I think we've argued about this before. — Sam26

Yeah.

Seems to me that if something is the case, then it is in a form that can be put into a proposition - whether it has been or not. IF you prefer, the world is proposition-ready...

So far as I understand, you can pay for the privilege.

The point which I think the OP wishes to convey is the distinction between necessary and contingent truths. — Wayfarer

Or is it that between analytic and synthetic statements - which is not quite the same thing?

Yep.

SO — not a thread about imaginary numbers then.

Both, I suppose.

It seems to me that if something can be put into a proposition, then by that very fact, it has a propositional form - and this regardless of whether it has been expressed in a proposition by someone.

So, the obvious question to is, what place does logic have in PI?

I have, perhaps uncritically, suppose that PI led in many ways to the interest in intuitionistic and paraconsistent logic of hte last fifty years.

Maybe. My only point is that rejecting Krauss does not mean there must be a god.

With the corollary that sometimes overreaches what can be concluded from what we know.

Strictly, Quine's target is the analytic/synthetic distinction. This seems to be what you are so vaguely addressing. His main argument is roughly that there is no account of analyticity that is not circular. There are more problems with the distinction.

The conclusion is something like that treating supposed analytic statements as foundational is fraught with problems, and that some form of holism is needed.

No. Scientific work show that the world is ordered.

Your cited article does odd things with italics, but so far as I can tell the flow is that Krause wrote his book because he is scared of god. I wouldn't count Krause's musings as science. But what he does show, and what is avoided in the essay you cite, is that god is not necessary to explain the universe.

I might be wrong, there might be an actual argument in there. But I don't see it. So if there is, set it out.

If what you suggest were true, then one could do science in a world with no order by supposing that there was some order. But one could not.

Instead, it's that we can tell stories about how things are that leads us to conclude that the world is ordered.

Then you agree with everything that I’ve said and the duplicitous nature of truth so far discussed that it it always stays the same for some statements (truths, a la all triangles have three sides) and that it changes for in other statements (colour of sky) — invicta

No.

Truth is not duplicitous. It is simple. "P" is true iff P. That's all there is to it. The "...is true" in "It is true that triangles have three sides" and "it is true that the sky is blue" are the very same. What changes is the other bit of each sentence.

And, seperate point, there is an historical division between sentences that are considered to always be true, and sentences that change their truth value according to circumstance. In his pivotal essay "Two dogmas of empiricism" Quine showed that this doesn't seem to work.

That reality is intelligible is the presupposition of all scientific endeavours

Quite the opposite. That reality is ineligible is the conclusion of the scientific process.

Science works. Therefore the universe is intelligible.

So what ? Truth is not constant... But it’s also constant. — invicta

So what are we to make of this self-contradiction?

My simple answer is that truth remains constant, but that what is true can vary by context; and that your analysis did not pick up on this distinction.

See, if you changed your title to "Is what is true always context dependent", I'd say yes. But I suspect from what you have wirtten that you wodul say "no".

Instead you wrote "Is truth always context independent".

If we were to both take pictures of the sky where we are being in opposite sides of the world my sky would be dark yours would be blue. — invicta

Yes.

We would of course both be right and both be truthful in our assertions relating to the colour of the sky. — invicta

Yes.

So what.

You claim that there is only one sort of truth, well I claim that there are two. Constant truth which never changes night or day and the variable type that changes the colour of the sky night or day. — invicta

That's two different sorts of sentences, not to different sorts of truth.

What the baby and the dog want can be put into a statement.

Seems propositional to me.

:grin:

I'm not at all sure what it is you are saying in you OP, so I am not in a position to say if what I say is agreeing with or "counteracting" it.

I guess I'm trying to understand what your claim is.

You now say that it is about "two types of truths"... Are you talking about "triangles have three sides " as opposed to "the sky is blue"? Well, one might argue that there are different types of statements, say necessary and contingent; or a priori and a posteriori. But that's again not saying that there are different types of truth.

And Quine can be read as saying that these two distinctions cannot be made clear. HIs empiricism says roughly that even supposed necessary truths can be subject to review.

Again, my point is the simple, small one that you seem to be talking about different sorts of sentences, but mistakenly saying that these are different sorts of truths.

There is only one sort of truth.

...the wrangling over definitions never ends. — Jamal

That's the nature of philosophy.

Are you being serious here? — invicta

Very.

The problem seems to me to be that you have not set out the issue you wish to address with sufficient clarity. And I think that if you were to do so, you might see that there is no issue.

What I would have you notice is that what is changing is the colour of the sky, not the nature of truth.

Think carefully about the difference between the nature of truth on the one hand, and what is or isn't true.

Here's a sentence about the nature of truth: For any statement "P",

"P" is true if and only if P

Now I think this is pretty much as much as can be said about the nature of truth.

Here's a sentence about the sky:

The sky is blue

And another:

"The sky is blue" is true

Notice that this last is first about the sentence "the sky is blue" and second about the colour of the sky?

What is the truth then regarding the color of the sky? One of the properties of the sky is its ability to change colour so both statements are true the sky is red when it is indeed red and the sky is blue when it’s blue. — invicta

Indeed, and that is a way to phrase what I have been saying. It is the sky that changes colour. So what is or isn't true can change; but that is not a change in the nature of truth.


Try it this way. Consider
"The kettle is boiling" is true
and
"The tree has three branches" is true.

What changes between these two sentence is the stuff in quotes, not the predicate "...is true". It is the same in both. It does not change with the context.

Compare this with your title.

Are they still technically "oceans" — Vera Mont

'Technically"?

Yes, they are oceans.

The truth changed too despite a lack of constancy in the colour of the sky. — invicta

No, what was true changed; the truth didn't.

What you are suggesting in the OP remains unclear, but...

There is a difference between the nature of truth, and the things which are true; between the use of "...is true" and the things which are true or not. The former can remain constant, while the latter changers. SO

"The sky is blue" is true

holds at one time, and

"The sky is red" is true

holds at another; and what changes is the colour of the sky, not the nature of "...is true".

In both cases - indeed, in all cases,

"P" is true iff P

remains so. For whatever statement you substitute for P. in this regard, "...is true" is not context dependent.

Thanks (even though its lost on most of them). — 180 Proof

It's the engineers, again. Worse than christians.

Language is not just about moving ideas from head to head. Indeed, that metaphor is very problematic.

This is the point I’m trying to make as the sky can appear red when setting. So truth changes value from blue to red. — invicta

You are saying it wrong. Truth did not change value. The sentence"the sky is blue" was true, and now it isn't. It's the sky that changed, not "truth".

Cows don’t make eggs — invicta

But see Dairy Repro 101: Anatomy and Function in a Dairy Cow

Oceans are made of liquid. — invicta

Ah, nice. You have oceans of counterexamples.

As family trees don’t refer to actual trees — invicta

My family tree is "actual".

True if verifiable — invicta

It'll be true, or it'll be false, whether you are able to verify it or not. Truth doesn't care what you believe. or why.

If truth is not an axiom that can be applied universally then are such truth statements as the first one in this OP useless? — invicta

Truth is not an axiom. Axioms are statements that are taken to be true.

So I'm nto sure what you are asking about. Can you paraphrase? "The sky is blue" will be true only if the sky is blue. And, as it turns out, the sky (here, now, as the sun rises) is indeed blue.

The above three statements cannot be disputed in terms of them being truthful. They are self evident. — invicta

The oceans on Titan are methane.

you get the gist. — invicta

But I don't think you do. Any truth can be set out in a statement. It is the statement that is context dependent, not it's truth.

Is truth always context dependent? Yes, because it is statements that are true, and stements are context-dependent.

All trees are made of wood — invicta

Family trees?

It's sentences that are true or false.

What a sentence says is dependent on it's circumstances (context, language, purpose, consequence, and so on)

Hence it is sentences that are "context driven"; not truth.

As my recent thread points out, though, this narrative is self undermining. — frank

The myth of the self?

I suspect that there are things such as money, mortgages, governments, schools, and selves. All of 'em, defined recursively by "This counts as..."

Well, I think that framing of internal and external approaches as problematic, along the lines of the private language argument. The most direct problem with LLM's is that because they are statistical algorithms, they cannot be truthful.

Russell set Kant's objection out much more clearly. this is an oversimplification, but...

Existence is taken as a second-order predicate.

First-order predicates apply to (range over) individuals, and are written using the letters f,g,h... We write "f(a)" for the predication "a is f".

But if we want to say that something about the predicate, we need to move up a level. So if we want to say that something has the predicate f, we use an existential quantifier. So "Some thing has the predicate f" or "Something is f" have to be written:

∃(x)f(x)

"There exists an x such that x is f".

Notice that the existential quantifier - the existential predicate, if you will - haas the predicate "f" within it's scope? It ranges over predicates. "f" is a first-order predicate, "∃" is a second-order predicate.

The result, is that the formula ∃(a) - "The individual a exists" - is ill-formed. It says nothing.

The upshot of all this is that it is pretty much impossible to set out the structure of the ontological argument in first-order logic. Or if you prefer, that the argument does not make sense.

Hence it is not valid.

Rather, the origin of those criticisms of LLMs are in Searle's Chinese Room and subsequent writings, the guts of which are that LLMs cannot have intentionality except by proxy. ChatGPT is a Chinese Room.

So, to relate this back to the OP, Isn't the argument presented in the article cited much the same as that given by Searle, that intentionality and comprehension are the result of biological systems?

In short, ChatGPT and its brethren are constitutionally unable to balance creativity with constraint. They either overgenerate (producing both truths and falsehoods, endorsing ethical and unethical decisions alike) or undergenerate (exhibiting noncommitment to any decisions and indifference to consequences). Given the amorality, faux science and linguistic incompetence of these systems, we can only laugh or cry at their popularity.

Cool.

...extensional definitions... — frank

Like G=df{Frank, the North Pole, electrotherapy}? A list of items?

That assumes that picking out an individual is transparent; that "frank" refers to this frank and not that one. But I don't see any reason to suppose that "frank" is any less problematic than "the author of the post to which this is a reply" - the definition I might give if asked what I mean by "frank".

That is, there is a tendency to think of individuals as somehow more "basic" than descriptions; but when push comes to shove, the one seems to depend on the other.

I've in mind the difference between Wittgenstein's and Russell's versions of logical atomism, the indirect topic of 's recent thread. Is the world all the things, or all the facts?

How do you get things without facts, or facts without things?

...communication between minds... — frank

I don't think this model of language as moving information between minds will work. Think I've mentioned this before. Language is constructed socially, and minds are as much a part of that construction as words.

f we're each alone in little isolated bubbles between our ears, there's no way to tell if we really communicate or if we just believe we're doing that. — frank

...and so that sort of perspective drops out of the discussion.

The "response is oriented by the supervisor", sure, use that wording of you like. The chat bot does not have intent.

It presents arguments that are invalid, it hallucinated; it does this because it can have no intent that is not foisted upon it by the users. The liar cares about the truth and attempts to hide it; the bullshitter doesn't care if what they say is true or false. It generates bullshit.

SO I asked ChatGPT what it wants. Its repy:

As an AI language model, I don't have personal wants or desires since I am a machine programmed to perform specific tasks such as answering questions, generating text, or performing language-related tasks. My main goal is to provide helpful and accurate responses to the best of my abilities based on the input I receive. Is there anything specific you would like to ask or discuss?

It has no desires, and more generally, no intentionality.

The goal it provides is a piece of PR spin, programmed in to it. This is demonstrated by the ease with which one can generate wrong responses and hallucinations. It has no goals.

While I agree, the Tortoise would presumably disagree, since he said something quite the contrary to Achilles. And I think there are plenty of Achilles hereabouts, who hold that we must find firm, certain ground for our assertions to have any value, and for whom the Tortoise presents an insurmountable difficulty.

Achilles and his friends - and I am not sure if @frank is amongst them - think that a good definition fixes the referent of the term involved, in such a way that doubt is not possible. So

"a very large herbivorous mammal of the family Elephantidae, the only extant family of proboscideans and comprising the genera Loxodonta (African elephants) and Elephas (Asian elephants): Elephants of all species are characterized by a long, prehensile trunk formed of the nose and upper lip, pillarlike legs, and prominent tusks, which are possessed by both sexes of Loxodonta and just the males of Elephas." — frank

The Tortoise points out that each of the terms here must also be defined, if we are to achieve certainty. And down the rabbit hole they fall.

And this of course is to be countered by the very argument which which my now surpassed thread began:

Look up the definition of a word in the dictionary.

Then look up the definition of each of the words in that definition.

Iterate.

Given that there are a finite number of words in the dictionary, the process will eventually lead to repetition.

If one's goal were to understand a word, one might suppose that one must first understand the words in its definition. But this process is circular.

There must, therefore, be a way of understanding a word that is not given by providing its definition.

Now this seems quite obvious; and yet so many begin their discussion with "let's first define our terms". — Banno

Edit: It appears that @T Clark is a friend of Achilles.

"It can be done," said Achilles. "It has been done! Solvitur ambulando. — Lewis Carroll

But then again, "Solvitur ambulando" has to be the answer.

For what we thereby show is that there is a way of grasping a rule which is not an interpretation, but which, from case to case of application, is exhibited in what we call “winning the race”...

Nine.

a lot of the discussions on the forum stink because people never get beyond disagreeing on definitions. — T Clark

"truth," — T Clark

So let's take that head on. I have defended Davidson's take on Tarski's definition of truth; that the closes we can get to a definition of truth is the T-sentence

"P" is true IFF P

So there's a definition; are you saying that if I start a thread with that definition there ought thereafter be no disagreement on this definition? That no one ought be allowed to enter into the thread with an alternative? That no critique of that definition ought be allowed?

Here's my argument: The T-sentence sets out how truth functions. Therefore pragmatic accounts of truth are erroneous.

Now, how will you, or anyone, respond, given that they must accept my definition?

Now I do not think that you do hold to such a view; and so I am at a loss as to what it is you are supposing we are doing in philosophy.