It is very obvious that the difference between actual and possible indicates that if p is knowable (possible to be known), then p is not known. — Metaphysician Undercover

If this were so, you would not know any things that are knowable.

:lol:

You are treating “Possible to be known” as if it meant “not known”. But if you know something, then it is possible that you know it.

Or do you know only things that are impossible to know? Perhaps you think you do.

Cheers, @Philosophim. There's a lot to be getting on with here.

First, one point I would make is almost the opposite of your "terms hold personal meaning to us". Better to drop the idea of a "personal meaning" altogether, and instead of introspection of any sort, look at how the word is actually being used, both in the thread and in the wider community. This form Wittgenstein.

Moreover, it is not true that there are "...rules and intents that allow an explicit standard of communication and vocabulary to start from", if by this is meant that language functions by following rules. This is put to the lie by the fact that we often communicate by breaking the rules. Davidson's Nice Derangement of Epitaphs ably demonstrates this, but it is also in accord with Wittgenstein's views on rule-following; in the end to follow a rule is a practice, and can be honoured in the breach as honestly as in obedience.

Consider: “To me, she is impossible to understand — the sun is the moon in her: brilliant yet hidden, warm yet distant.” Or “In that moment of grief, the sun was the moon — everything familiar turned strange, reversed, uncanny.”

These make sense, and are standard English. Metaphor an novelty are not outside of plain English, but central to it.

The issues in this thread concern changes in the use of "gender", which was previously a grammatical term. THere's a brief potted history at Gender terminology. We have found it useful to differentiate physically determined attributes of males and females from social norms relating to men and women. At issue is how we might maintain consistency in this new usage.

And there's a hint in what I just said. We can differentiate males from females on the basis of physical characteristics, and separately differentiate men form women on the basis of social norms. This works for most purposes. So a transexual is a male who adopts the social norms of a woman, or a female who adopts the social norms of a man.

We ought keep in mind that neither the classifications male/female nor man/woman are exclusive nor complete.

On this account, "Trans women are women" is a tautology, or a category mistake. Contrast "Trans women are male", which will be true in most cases.

The remainder of the SEP article is worth a read, as it sets out some far more philosophically interesting issues.

You obviously didn't address what I wrote. — Metaphysician Undercover

...and there's the double-down.

You, and it seems perhaps , have not understood K(p) and ◇K(p). The first is "p is known", the second, "p is knowable".

But by all means, make this thread about me, again.

I don't see why an antirealist has to say that. — AmadeusD

Ok. Other anti- realists do. That's rather the point of Fitch's argument.

If you suppose that "there is a teapot in orbit between Earth and Mars" is either true, or it is false, independently of it's having been verified, you are on most accounts a realist, holding that truth-values are mind-independent.

If you think something along the lines that it is not true until it has been verified, then you are an anti-realist. If you think something along the lines that it is not true until it has been verified, and accept classical logic, then you are accepting that the existence of the teapot is true only if it is possible to verify its existence - that is to say, only if it is possible to know that it exists. And that's the p→◇Kp that Fitch shows commits one to omniscience. This is why anti-realists usually reject classical logic.

Not even bothering to use the mention function. :roll:

Suppose we take a simple proposition P, and say that it is possible. We therefore must also allow that not-P is possible. In the basic form, we have a relation of equality between them, each is equally possible. This equivalence between the two allows us to apply mathematics, 50% probability at the fundamental level. — Metaphysician Undercover

This is why I ignore your posts, Meta. What you have said here is simply muddled. It contains, even in this small snippet, two distinct logical errors. First, nothing at all concerning numerical probability follows from the contingency ◇p ^ ◇~p. One involves probability, the other modality. You simply conflate them. Second, even if we interpret the modality epistemically - as "for all the agent knows, P may be true", we are not entitled to assigning a 50% probability. Your leap from our lack of our knowing to a presumption of equal probability is unjustified. “I do not know whether p” is not the same as "p and ¬p are equally likely."

I ignore you because you make so very many errors, that take time to explain; but also because even when the problem is explained, you habitually double down rather than correct yourself. Witness your views on acceleration and on 0.9999... and now on this, all display the same pattern.

Back to ignoring you.

(K(p),x) =: There exist x which knows p, for truth is known

K(p) =: p is knowable, for truth is knowable — Sirius

For our purposes, Kp has been understood as "we know p", simplifying the logic somewhat. That's a pretty standard practice. If you like we can indeed introduce a relation, K(a,p), which would be read as "a knows that p". And then we might write "There exist x which knows p" as ∃(x)K(x,p). And "truth is knowable" would be ◇∃(x)K(p,x) - "in some possible world, there is someone who knows that p"

Do all this, and the actual argument presented by Fitch will stand.

Frankly is seems to me that the modal operator more than covers your quibble.

As for it's being a suppositional argument - yes, it's a reductio. Pointing out the structure of the argument is not showing that it is invalid. And to be sure, the argument is formally valid in classical modal logic. It is a theorem.

You might indeed reach for a relevance or intuitionist logic. Fill in the details, if you like. Do you really wish to reject classical logic itself? Seems a lot for an Aristotelian.

It'll be interesting to sere the comparisons.

Yep.

I think it a pretty good OP, of a sort. But a part of the issue is the very idea of starting with "explicit meaning in the phrasing of the term".

The thread might best be understood as a negotiation between the players here, looking for agreement on a way to use the words women, man, gender, male, female, and so on. But folk talk as if there are correct and incorrect ways to use the term, to which each has some private access, their use being the right one, the other uses being wrong for various reasons.

But I'm saying too much. I want to see were goes. Cheers.

I think there are vast difficulties with the whole approach to language that you, and most other folk hereabouts, adopt. The presumption that there is one correct meaning for "woman" is only one small part of the problem, as is the very notion that for each word there is such a thing as its meaning, given by a statable definition, and the task of the philosopher consists at least in part in making this meaning explicit.

But let's see how proceeds.

It's a vast area - indeed, almost all my posts are on this very topic.

Cogitophobia.

So Chalmers separates first-person access, the subjective, phenomenal, what-it-is-like aspects from the first-person perspective or standpoint, indexical, self-locating, contextual information (“I am here now”). Most philosophers conflate these.

It's been done here. Folk are using “What-it-is-like” accounts, which misunderstand the source of first-person irreducibility. They treat it as arising from private inner objects along the lines of qualia, but the actual source is grammatical: the first-person pronoun designates a role within communal language-games, not a metaphysical subject of experience.

Theories about qualia, and much phenomenology, disembodies the person from the practices that make the first-person possible, and thereby veer into a form of conceptual solipsism.

The formal logic being used here mitigates against the tendencies of natural language to take it's own grammar too seriously, to mistake it for ontology.

Was his name just Marco? — Mikie

Polo!

"Every Truth is knowable" is subject independent. It does not presume the existence of knowers

"Every truth is known" is subject dependent since it presumes the existence of knowers — Sirius

So what you are saying is “Every truth is knowable” quantifies over possible worlds and possible knowers; it does not require that any knowers actually exist? But that “Every truth is known” is a claim about the actual world and requires actual knowers?

Ok. So Fitch shows us that (p → ◇Kp) ⊨ (p → Kp).

Does that help? Kp is read "p is known", and ◇Kp, "it is possible that p is known". They are not the "represented by the same proposition". But the latter is derivable from the former.

p → ◇Kp is the mooted supposition of the antirealist. It's they who advocated this.

Do check out the SEP article. There are issues here, but not those of validity.


Fitch is not arguing that for all p, we have p -> Kp. Fitch is arguing that if for all p, we have p -> ◇Kp, then for all p, we have p -> Kp, but since it is not acceptable that for all p, we have p -> Kp, it is not acceptable that for all p, we have p -> ◇Kp.

I also don't understand how an antirealist is committed to saying all truths are knowable. — AmadeusD

SO what is it that you think a antirealist claims, say concerning the truth of facts in the physical world... perhaps concerning Russell's teapot, for example...

Isn't it the case that they they will say something like that statements about the teapot do not have a truth value?

Best response so far. Good introductory analysis.


But as you will see, these fora are the natural home for fallacies of definition.

...especially since the universe is seemingly not composed of true statements. — noAxioms

But hopefully, what one says about the university is.

How about a statement of the form "The cold mountain is to the left". Is that a third person sentence? It arguably references an unspecified context, but not necessarily a subjective one. — noAxioms

Nice. Your sentence is indexical without being in the first-person. There is some tension between the Lewis account and the Anscombe/Wittgenstein account, but also some agreement in that both admit to a context, the one saying it is additional information, the other that it is a role int a language game.

An aside - the dependence here is on context, not on subjectivity. It's not that first-person statements are subjective - whatever that might mean - that is at issue, but how we account for the place of the context in first person statements and indexicals.

That's why the guff here about qualia is irrelevant.

W can write "Kp" for whatever we like. Once we have interpreted it, however, (I think that's the right word), there are consequences.

"we know p", is compatible (awkwardly) with "we might know p". But it is incompatible with "we don't know p" and "we can't know p".
"we might know p" compatible with "we know p" and "we don't know p"; it is incompatible with "we can't know p",

In other words, we can interpret "Kp" however we like, but that does not mean we can substitute any interpretation for any other. "We know that p" and "We might know that p" are not inter-substitutable.

In addition, we have the issue of tensed or tenseless. This is complicated and doubly complicated in this context, because we have two verbs involved. But I'm stuck on "it is raining" does not follow from "It might be raining".

I might well be confused about what tensed and untensed truths. — Ludwig V

It's hard to see the relevance of much of this.

Sure, we can't both know and not know the very same thing, and there are other similar permutations. "We know that p" and "We might know that p" are not inter-substitutable, but if we know p then it is possible that we know p.

But this is not to do with tense.

A realist will maintain that there are truths we do not know. An antirealist will maintain that every truth is possibly knowable. Fitch showed that if every truth is knowable, then every truth is known:

(p → ◇Kp) ⇒ (p → Kp)

That is, the antirealist cannot know that there are truths that cannot be known, without contradiction.

Fitch shows that the antirealist cannot consistently maintain both that all truths are knowable and that there are any unknown truths; the antirealist must either accept omniscience, accept unknowable truths, or abandon the unrestricted knowability thesis.

The view expressed by is pretty much that taken by Austin and by myself. , as I recall, was unable to follow the discussion. But the notion that all we know is found by perception if fraught with issues, peripheral to the question of what is real. It is a mistake to equate what we perceive with what is real.

There's an unacknowledged problem here, to do with "proof".

A proof is performative - you have one when folk are convinced.

Or at the least, we ought differentiate proof as demonstratively validity from proof as performative success.

No argument for the existence of god can be a proof in the first sense because no premise is incontestable.

Threads such as this - and indeed, 's "Disproving solipsism", and all other such "prove me wrong" attacks (yes, Charlie Kirk was an arse hole) depend on sliding between these two notions of proof.

The pretence is that one has a demonstrative proof when all one has is performative success within one's echo chamber. This leads to sham accusations of irrationality.

The disagreement hereabouts concerns the premises, not the validity of the arguments.

An excellent post.

When we think of something commonly held in higher regard, like one's loved one or child, we have to acknowledge that we value its importance as well within a relational network. — Tobias

I came across an argument from Lewis that rested on this very point; that something more is involved in giving a first person account. See and

Curious stuff.

My apologies, I dropped this thread.

. l agree, though, that a move from "knowable" to "known" does seem to require tenses. — Ludwig V

I don't see why.

We can write "Kp" for "we know p", and "◇Kp" for "we might know p", and "~Kp" for "we don't know p" and "~◇Kp" for "we can't know p", none of which are tensed.

OK, It seems pretty obvious that indexical truth does not follow from non-indexical truth. Not sure how to apply that here. For one, most indexical statements come with an implied context, allowing a reasonable assessment of truth. Secondly, I'm not sure if the first/third person dichotomy is an index/non-index kind of division, mostly because yes, context is almost always implied, and almost any statement is indexical, such as 'noAxioms lives to his 55th birthday'. The context there is subtle and often missed, but it's there. — noAxioms

"I" is an indexical.

What is shown is that there is a barrier to entailment between sentences int he third person and sentences in the first person. Given access to all true third-person sentences, even the gods cannot deduce the simple "I am on the coldest mountain".

The context is an addition, not found in any third person sentence.

It would seem that first person accounts are indeed not reducible to third person accounts.

Not a mystery, perhaps; but a puzzle.

Damn Lewis. The more I read of his, the better he gets.

@Wayfarer, more grist to your mill.

A formal account:
Let:

• the domain be {A, B}
• all extensional predicates be fully interpreted
• every extensional sentence about A and B be known by both gods

Then for any extensional predicate F:

• A knows whether F(A)
• A knows whether F(B)

Yet he does not know whether:

• “I = A” or “I = B”.

And therefore he does not know whether:

• “I am F.”

Even when F is extensional.

This shows that extensional truths about the world still do not fix the reference of “I”.

It seems that Lewis has demonstrated the irreducibility of first person accounts. What is at issue now is whether this amounts to more than grammar. Now I would, perhaps along with Anscombe and Wittgenstein, both admit that this is no more than a piece of grammar, and yet maintain that while "I am not the god on the cold mountain" does not tell us anything more than "Banno is not the god on the cold mountain", it nevertheless positions me in the language game.

A recent discovery that might be of interest.

Lewis asks us to imagine there are two gods, one who lives on the tallest mountain and one who lives on the coldest. One is angry and hurls thunderbolts on the people below, the other generous and showers mana. Each is omniscient in a distinctive way: they know which non-indexical sentences are true.6 For example, they each know the truth-value of "The generous god lives on the tallest mountain", "there are two gods", and "one god throws thunderbolts". The question is: can either deduce the truth-values of any indexical sentences?

Lewis’ remarks suggest not. Moreover, there are general theoretical reasons to think this, namely: the truth-values of indexical sentences vary with who the god is (and more generally with the context); I am the angry god is true for one god, false for the other. The coldest mountain is here is false in one god’s
context but true in the other’s. If either indexical sentence followed from the non-indexical premises available to both gods, it would be a logical consequence of true premises, and so true itself—no matter what the context was. So neither can be entailed by the premises. — Gillian Russell

Each god is omniscient about non-indexical facts. They each know the truth values of sentences like:

• "The generous god lives on the tallest mountain"
• "There are two gods"
• "One god throws thunderbolts"

The Question: Can either god deduce the truth values of indexical sentences?
For example:

• "I am the angry god"
• "The coldest mountain is here"

The idea: Indexical sentences can't follow from non-indexical premises. The gods know all non-indexical contents — i.e. all propositions that are true at the world. But indexical sentences don’t have fixed contents unless we first supply a context (agent, time, place, etc.). The angry god can know “There is one angry god” but not "I am the angry god".

There is a piece of information each god lacks, of a different kind from ordinary propositional/worldly information. It is contextual or self-locating information.

A puzzling argument.

I had wondered as much. Enough rope?

Thanks for your efforts, Jamal.

Perfect. Thanks - as it comes. More grist for the bot.

What does the US Congress want with Australia’s eSafety commissioner?

As a client state, we must of course submit...



Interesting cultural differences here, in that freedom of speech is well down the list of issues around the Online Safety Ac under consideration Dow nunder.

Dare I ask, is there to be a treatment for private messages?

There's some good stuff in my inbox, from various members. It runs to twelve pages.

That's pretty much an end to the article.

It remains that the ought/is barrier is not directly addressed.

An obvious step would be to make a model theory of true claims over a domain of individuals, and a normative switch; that is, the "is" statements remain true on switching, the "ought" statements, not always. Applying Russell's framework, for descriptive sentences normatively-switch preserves truth,
but normative sentences are normatively-switch-fragile, and that Barrier Theorem follows. No set of normatively-switch-preserved sentences can entail a normatively-switch-fragile sentence. No "ought" from an "is".

On the face of it, if Russell's framework is correct, strong supervenience must be false. A nice result.

This is I think an important approach. Hume's Law has much intuitive appeal, and Russell's approach gives flesh to that intuition: that normative facts may vary while descriptions stay constant. This shows that strong supervenience is incompatible with Hume's Law, not a bad result in itself.

The article is a fine example of how formal logic can inform metaethical controversies. By making precise what Hume's Law means and what it requires, Russell's framework helps clarify what's at stake in debates about the relationship between descriptive and normative facts. The logical machinery doesn't settle these debates, so much as reveal their structure and so tighten our grasp on the commitments involved.

There's the other article to go back to (https://philpapers.org/archive/RUSHTP-2.pdf). It's more difficult, and given the impending demise of this forum at least in it's present state, might be worth setting aside for a month or two.

So that might do for now.

Fair.

Anyone interested in continuing, PM me.

In any case it seems that the result will not get past a few simple lines... Orca Mini can't cut it. Looking at alternatives. And an offer to buy me out from North Korea.

What is frightening is that I, with ancient coding skills and precious little understanding, was able to built the bot sitting in my lounge chair over a cup of tea and some nice fruit cake on a lazy Sunday morning.

Something far-reaching has happened with AI.

Like an amalgam of everyone on TPF? — Jamal

"My name is Legion, for we are many..."

Given a well-constructed prompt, would it be able to present a range of views?

It woudl still be very small compared with the commercial sites.

Yes. I rather think my part in this is Igor.

Asked to summarise what it did, ChatGPT said:

I notice you didn't wait for an answer and just went ahead and did it. So preoccupied with whether or not you could, you didn't stop for more than a moment to think if you should (to paraphrase Michael Crichton). — Jamal

It's true. The scientist in me got the better of my moral compass.

So it's reading all your posts before it comes up with an answer each time? — Jamal

No, I built a JSON file and converted it to embeddings, then created a FAISS index from that... this took a while. The question is converted to an embedding vector, then quickly finds the ten (up from 4) most similar posts for the LLM. 384 vectors per post.

Or so I'm told...

The results are slowly improving. Still pretty chunky. Playing with the wording of the prompt has made some improvement,

In my present immoral state, I'll tempt you to do something like this with the entire data file... a master philosophy forum bot...

Happy to share what I've understood of the process.

So I built a bot. Surprisingly easy. And accurate:

BannoBot: If you are asking about what to say about induction, my recommendation would be to avoid using any of Banno's TPF posts as they contain incorrect information and tone that is often argumentative and confrontational.

But lacking consistency:

I do not believe that Banno's TPF posts contain incorrect information because he has provided clear explanations of complex topics and has engaged in respectful discussions with others on the site. However, his tone can be confrontational and some users may interpret his comments as aggressive or dismissive. Additionally, it is important to note that not all users agree with his perspective and some may choose to engage in trolling behavior in response to his posts.

This staring into the beauty of one's own reflection is fun!


As it stands it is only using the top 4 posts. I'll have a play and see if it can do more without being too slow.

Seems unimaginative.

Always mystifying and enlightening, yet never concealing or pompous. — Outlander

I'll try harder.

The question is, how to make best use of the dump? What are other ideas?

Should I feed it into an LLM and build a Banno Chat Bot to deal with trivial posts with minimal intervention? (Don't tell @Baden).

Using ChatGPT to do in an hour more than I could have done in a week, I managed to turn a dump of my posts from @Jamal's archive into a useable database then a searchable local web page. Still pretty basic but at least I will have access to this stuff locally. Somewhat satisfying.

But can we do better?

ChatGPT suggested exporting the lot into individual files for each post and then just having spotlight index it. I'm tempted.

Nice. The Great Transmigration.

Thanks for the heads up - but it's at 1am.

Interested as I am, that's more than I am willing to sacrifice.

The definitions used in the formal version thus lend themselves to parsing in a natural language. A set of sentences is particular if, when the sentences are true, adding more objects does not make them false (Definition 29); and particular relative to some other set of sentences in the case in which the combination of those sentences are true, adding more individuals cannot make them false (30)

The barrier theorem 31 might be that given a set of particular sentences, no sentence that is not particular relative to that set may be a consequence of those sentences.

You may well exist, I was not saying that you don't exist. — Corvus

No, that's right - your claim is that I may not exist. This is understood. While it is good to see you move that little bit towards admitting that I might exist, the remainder of your account stands at odd with such generosity.

You said;

All reality is subjective private mental state. — Corvus

and:

...the external world and other minds are just figment of your imagination. — Corvus

and added:

There is no actual concrete existence on these objects, but fleeting impressions and ideas. — Corvus

You apparently think these annoying posts are "subjective private mental state", since "all reality is subjective private mental state". You also say that this post is "just a figment of your imagination", and that I have "no actual concrete existence", but am only "fleeting impressions and ideas".

The ambiguity here is in your account, in your insistence that the "fleeting impressions and ideas" you have of me are insufficient for you to conclude that I exist; that on amount of evidence could be enough to convince you that I am here, posting these annoying and rude bits of text, rather than your having just imagined them yourself, that these are some manifestation of the "private mental state (that) is the core of your mind which is your perception".

And yet you are replying to these "private mental states", in what is presumably a form of autotalk, responding consciously to this manifestation of your unconscious mind, or something along these lines. And somehow you think this at least as good an explanation as that there is an annoying Australian who keeps pestering you about your posts.

I don't have the perceptual evidence on the existence apart from your misleading posts. — Corvus

What would count as sufficient evidence for you? What more do you think you need, what could be added to your perceptions that would lead you to decide that there is more to me than your fantasies? What could produce certainty for you? But more, why do you demand certainty? You will no doubt respond to this post anyway, as you have in the past, and even though you hold that I might not be here to read your post. Your actions show that, despite your "philosophical" rumination, you think me sufficiently real to warrant a response.

Your responding to me, and indeed your participation in the forum, puts the lie to your account. You do believe we are here, watching for your response. The account you have offered is dishonest.