
Seems to me that Frege's Judgment Stroke is a precursor to the subsequent work done in Oxbridge.
Sure. There are at least two places where something is done with a statement. The first is that somethings are spoken about, and not others - the statement denotes stuff, The second is to assert that the speaker holds something to be the case - the assertion.
Folk hereabouts seem to want a third "force", such that it is not a full illocutionary assertion yet more than a denotation. What I've been pressing is for them to set out explicitly what that might be. In my view no clear account has been given.
Quoting schopenhauer1
Extensionality. I understand that Frege spoke of the "course-of-values" for a variable - the list of values it might take. Tarski added the definition of truth as part of a metalanguage.
Perhaps it is worth pointing out that if one is going to assert that Frank posts on PF, one will need to set out that "Frank" denotes Frank and that "...posts on PF" denotes the list linked above. That is, one will need to set out the domain of discourse.
Since Newton, a force changes the movement of an object. We have a pretty clear notion of what that means. Someone can be forced to so something if their choices are restricted. That make sense, too. Someone can be a force for peace, in that they press in that direction.
"Illocutionary force" is what is different about question, statements, commands and so on; and that difference is what we do with those types of utterances. We do something different with a question to what we do with a statement or a command. Here again the word 'force" has some legitimacy, marking the act, the doing, the making it so.
"Assertoric force" makes sense in terms of Frege's Judgement Stroke, understood variously as "We know that..." or "It is true that..." prefixing and holding in its scope the whole of the subsequent expression, ensuring that multiple uses of the same term therein will be extensionally equivalent and so on.
If "assertoric force" is proposed to be understood as not an illocutionary force ranging over the subsequent expression, then it is up to the proposer to set out what it is that the force does that is different to the illocutionary force of asserting.
I'm not seeing that here.
I don't think I would know either..
Quoting Banno
The only thing I can think of is that "assertoric force" although a type of "illocutionary force" (the intention of the proposer is to assert something about the world), it is somehow conferred as something more important because unlike other illocutionary examples (like commands, questions, etc.), this one has to convey some sort of corresponding relationship to a state of affairs in the world. This kind of significance is not necessary for other kinds of illocutions. That's just one take. All other illocutions can be "true" in some sense, that is not about a state of affairs (though they can have that aspect too). This one by necessity MUST have a truth about a state of affairs.
Maybe it's the same as long as we narrow our focus to propositions in the Fregean sense.
But how does it differ?
We've talked at length about what a proposition is.
And with this I can only think of a few answers.. All probably detached from Kimhi...
1) That's Kimhi's point.. Assertion shouldn't be distinct from the other types..
2) That's Kimhi's point.. Assertion is more than just an illocutionary force, it is a deeply metaphysical thing.
It's like someone forked the repository of philosophical knowledge just after the publication of Wittgenstein's Tractatus, then merged in secondary literature in that heritage up to 2019. The set of problems and style of analysis is so obscure, but also so natural and pervasive. It looks at philosophy from an odd angle. But that makes philosophy appear as if looking at a circle from a side - a tiny strip in a space of possibilities.
I have tried a couple of times to present aspects of Kimhi's beef with the hole left by the neglect of the judgement stroke in logic in a new post. To portray the foreclosed future the abandonment of that problematic left. But I failed. I might try again once I've read more of the book.
Nice. It seems there is something going one here, then.
Yes, but I'm certain you won't like it. :lol:
Anyone still reading Kimhi might find this erratum useful.
I hope you say more about your thoughts on T&B as you progress through it.
When I began reading I was thinking, "Wow, this guy really takes the full context principle to the limit!" But after awhile it starts to feel like a collection of deferred explanations.
Quoting fdrake
Yes, haha.
Quoting fdrake
That is a more nuanced take than what we've been considering. I agree that the problematic of judgment cannot be abandoned. And maybe Frege primed the pump for its abandonment, but of course he himself did not abandon it.
---
@Banno - regarding illocutionary force:
Frege certainly thought so.
Quoting Srap Tasmaner
Yes, but I am not sure that in everyday language the content really stands apart from the force, at least in the sort of examples you have given. Something like, "The next town is like 70 miles," is rather different from what logicians do. Such a thing is implying via content, not truly separating force from content.
Quoting Srap Tasmaner
Walker Percy's writings on Helen Keller (and his own daughter) are interesting in this regard.
With that said, I don't know how much the experience of toddlers will bear on Kimhi's project.
---
Quoting J
It seems like you want to talk about symbols as stipulated signs. I'm not at all familiar with that usage, but I would question the idea that natural language is a set of stipulated signs. I think natural language and formal logic are very different in that way. I would say that the "true language of [stipulated signs]" is logic. This is why, for example, logic has no interest in philology (and also why philologists tend to be wiser than logicians).
---
Quoting Srap Tasmaner
Yep, fair. Teaching someone a language requires such separation, whether it be logic or natural language.
-
Quoting Srap Tasmaner
Don't get me started on the TPFers who want to talk about things they profess to have no interest/belief in. :grin: "Allow me put forth my thesis without any intellectual responsibility."
I just watched a bird land on a broken tree limb. It glided in to a spot less than foot from the tip, immediately trotted up to that furthest point, and then remained there for several moments looking around. The uttermost point on the branch was clearly its destination, but it got there not by aiming at it, which it was surely capable of doing, but by landing first at an easier spot and then making the short, easy trek there.
There's reason to think conversational language use is always like this, that we always say less than we mean and count on the audience to fill in "the rest," though whether that results in complete, self-contained propositions we both affirm or just another satisficing shortcut, that's hard to say. (Was this bird at the *exact* tip?) How often do we even try to understand each other "completely," whatever that might mean, and if such a thing is even possible, rather than enough to get along in a given situation? (Does a broken tree limb even have a well-defined tip? Did the bird care?)
One thing implicature suggests is that what the audience fills in can be pretty complicated, involving not just disambiguation and shared background knowledge but inference. It also goes with my other recent posts, in trying to suggest that force may not always fall into a neat taxonomy, and that even when some force is employed or conveyed it might still vary in its intensity. (A sentence can be a simple assertion about geography, but not intended to convey that information.) For example, the effect of an attempted cancellation of force by following something you've said with "Just kidding" is widely considered uncertain or partial. (When Moss is chickening out of the robbery he proposed to Aaronow, a whole spectrum of assertive force suddenly blossoms, from committing to considering to talking about it to speaking of it, "as an idea.")
Now, there was a lot of talk earlier in the thread about whether a sentence could display assertoric force without being asserted, and it occurred to me something a bit like this is going on in teaching language, something that looks a little like use, a little like mention, but doesn't make sense as either. You have to use a word and show your use, but your use of it in the first place is not a normal use -- to inform, say -- but a use chosen just so that it can be shown. Some features of assertion have to be in place, but not in order to make an assertion.
So I don't think it's helpful to think of utterances as having a content that can be "extracted," nor is it helpful to think they have or lack some stereotypical force.
Instead, most utterances only contain part of a point, at best, so whatever you count as the content of a statement is an interpretation that depends on how you fill out "what was said," and the force of an utterance is often mixed or uncertain, so what you count as its force is primarily an indication of how you intend to take it.
My point, again, being that logic makes choices about what to count as the content, what to say was the force, and these choices can be interesting, helpful, and defensible, but they are also underdetermined. Even if you have no expectation that logic can tell you "what's really going on" in language use, you can still get logic wrong by assuming it has to come out as one specific thing.
To be sure, it is a mistake to think that there is one correct analysis of any given utterance. But of course that does not mean we can't or shouldn't engage in analysis.
All this by way of again rejecting logical monism.
Good post. I agree with almost all of that, and although we may disagree on some of the implications, let me just break off a piece to try to disagree with. You can bring in some of the other pieces as they become relevant. As a caveat, we now seem to be doing speech act theory rather than logic, and this will need to be held in mind.
Quoting Srap Tasmaner
I think Kimhi is more or less correct that declarative sentences have (or display) assertoric force, and I would also say that utterances have force.
Now part of the problem here is that we can say utterance and mean something which contains force or does not contain force, and a lot of this goes back to our conversation about screwdrivers. First of all I would argue that something which does not contain force is not an utterance. Everything which is actually being uttered has actual force. But the interesting question is whether a certain material aspect of an utterance must also contain force, and this is perhaps the parallel to the OP in speech act theory. We could call that material utterance a sentence, just as we called the material assertion a declarative sentence. This is a sentence conceived as a bit of language.
In the first place I would say that all sentences have a common baseline of force. What kind? Communicative force. As a sign of communication a sentence has communicative force.
Now maybe you would concede that sentences do have communicative force, at which point the more difficult inquiry begins, namely that of deciding whether a given sentence has inherent force over and above communicative force. I think it will, and like the screwdriver, the availability of multiple uses does not preclude a singular form or force. A screwdriver can be used for many things, but there are many more things that it simply cannot be used for. A sentence is the same way, and its determinate range represents its inherent force.
I would then want to bring in different senses (for example, the theological senses of the literal, allegorical, tropological, and anagogical). I want to say, with Aquinas, that the literal sense is normative and foundational. It is what grounds the natural force of a sentence. If a sentence like, The old dog is hungry, had no natural force, then anything at all could be done with it. But not anything at all can be done with it; therefore it has natural force. What limits its range of use and its force? Its literal sense. Even metaphors and analogies play on the literal sense, and are not divorced from it. Irony and humor also depend on the literal sense, if in a different way. Someone who does not understand the literal sense will not understand any of the other senses, for these other senses build on the literal.
(Two quick preemptions. First, we have sayings whose literal sense has been lost to us. In such cases the sense which was previously metaphorical has now become the literal sense in a rather odd way. Second, the normativity of written or spoken language is interpersonally situated. The claim here is not that, say, an English sentence has natural force for the Russians. The concrete sense of an utterance will be a kind of relation between the intent of the speaker and the intent of the recipient, and the sense of a sentence will be an abstraction and reification of this.)
Oh -- there are dots I didn't connect there.
Part of my concern is, what are these statements, the Ps and Qs, we deal with when doing logical analysis?
In a sense, I'm trying to flesh out @frank's point about context. There's obviously something to that, we all know there is. Is it just dealing with indexicals? Maybe making explicit common knowledge that's relied on? You might be able to convince yourself that turning a non-truth-apt sentence into a truth-apt proposition is only a little more complicated than substituting names for pronouns, only there's more of that sort of thing to do.
But what if that's wrong? What if language never comes anywhere close to expressing a complete thought because that's not what it's for? What if language is all hints and clues and suggestions because the audience shares the burden of communication with the speaker?
Logical analysis, when it deals with "bits of language," seems to set aside the communicative nature of language and pretend that by presenting what one side of a conversation says, or what they might say if they were more prolix, it can present an argument in its entirety.
If that's false, what are we doing when we engage in logical analysis?
...
Lots more in your post to respond to, but I wanted to get to this first.
When I said that we are doing speech act theory rather than logic what I meant is that the content/force distinction is not the same for each. Speech act theory deals with intentional (illocutionary?) force, whereas logic deals with assertoric force. Martin points out that you can run the same sort of critique from the perspective of speech act theory, but it is a somewhat different critique.
What I am gathering from Martin, @fdrake, and @Pierre-Normand, is that assertoric force is not merely one variety of intentional or illocutionary force, for the logician and the speech act theorist use the word 'assertion' differently. Maybe the most obvious difference is that the logician need not speak or engage in interpersonal communication in order to assert. More generally, what this means is that the forces involved in logical acts are different from the forces involved in speech acts. Martin is an example of someone who is explicitly interested in the former and not the latter, at least in the paper cited in this thread.
Edit: This may go back to your observation about language qua thought vs. language qua communication.
Quoting Srap Tasmaner
Without yet opening this can of worms, I think my post accommodates this. I called a sentence "A bit of language," (following the classical understanding of a proposition which underlies the Frege-Geach Point). But I think a phrase or word is also a bit of language, at least insofar as my points about determinate range and literal sense are concerned.
(I've started the Martin paper, so I expect we can talk more about that soon.)
I don't want to just rush to deny that this is so, but all we have so far is the typical philosopher's gambit: "And by 'assertion' I don't mean assertion in the usual sense, by 'force' I don't mean force in the usual sense, ..."
Consider that we are discussing a man who thought it necessary to invent a language, separate from natural languages, that would be suitable for use in logical analysis. In Frege's language, a formula like "Fa" or "(x)Fx" is said to express a complete thought, that can be true or false, by fiat, by stipulation. Is it any wonder that his logic looks more like a branch of mathematics than anything else?
Which, again, is not to say that it is useless, anymore than mathematics is useless. But what are we to say about its relation to human reasoning conducted in natural languages? Is it, for instance, reasonable to imagine that something like Frege's system *underlies* human language use? I'm skeptical. Even while allowing its usefulness.
And that means what we say about logic is what we say about a certain approach to reasoning and language, a certain way of taking it, but we need not think we are saying anything fundamental about language or reasoning itself.
Quoting Srap Tasmaner
We have circled around this problem a number of times in the thread (i.e. the fact that the judgment-stroke is not a speech act). Most recently I claimed that Frege is concerned with assenting, not asserting, but that's also imperfectly stated. The judgment-stroke is something like the act of assent or the recognition of truth. This does not seem to be the same as assertion in interpersonal communication.
Quoting Srap Tasmaner
I don't think Frege holds that such things can be true or false by fiat.
Quoting Srap Tasmaner
I also don't think mathematics holds that mathematical claims can be true or false by fiat. I think this thread has often conflated metamathematics and metalogic with mathematics and logic.
We can represent truth-apt thoughts or truth-apt mathematical claims without providing content, but this is a very limited move, and does not imply that the truth of thoughts or mathematics is in some way stipulated. I don't want to move into a tangent, but the object of metamathematics is different than the object of mathematics, and what is stipulated in that case is not so much truth as a truth-mimicking value that then allows one to study formal characteristics of mathematical systems.
Quoting Srap Tasmaner
You seem committed to the position which says that we cannot say anything fundamental about language or reasoning itself. I don't take that as granted.
Sorry for the shorter post!
Sorry. That was ambiguous. The assignment of the truth-value is done by judgment, not by stipulation, but that "Fa" is truth-apt, that it expresses a complete thought, is stipulated.
Not at all. I'm contesting whether we should take Frege as having done so.
And I'll get back to work.
More response to your earlier post tonight, and then we'll go from there.
If you're a realist, you wouldn't say truth is "assigned.". You would just say some propositions are true and some are false. Some have never been expressed and some probably never will be.
No? Look at this sentence:
Quoting Srap Tasmaner
Now if we tighten up the logic, then the second clause would read, "...and therefore we must not think we are saying anything fundamental..." I want to say that whereas your second clause is a "X is not necessary" clause, your first clause in fact entails, "~X is necessary." If X is to remain a possibility then the first clause would need to be rewritten.
I take it that this discrepancy represents an important issue underlying the thread.
Quoting Srap Tasmaner
I am focusing mostly on his final section where he tries to set out an alternative to Frege. The other parts are interesting, but I think an alternative is what this thread is most in need of.
How very peculiar.
So we have (1) the primary phenomena, everyday language use and reasoning.
Then there's (2) the way logic schematizes these.
And there's the further claim that in carrying out (2), we see (3) the deep structure of everyday language and reasoning, the underlying logical form.
My claim was that we can talk about (2), whether (3) is true or not, and even without considering whether (3) is true or not.
It's the same thing I've been saying all along, that (2) doesn't entail (3).
If it turned out (3) is true, then all our talk about (2) would count as saying something fundamental about (1). I'm openly skeptical about (3), but I don't believe I have to commit to (3) being true or false to talk about (2).
All of this agnosticism about (3) depends on being able to formulate (2) neutrally. If you're a partisan for or against (3), you might not bother. I'm mostly a partisan against (3), but I hold out hope for a neutral (2) so that I can talk to partisans for (3) about (2), and maybe even (1), rather than just (3). And because I find (2) interesting and useful even though I doubt (3).
(I didn't follow your reasoning that turned my "not necessarily" into an even bigger "necessarily not". I do hope this was clearer.)
It's worth, I hope, pointing out that this treats the "underlying logical form" as if it were found in, rather than intended by, an utterance.
(3) requires an acceptance of logical monism- the notion that there is one true logic that provides the "underlying logical form" of language.
A better view would be that we can choose our "everyday language use and reasoning" so as to conform to some logical structure and thereby infix logical structure into our utterances. That is that logical structure is not to be found in our utterances but imbued by way of making what is being said clear.
Logical structure is not found in, but given to, our utterances. There are no rules of thought, but there are better and worse arguments.
There's reasons we tend to talk about utterances, sentences, and assertions rather than thoughts. One can present some particular utterance, sentence or assertion for inspection. Not so much a thought.
Those who say "Frege distinguished the thought qua logical content from the assertoric force attached to it when claimed to be true" might do well to say instead "We can distinguish what a sentence is about from what is being done with that sentence". That single act dissipates Martin's concerns.
See the SEP article on states of affairs.
"Thoughts can be the contents of propositional attitudes. When one says There are three things that everyone who works on elementary physics believes, one quantifies over things that everyone working in elementary physics believes: thoughts (see Chisholm 1970: 19). Thoughts are also truth-value bearers (There are three truths that everyone who works in elementary physics believes). How are thoughts related to states of affairs? For instance, how is the thought that Socrates is wise related to the state of affairs Socrates being wise?
"Prima facie,thoughts are one thing, states of affairs another. Thoughts and states of affairs differ in their individuation and existence conditions.
"Individuation-conditions: Thoughts are supposed to be the contents of propositional attitudes like belief and desire. Let j be shorthand for a propositional attitude verb (desire, believe etc). If one can j that p without eo ipso j-ing that q (and vice versa), the contents that p and that q are different. Now I can believe, for instance, that Hesperus shines without believing that Phosphorus shines. Hence, if thoughts are the contents of propositional attitudes, the thought that Hesperus shines is different from the thought that Phosphorus shines. If the thought that Hesperus shines is different from the thought that Phosphorus shines,thoughts cannot be logical complexes whose constituents are particulars and properties. Following Frege, many philosophers therefore take thoughts to be complexes that are built up out of modes of presentation. Here thoughts only refers to such complexes. Since there are different modes of presentation of the same particular (property), there can be different thoughts that concern or are about the same particulars and properties. In contrast, Hesperuss shining and Phosphoruss shining are the same state of affairs, namely the complex that contains only the planet Venus and the property of shining. We will see in section 2.4 that not all philosophers follow Freges lead. If one has arguments for a coarse-grained individuation of the objects of belief, states of affairs may serve as contents of propositional attitudes."
I think that rather than worry over this issue, this thread might benefit from comparing Frege's view of the world to Wittgenstein's. Or maybe that would be a different thread. But it would more interesting to me. It's a pretty fascinating topic.
I think I basically agree.
I would make two additional points: there's also no reason to think there's only one way to make our thoughts or our expressions clear (contra Frege, who might agree with you, but think his logically perfect language is the solution); second, clarity is obviously negotiated between speaker and audience, and thus our practices of making better, clearer arguments arise from the efforts of ordinary speakers -- addressing such issues is part of speaking a language, and of thinking as a member of a group.
It's why I keep harping on the usefulness of logic even while expressing doubt that our linguistic practice has a logical foundation. And logical analysis isn't appropriate for all things at all times.
And very last point, or set of points. Consider again musical notation. It's a simplification and representation of the practice of playing music, as, in my view, logic is a simplification of how we think. It's a fantastic invention, crucial for cultural transmission, and so on. And when children learn music, their first steps require simplification, and this one is ready to hand. But there's much, much more to performing music than what's on the page, and no one would think of disallowing the introduction of elements not captured there. No one makes the mistake of thinking the notation is an *ideal* that performance should strive to reach. It's not even the foundation of music, but a minimal record of what has come before, and in that sense can be used as a kind of starting point. (And I suppose the same could be said for a record of the words someone has spoken.)
Yes, very helpful.
Quoting Srap Tasmaner
Right, and that is the difficulty. Im not sure (2) can be formulated neutrally as a claim. Probably it can only be approached neutrally as a question. The question is something like, What is logic? Or, What are humans rationally capable of?
We can be more conservative and ask whether Freges distinction between assertoric force and thought has a real correlate in human reasoning, and I think it surely does. We are truly able to think things without judging them true. This is why Martin thinks the distinction needs to be redrawn rather than abandoned. If this is right then Freges logic represents something true about reasoning itself, even if what he says is skewed or off kilter.
-
Quoting Srap Tasmaner
This looks like that same conflation between speech act theory and logic. Can we form sound arguments and thereby gain knowledge without engaging in interpersonal speech acts? This is precisely what logic means in the classical understanding.
Quoting Srap Tasmaner
Each time you state the problem in terms of artifice or invention you fail to capture a neutral (2). Do you see this? To call logic an invention of artifice, or a schematization or formalization, is to have begged the question. If that's all logic is then the answer to (3) is foreclosed.
(We are now knee-deep in the topic I was hoping would become a new thread. Is it worth breaking off? The general membership would find this topic more interesting than Kimhi's.)
Have you actually put any effort into Martin's paper? Have you tried to understand any of this on its own terms, as fdrake invited you to do? In section 4 Martin spends a lot of time on thoughts.
The objection here looks like self-fulfilling laziness. "Martin doesn't give an analytic-stipulatively precise definition of 'thought', therefore logical nominalism holds." This is classic Wittgenstenian question-begging. Martin is damned either way. If he gives an analytic-stipulative definition then he is barred from contact with reality (i.e. barred from logical realism). If he instead works his way towards a real definition of thought then the Analytic rejects it as imprecise. For the Analytic, only what is stipulated can be precise, only what is precise is allowed, and therefore logic is the realm of tautology divorced from reality. Three cheers for circular reasoning. The corrective here is to stop being lazy and to start challenging yourself by thinking about things on their own terms, as they are in themselves, rather than as you stipulate them to be. Anyone who makes the simple observation that arguments presuppose thoughts should be willing to wrestle with the "a posteriori" question of what thoughts are. If they are not willing to wrestle with such questions then I'm not sure what they take themselves to be doing.
Leontiskos is the guy who was just a few days ago forcefully insisting that Frege did not philosophize in terms of thoughts. Then he said maybe Frege did in his early years, but transitioned to something else later own. :lol:
But they haven't paid their dues! We've earned this, by banging our heads against Kimchi. Oh sure, they'll join in *now*, for the fun part, but where were they when we were slogging through the mud, I ask you.
I do, absolutely. As I said, I'm largely a partisan against (3) so I'll keep making that case along the way.
I'm not sure (2) can be presented neutrally, but I hope it can. And if it can't, I'll keep saying "invented" rather than "discovered".
Quoting Leontiskos
Not "conflation" but derivation. Here again, this may not contribute to a neutral presentation of (2), but I have to treat language as being first for communication and other uses come after.
I don't think that quite forecloses (3). If you look again at musical notation, you can say there are patterns (the theory of harmony for example) that only really become apparent in this simplified form. And you can cheerfully claim that the move to notation *reveals* something that underlies the practice of making music. And so with Frege and his concept-script.
All I'm arguing for is slowing down the moment of schematization so that we can see frame-by-frame what's happening, regardless what we say about how before and after are related. --- They are at least related, in a different sense, by this act, so understanding this act may, or may not, tell us something about how they are related in a more abstract sense (whether one or the other is foundational and so on).
Those who only agree to come after the kimchi has already been served. :lol:
Quoting Srap Tasmaner
Well if language is essentially for communication then the answer to the question has again been foreclosed.
Quoting Srap Tasmaner
But the classical logician says that it's not a schematization at all, and on that account you have begged the question.
Here's how I would start a thread about logic. I would post the dilemma of Meno 80b. I would basically say that if that dilemma can be overcome then logic exists, and if it can't then logic does not exist. Per Rombout, someone like Wittgenstein doesn't think logic exists. But the thread would not use the word "logic," for that word is an equivocal quagmire.
Well then that word is not neutral enough.
We have on the one side,
(A) "Dogs are nice"
and on the other
(B) "For all x, if x is a dog, then it is nice."
We just need a neutral word for the relation between (A) and (B), and, if you start with (A) and recast it as (B), we need a neutral word to describe what you're doing there. Maybe you believe you are "revealing (A)'s logical form," and maybe you don't.
And then of course there's
(C) (x)(Fx -> Gx)
and you have to deal with (B)'s relation to (C) and probably (A)'s relation to (C). And that's the whole set.
Heh. I taught my phone "Kimhi" but it ignored me this time.
@J might not object. "It doesn't taste good, but it is healthy!" :grin:
Quoting Srap Tasmaner
Well, I don't think this Fregian move can plausibly present itself as something other than a schematization, so I agree with you in cases such as this one. But this is probably the weakest point of Frege's system. It's harder to tell if distinguishing force from content is artifice.
Again, for me it begins with the puzzle of the Meno. I want to say that if logic is artifice then knowledge is artificial. And of course some of what we involve ourselves in when we do logic is artifice, but that doesn't mean that there is nothing more than that involved.
Or we could put it this way: "Even if Frege's is not perfectly correct, it correctly points us in the direction of a real rational faculty that humans possess." To what extent can we speak about and explicate that faculty? And form and strengthen it? It's not altogether clear, but that it exists seems obvious.
This is good. I'll go look at the Meno (I think there's at least one thread on it here somewhere), and if I have anything to say, we can make a fresh start with that.
Sure, sure. I, ahem, recollect the Meno and I know it weirds modern readers out. We'll do better than that. Unless I have nothing to say, then it's on you.
You know it's funny, but in what you might consider the early days of cognitive psychology, before there was much neuroscience, there was an enormous amount of research specifically on how children learn geometry. It was a core topic.
I agree with your two points. And yes, logic is useful even if it is not the foundation of our language. There are multiple logics, and we chose a logic to use in order to set out a coherent account.
It seems to me that we agree in rejecting logical monism.
I read musical notation (sheet music) only very slowly, but quickly master tabs. I choose the latter, rejecting musical monism for reasons of utility. I recognise that I would need to move to notation if if I moved to keys rather than strings. Much the same as for choices between predicate, propositional, free, or any of the various other logics. Depends what you are doing.
I'm not interested in a precise stipualtive definition. Such a thing is anathema to much of analytic philosophy, and certainly against the spirit of Philosophical Investigations. It's worth noting that those who are critical of analytic approaches usually begin by misunderstanding them. Again, I was making the point that we can talk about our utterances with greater lucidity that about our thoughts, simply because our utterances are public.
Yes, a convenient ambiguity. In the Begriffsschrift "?" is an explicit judgement of what follows is known. In the Grundgesetze this has changes significantly; ? to something like "The following names the true". This is recounted in the SEP article on Frege's Logic. Subsequently truth was substantially replaced by satisfaction.
Quoting Banno
One of the problems here is that focusing on Frege may give the false impression that his account remains paradigmatic for modern logic. It isn't.
That may be true, but Frege was interested in thoughts. I think comparing and contrasting him to Wittgenstein would be a cool way to examine that.
Quoting Banno
That's fine. Frege remains fascinating. If I found a good article comparing and contrasting Frege and Witt on the issue of the world (...the world is all that is the case) would you be interested?
I suspect that the difference of opinion between @Leontiskos and I is that he thinks of logic as an account of how we either do, or perhaps how we ought, to think. In contrast I don't see how such a view survives the multiplicity of divergent logics we now have available, and rather treat logic as a choice, a set of tools we can apply depending on what we are up to.
So Srap offered Quoting Srap Tasmaner
But earlier Leontiskos offered an example that would have come out as
What this shows is how logic can be used to clarify the somewhat ambiguous English of "Dogs are nice" by making explicit the difference between a universal and existential quantification. Of course, we could have done the same thing in English by asking "Do you mean that all dogs are nice or that some dogs are nice?".
Not one logic, but many.
With that guy, I'll note that
at time 1, he's opposed to x, while being as insulting as possible
at time 2, he's in favor of x, while being as insulting as possible.
There's no explanation for why he changed his mind. Something's up with dude.
There are a few things I want to take away from my limited time reading the book (half of it over 3 sessions). The first is the syncategorematic/categormatic distinction. Syncategorematic expressions cannot be part of predicative judgements, categormatic expressions can be. An example of the former would be "Sally thinks ...", with an unevaluated placeholder. An example of the latter is "The cat sat upon the mat". The distinction there isn't between intensional and extensional understandings of expressions, either, it's to do with whether a given concept can be considerable as part of a predicative judgement tout court.
The idea of part of a judgement in the book is also non-truth functional. If someone thinks that P, the assertoric force associated with thinking that P is conceived of as part of thinking that P - and the force is not truth functional. In effect, one's thinking itself takes the form "thinking ("judgement-stroke ( that P )")", rather than "thinking ("that P")". I have used the quotes to denote something like "entity boundaries" (scarequotes, my term) in the state of consciousness that composes a judgement, and brackets to disambiguate parts which would correspond to propositions/declarative sentences.
Something particularly important for Kimhi is unity without dualities. To a first approximation, this is a unity of the propositional form in the judgement with the state of being which produces the judgement. It would thus be, respectively
A) neither psychological nor logical - in virtue of that unity being a composite of judgements of what is and of the mental juxtaposition of what is judged to be.
B) neither normative nor descriptive - in virtue of that unity consisting of a series of judgements of what is that may be true or false and thus not normative. Then, there are regularities of those judgements which enable them to express what is true or false in mental and practical ways. The latter in turn compels people to learn to judge in that manner, so that their expressions may be true or false.
C) neither mental nor abstract - in virtue of that the judgements are patterns of thought and enabling norms of chains of association, they are pragmatised patterns of thought.
In terms of the thread title, Kimhi definitely provides 'a challenge to Frege on assertion", but I think the thrust of the book is more properly thought of as providing a challenge to everything in the heritage of linguistic philosophy after Frege. And the nature of that challenge is to limit the relevance of extensional understandings of terms in judgements, undermine the distinction between psychologicism and logicism as responding to false problems, and try to bring the mental - in the sense of understanding the structure of concepts - back into the analysis of logical form.
So I'm going to imagine that Kimhi invites his readers to imagine what a post-Frege linguistically oriented philosophy can look like if it centred the understanding of concepts that coordinate expressions and situated expressions alongside the states which produce them.
I'm not convinced that Kimhi's approach to challenge that philosophical heritage succeeds or even produces anything particularly fecund for further explication on his terms, but I do think it raises interesting problems and (what seem to me to be) neglected associations.
I just don't know wtf to do with it honestly. After reading it I'm left wondering how I could use it to help me think about others' thoughts and expressions, and I see dubious relevance of it to my life. Other than reminding me that concepts matter, which is something I tend to believe anyway.
Quoting fdrake
This is also very illuminating, and I think correct about Kimhi. Is it true? I'm still not sure.
I too wonder if T&B is going to turn out to be a kind of unicorn, grazing in its own field, inviting awe and derision but perhaps not contributing much to philosophical discussion. And yet . . . look at us here, going on for pages and pages about it! Maybe a path for further engagement would be to take a step back from the specifically logical issues that Kimhi raises, and see what the book helps us to understand about the perennial problem of mind's special place in the world, or what Kimhi calls "the uniqueness of thinking." We shouldn't neglect that a good bit of Kimhi's project is highly "Continental," in that he's convinced that analytic dualities about thinking and being are just wrong, and misunderstand subjectivity completely.
Perhaps this is why philosophy of language should not be examined in a vacuum. For example, I realized I had a reply in another thread that perhaps has relevance here:
That is to say, all these questions can revolve around how it is humans have this inter-subjective understanding of meaning, and thereby how "Truth" is judged in regards to "state of affairs" (of the world - metaphysical), versus our epistemological underpinnings (a species that conceptually and linguistically communicates and invokes/evokes "meaning" in a psychological sense). But all of this is getting obscured by this talk of Frege.. As if, to make shoe-horn it.. That's just my sense.
If you read the SEP article on states of affairs, it talks about how they have the form of thoughts. In other words, we don't think of the world as disconnected objects, we think of it as states, which implies the verb "to be.". The way I've been putting it is that we imagine the world can talk.
Remember in the Tractatus, Witt says the world is all that is the case. He's expressing this same idea, but he's going to move toward saying logic is not in our field of view when we look at the world. So if one got the notion that since (phenomenologically) the world talks to us in complete thoughts, that logic is the structure of the world (this is basically Stoicism), then Witt says your language here has gone on holiday. You're spouting nonsense. Logic is not informative about anything.
That's one way to think of it anyway.
@fdrake
I think these questions revolve around the difference between meaning versus the "states of affairs". Once you understand that connection, you are getting closer to most of the issues at hand that revolve around correspondence.
Humans are an inter-subjective species. We by-and-large can successfully communicate meaning, and have an understanding. This is a type of consciousness- one that can convey meaning of the world. "True propositions" (reflections of actual states of affairs going on in the world), is more a question of how we cache out "Truth". Meaning, however, is largely inbuilt. Meaning itself, "The grass is green", is something that comes naturally to humans.. "It is true that the grass is green", is more of an extra layer which we learn, whereby truth is assumed to be an extra layer of "error-checking" (i.e. repeated observation, experimentation).
Maybe, but Frege denied that correspondence is a definition of truth.
Fine, can you articulate his idea of truth without reference to more obscure ideas that obfuscate it? Just speak plainly.. In a couple sentences, what is Frege's idea of Truth?
I have a sense (no pun intended), that what is going on here is something along the lines of the truth of the meaning of a proposition (that we can discern propositional meanings), and the TRUTH of the world (that those propositions accurately portray states of affairs of the world). But not sure.
He thought that truth can't be defined. Definition implies breaking something down into smaller pieces (a zebra is a horse with stripes, for instance.). Truth can't be broken down any further. It can't be taught. You just know what it is.
Quoting schopenhauer1
Or that propositions are states of affairs.
I figured the answer would look something like this. What is the "know" here though? Meaning of words (denotation), meaning of statements (declarative statements- the cat is on the mat) or states of affairs (what is the case going on in the world)?
This is just spitballing: I didn't see much new in it? A deformation of Kant? New schema of thought and content? Concretising the schematism into expression rather than making it transcendentally prior? The only touchstones I saw for his central theme of unity were Kant and Parmenides. I have no idea about the connection between that unity and oneness.
Troll summary in a nutshell: Is the like like the like that likens the unlike with the like in the like and the unlike alike?
In this case "know" means to understand what's being asserted by the use of the word. No word means anything until it's used, as opposed to mentioned.
That itself is a (possibly not true) assertion.
Quoting frank
Quoting frank
This doesn't make sense to me. Does he mean that E=MC2 is somehow intuitive to us? Or that "that particular grass is green", is true? Or that "The grass is green" is intuitive? Because I would think only the last instance makes sense.. And then I was correct, this is just a difference in how "truth" is being used. "Truth" for Frege becomes simply about the ability to parse meaning of statements (The grass is green), rather than corresponding to the world, (It is true that grass is green).
I think so.
I guess I should "like" your post. :wink:
Quoting fdrake
That may be close to it, if by "expression" we include the act of thinking. The new part is Kimhi's confident assertion (sorry!) that what he calls the syllogisms of thinking and being cannot be connected in predicate logic. Frege might reply, But that's a good thing! whereas Kimhi sees it as a bug, not a feature.
Oversimplified, of course, but I'm trying not to dive back in!
Can't I just say that he was confusing the two forms of truth? Actually, there might be three things being confused..
1) The ability to parse the meaning of words (cat, on, mat) - a cognitive ability, related with our species' ability to use language, often associated with various brain regions, studied extensively by cognitive scientists, linguists, anthropologists, biologists, and the like..
2) The ability to use the words to make meaningful statements (the cat is on the mat)- also a cognitive ability to, related with our species' ability to use language, often associated with various brain regions, studied extensively by cognitive scientists, linguists, anthropologists, biologists, and the like..
3) The ability to use statements to make statements about states of affairs of the world- this is a culturally learned notion whereby we are taught that observation and experimentation might lead to a corresponding "fact" of the world (It is true that the cat is on the mat). It is true that the cat is on the mat, is considered "true" in a "factual way", because of repeated observations or experimentations. The cognitive ability to understand word meaning, and meaningful statements (1 and 2) are assumed.
Right. States of affairs are truth makers. Just using the word "state" implies being, to be. What is the state of affairs? It's that the cat is on the mat. States of affairs have the same form as thoughts. Maybe we can't move away from language. Maybe there's no way to do that.
I'm not really sure how important metaphysics was to Frege. His ideological descendants, like in philosophy of math, don't seem to really care much about the political fallout associated with being platonic. Being platonic just fits what they see as math. They leave metaphysics on the shelf.
Witt says that all such worries about how thought is related to cosmology amount to nonsense. If you're worried about metaphysics, you're trying to do something with language that it's not capable of. But the attraction of going back down the ladder and getting all worked up over metaphysics is always there. Who can resist?
This may it not have any bearing on the OP. :grin:
The problem with that sentiment is when you are doing a sort of "origin story" of "whence language". In a way, the species' evolutionary history and intertwinement with language DOES get metaphysical- pace academics and a host of theories revolving around "semiotics" or "information theory" or simply the "metaphysics of biology" or "what it means to be a human".
Wise.
Yes. It's a secret that it's all nonsense.
No worries, this is sort of the after-party!
Quoting frank
Well, but this is what I'm contesting. Even on the most generous interpretation of "form," a cat sitting on a mat doesn't look remotely similar to any thought or linguistic expression. So if not in appearance, where are to we to find the similar form?
Quoting frank
Possible but unlikely. Do you believe that Witt himself succeeded in demonstrating this?
In the Tractatus.
Non-sense in what way? There's several senses to non-sense.
I know that's not what you meant.
But seriously, how do you understand Witt's explanation of "similar form" in this context? Are you referring to picture theory?
It's far from obvious that states of affairs are helpful, rather than just yet another thing to puzzle over.
Form is probably the wrong word. How did the SEP put it? They're similar?
Quoting J
I think so.
He seems to think there's a sort of isomorphism here, that atomic propositions are structured as atomic facts are structured. It's why you can use a sentence or a picture or a model or the actual things to say something.
It would be like the knight on a chess board describing the game of chess. It can't have that vantage point.
no
So is evolution and the development of the universe also off the table even though we don't have those vantage points?
For a while Russell thought they're the same thing. A true proposition is an obtaining state of affairs. Neutral monism.
Metaphysics is different because it's talking about the whole world. Language is for talking about things in the world, like evolution or cosmology.
Wait, metaphysics is about the "whole" world, now? Really? So when someone refers to the "Metaphysics of X", and it's only part of the world, that is not metaphysics? Metaphysics is ALL or nothing? In some conceptions, but ALL metaphysical conceptions?
That would be an application of an overarching ontology to X.
Right, but that's not "the whole world"- the overriding ontology though, true.
So, okay, getting back to evolution and history of universe, you said:
Quoting frank
Yet you said:
Quoting frank
Yet evolution and history of the universe are things we cannot have a vantage point about. Same goes perhaps about the evolution of language, or for that matter, "the ontology of language", or the "ontology of information", yet here we are sharing information, using language, evolved from a universe over the processes of time and space.
I guess what I'm asking is, How is this a powerful or important theory? Thus far it seems to have very little explanatory power.
Agreed, but just about no one mistakes the statement for the state of affairs. But you know this, so I realize there's something I'm not understanding here. Expand?
Sounds like a performative contradiction to me! Can't get out of statements!
As I said:
Quoting schopenhauer1
Well, yes. What a statement sets out is a particular situation in the world. Do you then have three things, the true statement, the situation in the world and the fact? Or are we multiplying entities beyond necessity?
1. They could. I forget who this was -- LW? Sellars? I don't know -- but someone pointed out that you could write
for "The cat is on the mat".
2. Anyway, the whole point of the "logical form" thing is that there is something we happen to represent in particular ways in particular languages using sentence structure, but that structure is not the logical structure, just how we represent it.
It's one reason people are sometimes inclined to posit a "language of thought".
3. I think the isomorphism thing is not crazy. In order to say that a couple things are related in a particular way, appropriate to those things, you combine names for those things in a particular way, appropriate to names of things.
Not crazy, but the trouble is it sounds easy to put this into a theory and it turns out to be hard.
4. Probably because it's a fundamental mistake to think that language has the same kind of structure you think the world has. Not crazy, but wrong, and understandable, though why we think this is itself an interesting puzzle.
The very idea that in language we represent the world, is probably a sort of illusion, or a myth.
Maybe so. I'd have to think about it.
That's Sellars. Naturalism and Ontology I think.
I take it as phenomenology.
I commented earlier that the emphasis hereabouts is Tractarian. The picture sitting between the statements and the world. It doesn't solve the problem of replace the picture with the state of affairs.
But we can be pretty confident that we have the statement on the one hand and how things are on the other.
All this by way of hoping to avoid "states of affairs" becoming part of our ontology.
Quoting J
I didn't mean everything was "made of statements".. I'll lead you to something, but first let me take the route there..
Why do you think the Tractarian vision of "states of affairs" and "true propositions" pointing to the states of affairs as anything really profound rather than common sense? That is to say, this notion that the world exists, we talk about it with statements that pick out possibly true ones.
Quoting Banno
A statement and what a statement sets out are not the same thing, and it is not redundant or superfluous to talk about what a statement sets out. Thus Banno is arguing for a different thesis here than his original one (i.e. equivocating). Even if we agree that a state of affairs does not differ from what a statement sets out, it does not follow that a state of affairs does not differ from a statement. A statement is a locution; a state of affairs is not.
---
- Good posts. :up:
How do you know? You are referring to something. Yet your reference is cognitively something. That doesnt have to be a state of affairs.
Well, no, I didn't, and the folk here are competent enough to understand the difference between "It's far from obvious that states of affairs are helpful" and "states of affairs is redundant and superfluous". Your misrepresentation of those with whom you disagree is by now well understood.
What we might do well is to avoid is inserting a third entity between the world and the statement. A state of affairs is not a something apart from how things are.
Folk are welcome to talk about states of affairs, but might do well to remember that they are a turn of phrase, not a piece of ontology.
Well, yes, you did:
Quoting Banno
Quoting Banno
-
Quoting Banno
I don't know what it would mean for state of affairs to be a "piece of ontology." In all likelihood you don't either.
This is a classic Analytic move of claiming that natural language has gone astray and "states of affairs" is unnecessary. In natural language "state of affairs" and "fact" do not mean the same thing. I'll stick with natural language rather than the artificial simplifications.
Thought it might have been him.
On the one hand, it's a ridiculous point because you can't *say* one word on top of another -- gotta say them in order. But on the other hand, spoken language is pretty much always accompanied by gestures, so you can imagine an accompanying gesture to convey the "on". On the third hand (the gripping hand), this won't work over a telephone. But on the fourth hand, language is spoken in person long long long before telephones, and pretty damn long before writing. And even writing has its own story, a little different from the story of speech.
Thats why Tractatus is confusing. It posits an ontology but doesnt want to remain there too long. Objects, state of affairs. Call them real or tokens, but they are something that he is corresponding with propositions. I hired they could be thoughts if one is to make an idealism from it.
We even had a long discussion about it 7 years ago.
This may be getting to the heart of it, especially if we push back, even gently, on the idea that "language" and "world" are easily separable and distinct. Language, or at least some parts of it, may in fact construct the world rather than represent it.
That confusion was addressed in PI. But on that, as I recall, you disagree.
The SEP article that @frank introduced has arguments - section 1.2 - for the need to introduce states of affairs.
Hmm. Streetlight, of loving memory. Up until that thread I had refused to use "proposition", but Street convinced me of its utility.
Rombout has a nice section on linguistic differences, such as Frege's spatial notation. For example, the author she appeals to considers the difference between the Roman and Arabic numeral systems. I would say it's not ridiculous, because written language is not somehow limited to linear left-to-right symbols. Even spoken language can have similar things, such as tonal languages like Vietnamese where inflection becomes centrally important.
Happy to go with you, but could you restate the question? Something off about the grammar.
Huh. Whaddya know.
Quoting Leontiskos
Yeah that's nice, I forgot about tone. (I really should learn something about how it's used in such languages.)
Continuing:
The basic idea seems to be that modal statements say something, and can be true, so there must be a something to which they correspond - and hence the need for "states of affairs" that can be what modal statements are about while not being how things are - not facts.
A state of affairs as how things might be.
But in most case we can keep track of what is modal and what is actual.
And drop the correspondence.
The foundational topic here relates to the Meno, which you are welcome to weigh in on:
Quoting Leontiskos
That topic pretty much moved over to Logical Nihilism
The idea of a state of affairs comes from the Cartesian worldview. You can't demolish someone's worldview without giving them an acceptable alternative. They won't let you.
In part it come back to the place of the "?"....
"We know that..."
"It might be that...."
"We believe that..."
Just trying to get back on task.
Know and believe are intensional operators. Is that where you were headed?
It's where I came in. "One might see this as setting aside the "assertoric" aspect of the sentence in order to deal with other aspects of its structure - what it is about." We can seperate the content from the intent.
I see.
So what I mean is, basically, as I see it, the Tractatus is simply a common sense point of view. X event happens in the world, we make statements that reflect these events. Actual events in the world (states of affairs) are reflected by accurate statements (true propositions). X state of affairs is reflected by Y true proposition (about/describing that state of affairs).
I won't open that can of worms at this time.. Witt's theory of language in context/use and shift away from language as static correspondence, etc. However..
Quoting Banno
In that article SOA are possibilities, where facts are what is the case from those possibilities. As far as I know, SOA that obtain are what Wittgenstein is saying is captured by true propositions.. Either way, whether modal possibilities of possible arrangements exist, versus the actual arrangements, he seemed to posit that there was a "something" that was being captured by true statement ("facts" or SOA that obtains).
To me, this is still a (barebones) metaphysics. It's a realist metaphysics that puts a lot of value on declarative statements are mapping "reality" in some veridically accurate way. The barebones aspect is that the "reality" is given short shrift in his koans referring to "objects" and states of affairs, and "facts", etc.
And yeah, there is something of modality in the Tractatus "logical space".
And so the question becomes interesting as to:
a) Why would our language/logic correspond to the world?
b) How do we know something is veridically accurate?
And thus this opens up interesting notions of information. Information theory seems to have some role to play for why "The grass is green" makes sense, AND then what it means to say, "It is true that grass is green". These are two different capabilities, possibly being conflated in this discussion, revolving around Frege. And Frege perhaps, did not have the tools to really go further with it. Modern ideas of information, linguistic evolution, and other forms, possibly outside of formal "logical systems", would help elucidate this. Yet this discussion becomes hermetically sealed to the dates of 1870-1950 when it is not opened up to these subjects which better tackle these confusions of the early analytics.
Quoting schopenhauer1
Yes, two different capabilities. As we've seen, Kimhi wants to minimize or even eliminate what is different about them, in aid of unifying thinking and being. Glad to learn more about how information theory might apply, if you have some references.
One possible insight: The question about how language/logic corresponds to the world is rather unclear. Some philosophers seem to take "correspond" to mean "reveal formal commonalities" or even "make a picture of." Others are content with showing any kind of naming or symbolic relationship, and for them this is correspondence enough. What question are we examining here? I suggest it's about the latter kind of correspondence, since even if there is no formal or pictorial relationship between "The cat is on the mat" and 1) the idea of a cat on a mat, and/or 2) the fact of an actual cat on a mat, it's still puzzling, from a certain angle, why we can rely on language to make reliable connections of this sort.
Isn't that oddly passive? A bit like puzzling over how the Philips Head driver just happens to fit a Philips head screw. We use language so that we can talk about the world. If it didn't work, we would use a different language.
But why should it be so puzzling with theories of evolutionary adaptation/exaptation? That is to say, clearly our species has a linguistic capacity. Academics like Steven Pinker (The Language Instinct) and Terrence Deacon (The Symbolic Species) even think that language is THE defining human feature. It seems to me, evolutionary development holds the key to why our species is able to parse the world out in discrete objects, and arrange them together using various verbs/prepositions, describing them with adjectives, and the like. I wrote this a long time ago, but I think it applies here.. This might be my most articulate and developed explanation for this set of phenomena revolving around human capacity for language, and language's subsequent ability to recognize natural patterns (what I now am calling "correlation-distillation"). Let me know what you think:
Yes I fully agree. Please see my full reply (which includes more-or-less my birdseyeview of language and its efficacy) in the post to J above:
https://thephilosophyforum.com/discussion/comment/939555
:up:
A simple example would be the pattern of day and night. It was certainly important for the human species survival to be able to recognize this repeating pattern, and to be able to make predictions about when and how darkness would fall, for how long, etc. But when language enters the picture, we get a series of explanations that all involve the sun doing things like rising and falling. While this is accurate pattern recognition, it happens to be untrue. So . . . what is it that allows language to move beyond mere phenomena, and strive for a truth that is observer-independent?
I dont think this is some kind of knockdown argument against evolutionary explanations, but is meant to indicate how they need expansion.
I think I did set out a historical framework for how this developed though:
That is to say, you cannot discount how the capacities of language led to both "formalized logic" and "empirical pattern-recognition" through contingencies of historical development that took place (for example, the culture of ancient Greece, the conditions of Renaissance Italy, etc.). I think WITHOUT historical contingencies, indeed, we MIGHT NOT be talking about the formal logic/math/scientific systems we are doing now. In other words, our current concepts and uses of logic/science WAS NOT a necessary/foregone conclusion. The capacity was nascent in the human by necessity of evolutionary demand, but it was an EXAPTATION that we hit upon these more formal versions of what we could do primitively as hunter-gatherers.
However, I do allude to the fact that the pattern-recognition itself, which we can call "nascent/primitive/en potential" in the early human, might have some connection to the fact that it could not go any other way. The universe has perhaps a certain set of patterns that cannot be be helped to have lifeforms that in turn recognize them. Imagine a spiral with a line running from the end of the spiral throughout the whole spiral system (humans are created from the patterns but can recognize the patterns, but this wouldn't be disconnected).