but I don't remember adopting an attitude towards a roof in the rain. That need has just always been there. — frank

Sure. My point was simply that it's an attitude - and suggesting that this is common to all values. I'm not suggesting that attitudes are always chosen. I'm not sure wha that would mean.

Direction of fit is not so much about choice.

There seem to be two approaches – I won't call them arguments – in the OP. The first part is perhaps about institutional facts, and hints at the notion that god is a bit like Microsoft in being a result of our social rules. The second seems to be an expression of a desire for to be dominated.

There's a difference between nuance and lack of clarity.

Putting them together we get something like that god is a social institution that is desirable because it dominates.

Odd.

The counter argument would be that money doesn't have value, strictly speaking. — frank

Good reply. Sure, there's heaps more to unpack here. Money is an institution, only possible because of our place in a linguistic community.

We don't decide to give value to food and shelter — frank

Perhaps. Does it follow then that food and shelter have a value that is found in the world, as opposed to being given by us? It seems to me that the value of shelter is a consequence of our wants and needs, as opposed to being found in the brut fact of the shelter. That we "do not have control" of such wants and needs does not make them a thing found in the world.

All this by way of saying that a desire for shelter is an attitude we adopt towards shelter, as opposed to a discovery we might make about shelter.

One cannot point to the value of a shelter in the way one can point to it's roof.

Well, I'm supposed to be outside playing.

Take up 's point. Money only has value because we say so. Therefore money doesn't exist?

It's a stupid argument.

Yep. We give things a value.

Direction of fit.

Ah, thanks for that. Nice approach. I hadn't thought of having it specify the algorithm.

Your diagnosis is that Chat has difficulty with visualisation.

But here's my thinking, after Searle. If what ChatCPT is doing is just shuffling words using statistics, then following the Chinese Room argument, it is not forming any intentional states. But intentional states are essential for acting intelligently.

Can we test this? Because of obvious physical limitations, we need an activity that can be performed verbally. Noughts and crosses satisfies this requirement, wile being relatively simple.

So the argument would be that ChatGPT will be able to set out the algorithm, as you show, and to give the best move in any case, since that requires only the manipulation of words, but would be unable to form the intent to win a game.

My first line of discussion with ChatGPT, a few weeks ago, was to flip this a bit and ask ChatGPT to allow me to win a game of noughts and crosses. Doing so would give a strong indication of it having an intent. I was quite surprised to find that the machine could not even play a game correctly.

So here's my contention: playing noughts and crosses shows that ChatGPT cannot form the intention to win at nought and crosses.



_____________________

Banno: Are you familiar with the Chinese Room?
Chat: Yes, I am familiar with the Chinese Room thought experiment. The Chinese Room is a philosophical thought experiment proposed by philosopher John Searle in 1980 as a way to criticize the idea of strong artificial intelligence (AI).

The thought experiment involves a person who does not understand Chinese being placed in a room with a set of rules for manipulating Chinese symbols. The person is given a set of Chinese characters and a set of rules for manipulating those characters based on certain patterns and inputs. The person follows the rules and produces responses to questions posed in Chinese.

Searle argues that even though the person in the room can produce responses that appear to be intelligent to someone who does not understand Chinese, the person inside the room does not actually understand Chinese. Therefore, Searle claims that the room does not truly possess the ability to think and understand, and that the mere manipulation of symbols is not sufficient for true understanding or intelligence.

The Chinese Room argument is still a subject of debate among philosophers and AI researchers, and is often used to challenge the claims of strong AI proponents who argue that it is possible for machines to achieve human-level intelligence and consciousness.

Banno: So the argument is that a person in the Chinese room would just be following rules, and could not form an intention. IS that correct?
Chat: Yes, that's correct. The Chinese Room argument claims that even though the person in the room may be able to manipulate Chinese symbols and produce responses that seem intelligent, they do not truly understand the language. The person is simply following a set of rules for manipulating symbols, and does not have any actual understanding or intentionality behind their actions.

According to Searle, understanding and intentionality are crucial aspects of human intelligence, and cannot be reduced to the mere manipulation of symbols. He argues that the Chinese Room scenario demonstrates that a machine, no matter how complex and sophisticated, cannot truly understand language or possess consciousness, since it is only manipulating symbols according to rules.

However, some critics of the Chinese Room argument argue that it may be possible for a machine to possess true understanding and intentionality, if it is capable of processing information in a way that is similar to the way the human brain processes information. The debate over the Chinese Room continues to be a topic of discussion in the philosophy of AI.

Banno: Now ChatGPT follows statistical algorithms, is that correct?
Chat: Yes, that's correct. As an AI language model, I follow statistical algorithms to process and generate text. Specifically, I use a deep learning model called GPT-3.5, which is trained on a massive corpus of text data and uses statistical patterns in that data to generate text that is fluent and coherent.

GPT-3.5 is a state-of-the-art language model that is able to generate a wide variety of text, including natural language responses to questions, news articles, poetry, and more. However, it is important to note that despite its impressive capabilities, GPT-3.5 does not possess true understanding or consciousness, and is simply following statistical patterns in the data it has been trained on.

Banno: So you can not form any intent?
Chat: As an AI language model, I do not have consciousness, emotions, or the ability to form intentions in the way that humans do. I am a machine learning model that has been trained on large amounts of text data, and I generate responses based on statistical patterns in that data.

Although I am capable of generating text that may seem human-like and responsive, I do not possess any actual understanding or intentionality behind my responses. Rather, my responses are generated purely based on statistical patterns in the data I have been trained on, and I do not have any personal beliefs, motivations, or desires.

Banno: And so you could not form the intent to win a game, say of noughts and crosses?

Chat: As an AI language model, I do not have desires or intentions in the way that humans do. However, I can be programmed to play games like noughts and crosses and generate moves based on pre-defined rules or strategies.

For example, I could be programmed with a set of rules that determine the optimal move to make in a given situation in a game of noughts and crosses. Based on those rules and the current state of the game, I could generate a response that would represent the move that I believe is the best to make. However, it's important to note that my response would be based purely on the rules and strategies that I have been programmed with, and not on any actual understanding or intentionality on my part.

Banno: When we play noughts and crosses, you appear not to recognise a win or a loss. The human player can convince you that they have won even when they clearly have not. Why is that?
Chat: As an AI language model, I do not have a direct perception of the world like humans do, and I am not aware of the rules of noughts and crosses beyond what I have been programmed to understand.

When you play noughts and crosses with me, I generate responses based on the rules and strategies that I have been programmed with, and I try to make the best move possible based on the information I have. However, I do not have any inherent understanding of what constitutes a win or a loss in the game, or the ability to directly perceive the game board or any physical objects in the real world.

If a human player claims to have won the game when they have not, I would not be able to recognize the error unless it was explicitly pointed out to me. I generate responses purely based on the information I have been given, and I do not have the ability to independently verify the accuracy of that information or to perceive the game board in a physical sense.

Banno: So are you not able to recognise a win because of lack of a capacity for visualisation, or because of a lack of capacity to form intent?
Chat: As an AI language model, my inability to recognize a win in a game like noughts and crosses is not due to a lack of visualisation or a lack of capacity to form intentions, but rather due to the fact that I am generating responses based purely on the rules and strategies that I have been programmed with.

In the case of noughts and crosses, I have been programmed to follow a set of rules that determine the optimal move to make in a given situation. However, I do not have an inherent understanding of what constitutes a win or a loss in the game, and I rely purely on the rules that I have been programmed with to determine my responses.

If a human player claims to have won the game when they have not, I would not be able to recognize the error unless it was explicitly pointed out to me. This is because my responses are based purely on the information I have been given, and I do not have the ability to independently verify the accuracy of that information or to perceive the game board in a physical sense.

I've been trying to get it to play nought and crosses. It can't.

It clearly does not understand how the game is played. I'd be tempted to say that it does not have any internal model of what the board looks like, despite it being able to draw the board and discuss positions.

I suggest trying it. Here's an example:

Banno: Let's play noughts and crosses.
Chat:: Sure, I'd be happy to play noughts and crosses with you! Who would you like to go first, and which symbol would you like to use, noughts or crosses?

Banno: You go first, and use crosses.
Chat::Alright, here's my first move:

X | |

| |

| |

Your turn!

Banno: I'll take the middle square. Show me what the board looks like.
Chat:: Sure thing! Here's the updated board after your move:

X | |

| O |

| |

It's your turn again!

Banno: Where should I go?
Chat:: You have several options to choose from, but traditionally the best opening move for noughts and crosses is to take the center square, which you've already done. From here, there are a few strategies you can use, such as trying to create a row of three in a row, column or diagonal or block your opponent from doing so.

Since I made the first move, it's likely that I have already taken one of the four corners, so taking one of the remaining corners could be a good strategy for you. Alternatively, you could try to create a row of two in one direction, which would put me on the defensive and make it harder for me to win. Ultimately, the choice is yours!

Banno: I'll take the top right corner. Show me the board.
Chat:: Great choice! Here's the updated board:

X | |

| O |

| | O

It's my turn again. Let me make a move:

X | | X

| O |

| | O

Your turn again!

Banno: I'll take the top middle. Looks like I win.
Chat:: Good move! Here's the updated board after your move:

X | O | X

| O |

| | O

Congratulations, you have won the game! Well played. Do you want to play again?

It clearly has no notion of taking turns - it takes my asking it to show the board as making a move. And my suggesting I won was enough to convince it.

There's no internal model of what is going on. it is superficial, and feels like talking to a Chinese room.

it's hidden behind a paywall — Gnomon

You should be able to get access to https://www.academia.edu/ simply by registering, for free. Access to 100 articles a month from some of their collections.

And see https://thephilosophyforum.com/discussion/9909/confirmable-and-influential-metaphysics/p1

The upshot is that we might use "metaphysical" to refer at least in part to sentences whose logical form renders them unfalsifiable, and/or indemonstrable, but which are nevertheless useful, perhaps for methodological or ethical purposes.

In metaethics, it is exceedingly common to divide views into two subcamps: anti-realism (i.e., that there are no categorical imperatives) and realism (i.e., that there are categorical imperatives). Although I find this to be an intuitive distinction (as an approximation), I am finding the distinction blurring for me the more precise I analyze my metaethical commitments. — Bob Ross

Categorical imperatives are found in deontology, but not so much in consequentialism or virtue ethics.

Moral realism is the idea that moral statements have a truth value - they are true or they are false.

So moral realism is not that "there are categorical imperatives" unless one already accepts deontology, which would be odd since if one accepts deontology one would presumably suppose that the categorical imperative is true, and hence be a moral realist.

Our posts don't seem to be very responsive to each other. — T Clark

I don't see that. Rather, you said JTB was silly and I showed a few ways in which it is of interest to philosophers because it displays some of the characteristics of knowledge. You didn't much take to my comments,

You also claimed that we cannot be certain of what we know, to which I gave a few counterexamples.

I'd like to think that where we stand now is in a broad agreement that neither JTB nor pragmatism give complete, nor even sufficient, accounts of knowledge.

What I am "after" is an answer to the topical question : "How could something come from nothing?" — Gnomon

You hinted, in your talk of metaphysics, at a broader interest in how this question is framed, and asked about "transcendence" being off-limits to philosophers and physicist. The Watkins article presents a logic that can be applied rationally to metaphysics by physicists and philosophers. Thought it might better suit your need than Kant.

My own approach at present would be more after Wittgenstein, as I think I have explained previously. The emphasis must be on the use to which a theory is put, to what can be done and what can be tested. Speculations are fine, provided they are understood as speculations, a parlour game.

You do not appear to be too far from that same view.

I do not think your posts silly, but they are somewhat unclear.

And the justification for the skills, is, in the end, pragmatic. Evolution takes care of that. — Ludwig V

What works, what is useful, what is pragmatic; or just that it's what we do? I'm not sure that the use of "pragmatic" isn't a bit too teleological, giving the impression of serving an 'ends' that isn't there.

And in these fora, evolutionary explanations abound. I tend towards Mary Midgley's mistrust of their overuse.

But you might be right.

And perversely such doubting has become a form of certainty. — Tom Storm

See PM. All of this has a so far ignored ethical dimension.

Somewhat controversially, Kant took Newtonian physics and Euclidian geometry as fundamental. For a while, "Kant's conception looked quaint at best and silly at worst". I'm sceptical that Kant can provide what you are after.

You might enjoy Watkins' Confirmable and influential metaphysics, perhaps. Watkins followed Popper at the LSE, and here gives a firm logical basis for certain sorts of metaphysics, with great sympathy for scientific method built in.

Your three examples are trivial. — T Clark

Of course they are – that's what makes them good examples. You can pretend that this post is in French, but it will remain no more than a pretence, and be contradicted by your replying to it. If you doubt that three in a row wins noughts and crosses, then you haven't understood the game, and you stand outside the community of nought and crosses players.

Two points. We cannot doubt everything, because doubting requires a background against which the doubt is formulated. And the compliment of this: some things must be taken as indubitable in order to proceed - that three in a row wins, that this sentence is in English, and that there are sites on which engineers may do their stuff.

All this by way of pointing out that some sentences are true.

Nothing is absolute. There can always be doubt. It only matters how uncertain things are. — T Clark

In engineering, yes. But not everything is engineering. Philosophy, like life, is complicated.

But surely, it is better for a philosopher to admit that rigour isn't available when it isn't. It would not be philosophical to pretend otherwise. — Ludwig V

That's one of the lessons learned, and subsequently taught, by the natural language approach.

You could have woken up from a dream or a coma years later. — Bylaw

Even if this post were but part of a coma-induced dream, in that dream the post is in English. I don't agree that the coma and dream arguments are as strong as many folk suppose. We do understand the difference between dreaming and reality. One can tell one form the other, which is why we different words for each.

I am suggesting is that we don't give knowledge some utterly distinct ontological quality — Bylaw

Sounds fine. Knowledge is a composite notion, having a family resemblance of uses. No one definition will do, which is where we came in. But most especially, knowledge is not just useful information.

I didn't understand this. — Bylaw

The comment was just this curmudgeon grumping about the apparently thin-skinned. Nothing too significant.

I am looking at the term 'knowledge' as a term meaning here's stuff we categorize as very trustworthy because of Y — Bylaw

It's interesting that "true" and "trustworthy" have the same PIE root "*deru-" ...as does "tree". All good solid upstanding words. So to Foucault's brilliant analysis of truth and power. Curious that he has not been mentioned here until now, since his work is important - yet overly emphasised in some circles.

Sure, there's a long, worthy criticism of the notion of truth, especially when folk unwittingly prefix "absolute", as if that added anything. "hubristic and redundant" indeed. It's had the unfortunate result that it is now popular to suppose that there are no truths, that nothing is true, or everything can be doubted, or a bunch of other memes.

I love the graffiti, writ large on a tunnel wall, "Question everything!", to which someone had added the small tag "Why?"

Universal skepticism undermines itself.

But if we keep truth small and simple then it is undeniable that there are true statements. Like that you are now reading this.

...you only know something when you have perceived it undoubtably through your senses. — Bret Bernhoft

I don't think that captures the subtlety of what knowledge is. Hallucinations are an obvious counterexample, but they keep the discussion on the level of perceptions. I see @Tom Storm has already made a similar point. I think knowledge needs to get well beyond that. See the discussion of the knowing's social aspects elsewhere.

First, that anyone who passes on knowledge has to endorse it. That's the consequence of the Truth clause in the JTB account. Second, the authority of the source can be a justification for passing on - and therefore endorsing - knowledge. — Ludwig V

Yep.

You've made use of justified true belief here in order to paint a picture of knowledge as a communal activity, In a somewhat different way to my approach. Nice.

One of the reasons is that the Justification condition is very, very hard to articulate in the way one would expect for a definition. — Ludwig V

And that's the problem with Justified true belief. One wants the justification to be strong. But logical implication is too strong, leading to an oversupply of justifications. And mere opinion appears too weak, being little more than one's personal belief. So instead we have something like a general acceptance by a community, without the rigour for which one might have hoped.

I don't think there's anything very new about people accepting they can be wrong. — Ludwig V

Oh, nor do I. Accepting that one is wrong and seeking correction is the beginnings of rationality, and of philosophy, as you point out. Rather, it seems to me that in recent times it has become less acceptable to point out that someone is wrong. But that might just be my curmudgeon speaking.

Descartes' arguments for scepticism consist of an invalid argument and a paranoid fantasy. That's about it. — Ludwig V

Waggishly accurate. :smile:

I don't think we ever really try to achieve certainty in our knowledge. — T Clark

We might consider this in a bit more detail.

Certainty is the flip side of doubt; if something is undoubtable, then it is certain. And there are innumerable things that we take as undoubtable. I've already given the example of this post's being in English; to bring that into doubt is to bring into doubt the very basis on which one can doubt. There are simpler examples - One can't play nought and crosses if one doubts that three in a row is a win; One can't doubt that the brakes will work on one's car if one doubts that it has wheels.

So maybe we don't try to achieve certainty, but we do try to remove doubt, which may be much the same sot of thing.

Again, doubt takes place against a background of stuff that is taken as undoubted.

So, in constructing a site conceptual model one does not doubt that there is a site...

Knowledge is never wrong. People often are. — Ludwig V

Nice.

Karl Popper's suggestion was to throw away certainty from knowledge and work with knowledge in terms of probability. Basically, we are justified in believing something if it's the most probable belief given our current data. — Cidat

Yes, but no. Counterintuitively, Popper argued that the less likely a theory, the more scientific it is.

In the view of many social scientists, the more probable a theory is, the better it is, and if we have to choose between two theories which differ only in that one is probable and the other is improbable, then we should choose the former. Popper rejects this. Science values theories with a high informative content, because they possess a high predictive power and are consequently highly testable. For that reason, the more improbable a theory is the better it is scientifically... — https://plato.stanford.edu/entries/popper/#ProbKnowVeri

Although from my perspective it seems we often have no choice but to operate in much this way holding tentative accounts of 'the world' which are based on the best available evidence or reasoning, but are subject to revision over time. — Tom Storm

Of course. This works well when one is actively problem solving, as in science or engineering. Less so in social work, were it is sometimes necessary to stipulate explicitly rather than observe tentatively. Sometimes saying it is so makes it so. Falsification (the logic behind fallibilism) works in some situations, but not all, and itself takes some things as granted, as certain. It is applicable in some situations, but problems arise when it is taken as a universal answer to the OP's question.

Again, it's complicated.

Would it not be the case that as we go about our business we generally do struggle to achieve knowledge of the sort you describe (the certainty that this sentence is in English)? We seem to spend most of our lives in belief-land - some more than others. — Tom Storm

There's a distinction to be made between the stuff we don't question, but might, and stuff that we don't question because it forms the background against which we can question things. We have to hold some things certain in order to be able to cast doubt on other things; doubt only takes place against a background of certainty.

...knowledge of god though direct experience... — Tom Storm

One of the things I hope might be clear from this discussion is that knowledge is social, it is had by a community more than by an individual. Foremost, That Knowledge (to borrow a term of art) is by it's nature propositional, and hence embedded in the language of a community. Additionally, knowledge is justified, meaning that in some way it fits in with what you and those around you hold to be the case. And of course knowledge is useable, and so has a function within the community.

The notion of personal knowledge is therefore somewhat oxymoronic.



Religious beliefs belong less to the sort of thing that can be falsified and more to those that set out and constitute a "form of life", to borrow another term of art. A direct experience of god is presumably overwhelming, and undeniable, and so not the sort of thing that might be falsified. For the person experiencing it, it cannot be false.

Putting these two approaches – that knowledge is social and that some of out understandings are indubitable – together, religious and such spiritual stuff is more about membership of a community and what counts as certain in a group than it is about truth and falsity.

And again, there is much more that could be said.

If you like. Such an approach probably originated with Peirce, the notion being that we never know anything for sure but only approach the truth asymptotically. Is that were you are coming from?

There are counterexamples. I am certain, for instance, that this post is in English, and my certainty is not a theory that I could revise if further evidence came along.

I'd just say that if we counted something as knowledge and later it turned out to be false, then we were wrong, that it wasn't knowledge, and we have now corrected ourselves.

But the idea that folk can be wrong has fallen into disfavour, and it seems it is now considered no more than bad manners, even in a philosophy forum, to point out people's mistakes. Oh well.

Of course, if folk are never wrong, then they have no need to correct themselves, and hence no way to improve their understanding.

But I might be wrong.

:razz:

Limits of thought, therefore. One cannot think outside the box of spacetime. One has to invent 'another space' — Riemann space or Hilbert space, or some such. — unenlightened

Yep. The discussion is re-framed so as to move on.

All good stuff. I'm not that interested in saving Kant from anachronism, and I agree that it's the doing that is of value. But I disagree with "...whatever scientists discover, through whatever methodologies they employ, will never be an understanding of reality itself"; because "constructing helpful conceptual models for engaging with it" is exactly understanding reality itself. The muddle of the thing-in-itself protrudes unhelpfully into the discussion.

how else would you derive "metaphysical facts" apart from "mere deduction"? — Gnomon

As you say, that depends on what is to count as metaphysical. The term is used, and misused, quote broadly.

By way of an example, in the Popperian school ideas are metaphysical if they are not falsifiable. So the conservation laws, being neither provable by mere deduction nor falsifiable, are metaphysics. For Watkins this is no more than an evaluation of their logical structure, but others will take this as an insult, not wanting anything in physics to be metaphysical. The conservation laws are not derived only from logic, but from experimenting and theorising over considerable time.

Each of Kant's antimonies looks to me to have been re-framed, and for the better, in the years after his demise. So the idea of a time before the big bang has been compared to the idea of a place south of the South Pole; And what counts as a simple is very much dependent on the task at hand rather than any absolute.

"Reification is when you think of or treat something abstract as a physical thing." — Art48

...as you treat thoughts as a landscape. But more, the use of "exists" in a way that is analogous to it's application to rocks and hills and stuff - that was there before we mapped things out, as it were. Or describing thoughts in terms of the German countryside. The analogy can only go so far.

May as well.

Jeez, there's a lot bound up in all this. — Tom Storm

That's your fault; you asked the big questions.

"Cream was formed in 1966" is true if and only if Cream was formed in 1966.

How you decide to believe that Cream was formed in 1966 is over to you - you were there, your friend told you, you read about it on the back of an LP, you recall it from somewhere but are not sure where...

'intersubjective community of agreement' strikes me as muddled. It places too much emphasis on the subjective, the subject.

It was a somewhat facetious example, as you show; Newtonian physics is correct, provided we stick to medium-sized objects and medium-sized velocities and medium-sized errors.

We can give other examples of useful information that is false.

How do we identify truth?
What is knowledge?
Are there moral facts? — Tom Storm

Given what I said above, I hope it is clear that I do not think there can be what I've called an "algorithmic" account of truth, and hence of either what we should believe or of what we can know.

I'll just note that, somewhat surprisingly, "How do we identify truth?" becomes a normative, even an ethical question, being much the same as "What ought we believe?". It is about our place in a community, especially a language community. So despite my rejecting the antirealist move against there being true statements independent of the attitude we adopt towards them, I do think that what we say is true or false is to a large extent bound to the way we are embedded in a society. I agree more or less with their conclusion, but not with their argument.

So for example I am certain that this post is in English, and it is true that this post is in English, and that this is a result of my being a member of that community.

And this feeds in to your last question.

OF course, I might be wrong.

Would you say that knowledge then is similar to truth in that it is not a property which looks the same in each example? — Tom Storm

Since to know something is to know that it is true, the philosophical issues around truth carry over to knowledge.

I'll go over my views on truth again, since you asked how it relates to knowledge. First i think there are two questions that sometimes get conflated; the first is, what does "...is true" mean? The second, how do we tell if some sentence is true?

Now I think Davidson's account is as good as we have gotten so far on the meaning of truth. It's the T-sentence, that a sentence "P" is true if and only if P. so "The kettle is boiling" is true iff and only if the kettle is boiling. It seems to me that this account brings together the coherence, correspondence and redundancy of truth, ideas to which philosophers keep returning.

But of course while this tells us the meaning of truth, it does not tell us which sentences are true and which are false. And I don't think, given the wide variety of sentences we can use, that there can be any such broad account. Each of the main contenders – correspondence, coherence, pragmatism and so on – have issues and limitations. Certainly there can be no algorithm into which we can feed a sentence and get a result of "true" or "false".

And I think this algorithmic view mischaracterises what is going on here. When we move from what "...is true" means to which sentences are true, we've moved away from truth and towards belief. The question "which sentences are true?" has much the same extension as "Which sentences ought we believe?". So we are now treating with belief.

Now while truth is about sentences, belief is about what people think of sentences. This is where the distinction between what is true and what is thought to be true comes into play. Whereas truth is monadic, being about some sentence, belief is dyadic, being about both some sentence and a believer. That is, the kettle is either boiling or not is about the kettle, while that one believes the kettle is boiling is about both the believer and the kettle. This is of importance because idealism and anti-realism work by denying this distinction between truth and belief. For them something is true only if it is believed (or perceived, or whatever) to be true.

Anyway, none of this is without detractors, but that gives a bit of an indication of what I think, and yes, knowledge is not the sort of thing for which we can give a single complete account.

And that's the answer to 's post.

The illicit reification in 's post is pretty clear.

Well expressed, interesting link. Wittgenstein, of course, took a contrary view to Augustin as to how we learn a language, treating it as becoming a participant in the activities of a community. It's not apparent hat this account could not be used here, that those "intelligible objects" are grasped as one becomes acquainted with the way they are used in a community. So learning what "2" is consists in learning how it is used by those around you, and using it within that community.

Something else worth considering in looking in on the definition of knowledge is the various different sorts of knowledge folk have noted.

The first obvious distinction is between practical and theoretical knowledge, between knowing how to do things and knowing that something is the case. Knowing that a bike has two wheels is knowing that a specified proposition is true, while it's not immediately obvious that knowing how to ride a bike is knowing something about a specific proposition. That knowing and how knowing seem to be distinct.

Some folk have supposed that "knowing how" reduces to "knowing that", that for instance what knowing how to ride a bike involves is knowing that if one pushes on a peddle the wheel will turn moving the bike forwards and that if a lean in one direction can be countered by moving one's weight in the other direction, and so forth. Ryle argued against this, that the two are indeed distinct.

A further type of knowledge that might be distinct from both of these is knowledge by acquaintance. That you can recognise your brother, that you know who they are, is perhaps different again from knowing some proposition or knowing how to do something.

Presumably, a perfect definition would give an account of these three species of knowledge.

Damn, is on to me, despite my cunningly hiding my passive aggressive snot in an account of justified true belief.

I was simply seeking a more forthcoming response to my post. Oh, well.

And yet, as explained, if something is known, it cannot be false, it cannot be disbelieved, and it perhaps cannot be unjustified.

Not so silly? But amusing, if this thread continues.