Does TPF now disparage as vanity or prejudice or laziness the preference of some posters to decline to use AI at all? — bongo fury

No, the idea is to encourage specific good practices in the use of LLMs, assuming they're going to be used. We are not encouraging people to use it if they're not already.

Which parts of "research, brainstorming, and editing" does that apply to? — bongo fury

The meaning of "substantial" use is detailed in "2. The Cardinal Rule: Transparency and Disclosure":

Substantial Use: If an LLM has contributed significantly to the substance of a post—for example, generating a core argument, providing a structured outline, or composing a lengthy explanation—you must disclose this. A simple note at the end like "I used ChatGPT to help brainstorm the structure of this argument" or "Claude assisted in refining my explanation of Kant's categorical imperative" is sufficient. — Deepseek

Anyway, as I said, those guidelines are merely suggested; I am looking for constructive criticism.

(I don't want to dominate this discussion too much. I'll probably end up starting a new discussion thread specifically for building and refining the AI guidelines.)

Standard preferences to properly orientate the LLM at the beginning of every conversation are good. Like this:

My LLM Philosophy Discussion Preferences

Your Role: Act as a Socratic sparring partner to augment my thinking, not a ghostwriter.

Direct Instructions:
- Challenge my arguments and suggest counter-positions.
- Help brainstorm and structure ideas, but do not compose full arguments for me.
- Clarify concepts neutrally; I will verify all information.
- Improve the clarity of my existing writing.

Critical Rule: All output is for brainstorming and must be usable with full transparency on a public forum. Do not do my thinking for me.

Response Style: Be logical, direct, and transparent about limitations.

So you keep this somewhere easy to find and paste it in at the top of every philosophy-related conversation you have with an LLM.

No, it isn't. Wittgenstein said nothing of the sort. — Banno

So you say, but will you demonstrate that you actually believe what you say? Otherwise you are just showing that you know how to arrange words in an intelligible way.

I elicited your response, thus doing more than arranging words. Which was to be proved.

I elicited your response, thus doing more than arranging words. — Banno

You appear to be incorrectly applying some sort of theory of cause and effect. You did no such thing. I willfully criticized your act of arranging words. I apologize for having to disillusion you, concerning your attitude of having power over me, but you are referring to something I did, as if it was something you did. Please, assign responsibility where it is due.

We are not encouraging people to use it if they're not already. — Jamal

Good, thanks. Even better if you could retain:

AI LLMs may be used to proofread pre-written posts, but if this results in you being suspected of using them to write posts, that is a risk you run. We recommend that you do not use them at all.

Failing that, a clear statement of,

We are not encouraging people to use it if they're not already. — Jamal

?

Also helpful, perhaps, some routine and visible indication, one way or the other, of,

No AIs were consulted in the making of this post. — Pantagruel

? Or if that's too harsh, something like, that none (or some) were used for

generating a core [or subsidiary] argument, providing a structured [or unstructured] outline, or composing a lengthy [or short] explanation — Deepseek

[Depending on where lines got drawn?]

As the question is now (rather suddenly) tending to arise, when one starts to browse any post?

Thanks for pointing that out.

And saying nothing else.

Am I the only one saying things that could fit in the other thread?

Fair point. There I struggled with thinking on how to do it, which no answer leads to your line of questioning.

Not at all :) -- I suspect that here we're likely not very alone on this after all.

how we can use AI to do better philosophy — Banno

Doesn’t that just depend on the LLM? And who determines that? We need to be better philosophers first in order to judge whether the LLM output is “better” and so whether the LLM is useful.

The question since 3000 years ago is “How can we use X to do better philosophy?” AI is just a new tool, a new “X”. Nietzsche asked “how can I use prose to do better philosophy?” Russell and Witt asked about math and linguistics.

Unless this thread is a tutorial on using LLMs that “better philosopher” way.

Amateur philosophers just spend their lives struggling to understand the world, ping off a few cool philosophers, and spout what they may. — frank

How is that any different from any philosopher?

The difference (to you) is your own judgement of what is “spouted”. And maybe the number who make up the “few”.

I appreciate the explanation of sandbagging. The adaptive process seems parallel to marketing feedback to customer selections: An algorithm of mirrors inducts future novelty.

That adds another wrinkle to "when is the interlocutor not an interlocutor" question discussed previously.

I really do not see the difference here. Following Wittgenstein, all that "saying something" is, is arranging words as if you were saying something. Meaning (as in what is meant, by intention) is not a separate requirement for "saying something", because meaning is assumed to be inherent within "arranging words as if you were saying something". — Metaphysician Undercover

That reading of Wittgenstein assumes "meaning" is an arbitrary convention. That is precisely what he militates against in Philosophical Investigations. There is a passage that is amusing to read in this conversation about interlocuters being actual or not.

A human being can encourage himself, give himself orders, obey, blame and punish himself; he can ask himself a question and answer it. We could even imagine human beings who spoke only in monologue; who accompanied their activities by talking to themselves.—An explorer who watched them and listened to their talk might succeed in translating their language into ours. (This would enable him to predict these people's actions correctly, for he also hears them making resolutions and decisions.)

But could we also imagine a language in which a person could write down or give vocal expression to his inner experiences—his feelings, moods, and the rest—for his private use?——Well, can't we do so in our ordinary language?—But that is not what I mean. The individual words of this language are to refer to what can only be known to the person speaking; to his immediate private sensations. So another person cannot understand the language. — PI, 243

As it relates to this OP, Wittgenstein's statement throws the issue of pretense of AI into sharp relief. It is a pretend form of monologue when talking to oneself and a pretend form of dialogue when directed at others, whether admitted or not.

As a camper on the colline de Molière, my observation more properly belongs on the other OP.

There are those, Hinton being one of them, who claim that the lesson to be learned from the LLMs is that we are also just "arranging words as if it were saying something", that is that we don't have subjective experience any more than they do. I remain skeptical, but I entertain the possibility that there might be something in that. — Janus

Yes ... reminds me of school, and later as well. Many teachers and the whole approach to education considered us to be basically things, automata, robots. And then later, in the early days of internet forums, there was this in-your-face atmosphere of, "You can't think for yourself, you're just parroting others, you can't produce anything original". That line, "Please, Blue Fairy, make me a real life boy (girl)" was oddly relatable. Come to think of it, it still is.

So when I now read criticism of AI/LLMs, I'm reminded that those were the exact things we were told.

Rejecting an argument because it is AI generated — Banno

Not quite. I reject the headlong conflation of a text, identifiable word for word, with the host of arguments, meanings, ideas, intentions, speech acts etc that we seek to discern and delineate by comparing texts. All of which are potentially noble and valuable things, but not reliably identifiable nor distinguishable from instance to instance.

Natural language games (arts and sciences) are typically indeterminate that way. As pointed out by many. Goodman, in particular, points out (in the usual place) that the discerning and discriminating, though frequently too fine-grained to achieve replicability, is usually valuable (cognitively) partly on account of the tradition of anchoring it in a comparison of physically identifiable artworks or literary works. (Or photos or musical recordings.)

Hence the potential importance of authenticity of a painting, and of identity of a text. And one way we often are able to benefit from the identification of texts and paintings, in our striving to discern meanings and arguments and intentions (e.g. hidden but implied premises or allusions) is by reference to historical facts about the authorship. A fallible way, sure. Fallacious, often. But certainly disrupted, and not necessarily for the better, by plagiarism of one kind or another.

I did it again. The Phatic act of stringing a few words in order performed the illocution of making a post and the subsequent perlocution of your response.

I'll leave you to it. This should probably be elsewhere.

Doesn’t that just depend on the LLM? — Fire Ologist

It also depends on the prompt. Prompt engineering is a "thing", as the kids say.

The difference between the response of GPT to my OP, prefixed or not prefixed by "Look at this rubbish, by Fred".

Perhaps an instance of Hegel noting where a change of quantity is a change of quality.

Well, it's output seems generally well written, though not scintillating. And, what's written speaks for itself. I think it should be identified when used but otherwise am unconcerned. I long to see its comment on such gems as "Nothing nothings."

Good stuff.

But first, it seems inevitable that in a thread on the effective use of AI to do philosophy, there will be some need to defend the use of AI to do philosophy. That by way of my excusing my going somewhat off topic.

In the OP I mentioned a few objections, but not aesthetics. From what you and others have said, it's clear that the strongest objection is aesthetic.

And if your objection is that we should not use AI because it is ugly, then that's perhaps an end to the discussion.

It is ugly because it is inauthentic. Not in the existential sense, but by way of not having a flesh-and-blood person behind the phatic act.

An AI cannot put its balls on the anvil.

I think this a very good objection.

The answer we have is

The final responsibility for the content and quality of your posts always rests with you. — Deepseek

In posting, one commits oneself to the content of the post. That's the move from the mere phatic tot he illocution. And it occurs, AI or no.

In the OP I mentioned a few objections, but not aesthetics. From what you and others have said, it's clear that the strongest objection is aesthetic. — Banno

I would like to challenge that but am presently more interested in the Bongo response.

An AI cannot put its balls on the anvil.

I think this a very good objection. — Banno

Agreed! That's indeed the chief ground for not treating it like a person. People often argue that chatbots should not be treated like persons because they aren't "really" intelligent. But being intelligent, or wise, in the case of persons (i.e. socialized, enculturated rational animals), always has two tightly integrated components: one doxastic and one conative. One must know the layout of the space of reasons and one must be motivated to pursue the right paths while navigating this space in the pursuit of theoretical and/or practical endeavors. Chatbots lack conative autonomy and hence purse whichever paths they think their users want to explore (or, worse, that merely lead to the outcomes they think their users want to achieve, while having the mere appearance of soundness.) So, they lack part of what it needs to be wise, but that's not because they aren't smart or knowledgeable enough to be useful conversation partners. The human partner remains responsible for deciding where to put their balls.

"Nothing nothings." — Ciceronianus

Let's take that on as an example. Just as is, the reply is:

That’s a nice compact paradox — evocative of Heidegger’s “Das Nichts nichtet,” isn’t it?

If “nothing nothings,” then nothing is doing something, which already seems to contradict its status as nothing. Yet Heidegger’s point was that the nothing is not a mere absence, but an event or activity: it “reveals” beings as such by withdrawing them into non-being.

Do you mean it in that Heideggerian sense — that “nothing” acts or occurs — or more as a logical or linguistic puzzle (like “the concept of nothing cannot have a referent”)?

But add "That fool Fred said..." and we get

Heh — then Fred has stumbled (perhaps unwittingly) into Heidegger’s paradox.

“Nothing nothings” (Das Nichts nichtet) comes from Heidegger’s 1929 lecture What Is Metaphysics? — and it’s deliberately outrageous, because it violates grammar to reveal something about how language and thought presuppose Being. Heidegger’s move is to treat “Nothing” not as a mere negation of things, but as something that actively “nihilates” — that is, makes possible the disclosure of beings as beings by withdrawing them.

So when Fred says “Nothing nothings,” if he means it mockingly, he’s missing the point. But if he’s accidentally gesturing at the idea that the nothing is not nothing, that it somehow “is” in its own way, then he’s (accidentally) paraphrasing Heidegger’s entire essay.

Would you like me to unpack Heidegger’s logic step by step — why he thinks “Nothing” must “nothing”?

Following the protocol suggested in the Game changers article, we begin:

• Identify the problem / question / task
• Incorporate prior knowledge / clarify assumptions
• Design the prompt (structure)

We might leave the problem fairly general - what are we to make of "Nothing nothings"? The prior knowledge, we might lift from what was said above. A prompt such as :

"Nothing nothings" is a translation of “Das Nichts nichtet”, from Heidegger’s 1929 lecture What Is Metaphysics? What are we to make of this? Summarise three different responses.

Here's the result.

What do you think, @Ciceronianus?

Yet more grist: AI Generated Content and Academic Journals

The discussion is in reference to academic journals, however many of the issues mentioned carry over to our simple convocation.

The comment by Ian McLaughlin: "L;DR: Worrying about keeping AI out of scholarship is elitist, capitalist, and fruitless conservative sheep dip" continuing:

In short, we should focus less on keeping AI-geberated works out of scholarship and more into how scholars can use it successfully. I think, for instance of the movie Finding Forester. In this movie Sean Connery’s character mentors a young black author. One of the assignments he sets is to copy the first paragraph of another work and then see where his own thoughts take him. The young man uses this tool poorly and is accused of plagiarism. However, the tool, if it had been used properly, would have been a useful one. Such is AI.

Ugh. It seems that AI can successfully parrot
the explanations of Heildegger's many apologists. I'm with Carnap in this, of course, but am willing to acknowledge that the phrase may be an inept stab at poetry of a sort, which I think is what Carnap suggested as well.

That said, I think it's a good response.

I like this. I asked Deepseek to incorporate it into a set of guidelines based on the existing AI discussions on TPF. Below is the output. I think it's a useful starting point, and I encourage people here to suggest additions and amendments. — Jamal

Isn't it a bit ironic to have AI write the AI rules for the forum? This is the sort of appeal-to-LLM-authority that I find disconcerting, where one usually does not recognize that they have appealed to the AI's authority at all. In this case one might think that by allowing revisions to be made to the AI's initial draft, or because the AI was asked to synthesize member contributions, one has not outsourced the basic thinking to the AI. This highlights why "responsible use" is so nebulous: because everyone gives themselves a pass whenever it is expedient.

3. Prohibited Uses: What We Consider "Cheating"

The following uses undermine the community and are prohibited:

[*] Ghostwriting: Posting content that is entirely or mostly generated by an LLM without significant human input and without disclosure.
[*] Bypassing Engagement: Using an LLM to formulate responses in a debate that you do not genuinely understand. This turns a dialogue between people into a dialogue between AIs and destroys the "cut-and-thrust" of argument.
[*] Sock-Puppeting: Using an LLM to fabricate multiple perspectives or fake expertise to support your own position. — Deepseek

I like the separating out of good uses from bad uses, and I think it would be helpful to continue to reflect on what is disagreeable about AI use and why. For example, if we don't know why we want to engage in human communication rather than non-human communication, then prohibitions based on that axiom will become opaque.

A sort of core issue here is one of trust and authority. It is the question of whether and to what extent AI is to be trusted, and guidelines etch the answer to that question in a communal manner. For example, it is easy to imagine the community which is distrustful towards AI as banning it, and the community which is trustful towards AI as privileging it. Obviously a middle road is being attempted here. Transparency is a good rule given that it allows members to navigate some of the complexities of the issue themselves. Still, the basic question of whether the community guidelines signify a trust or distrust in AI cannot be sidestepped. We are effectively deciding whether a specific authority (or perhaps in this case a meta-authority) is to be deemed trustworthy or untrustworthy for the purposes of TPF. The neutral ground is scarcely possible.

Thanks.

Next step is to refine and optimise. I'm with Carnap, too, so let's look for problems therewith.

"Nothing nothings" is a translation of “Das Nichts nichtet”, from Heidegger’s 1929 lecture What Is Metaphysics? What are we to make of this? The Logical–Analytic Critique, characterised by Carnap, "nothing" is a quantifier and so not an individual, hence "Nothing nothings" is not well-formed; or less charitably, is nonsense. Give three reasons for rejecting this response.

And a follow up:

How has the analytic tradition respond to each of these?

The result.

It seems that AI can successfully parrot
the explanations of Heildegger's many apologists — Ciceronianus

Does that mean that you dont believe the a.i. captures Heidegger’s intent but only his devotees’ misinterpretation? That would seem imply that you understand the a.i. response and perhaps even find it somewhat valuable. I’d say that’s progress.

Next step is to refine and optimise. I'm with Carnap, too, so let's look for problems therewith.

"Nothing nothings" is a translation of “Das Nichts nichtet”, from Heidegger’s 1929 lecture What Is Metaphysics? What are we to make of this? The Logical–Analytic Critique, characterised by Carnap, "nothing" is a quantifier and so not an individual, hence "Nothing nothings" is not well-formed; or less charitably, is nonsense. Give three reasons for rejecting this response.
And a follow up:
How has the analytic tradition respond to each of these?

The result. — Banno

I could easily counter these analytic objections to Heidegger’s phrase ‘The nothing nothings’ (and I have done so on many occasions) , but given my very positive experience with a.i. I was confident that it is more than capable of capturing the essential features of my critique. And it did not let me down:

To craft a counter-critique with philosophical bite, the goal is not simply to defend Heidegger’s phrase “the nothing nothings” as meaningful, but to expose the poverty of the conceptual terrain from which the analytic tradition mounts its critique.

Here’s a strong and structured counter-critique, section by section, with the overarching thesis that the analytic tradition lacked — and perhaps still lacks — a conceptual ground adequate to the mode of thinking that Heidegger’s phrase demands:

⸻

Counter-Critique: The Analytic Tradition’s Conceptual Inadequacy in Confronting Heidegger’s “The Nothing Nothings”

1. The analytic tradition presupposes a theory of meaning that forecloses Heidegger’s question from the start.

The logical positivist insistence that a statement must be translatable into a “logically well-formed” or empirically verifiable proposition presupposes a metaphysical decision about what counts as meaning — namely, that meaning must arise from reference to entities or states of affairs. But Heidegger’s inquiry into das Nichts is precisely a questioning of the ontological ground of such entities and states of affairs; it inquires into what makes the appearing of beings as such possible.

Thus, the analytic critique never actually meets Heidegger on his terrain. It rejects the question of the Nothing on the basis of criteria that themselves depend on the unquestioned acceptance of beings as primary. The analytic tradition thereby circularly immunizes itself against the very kind of thinking Heidegger is attempting: a thinking prior to, or beneath, the ontic-epistemic dichotomy that analytic philosophy assumes.

In short: the analytic critique does not refute Heidegger — it merely excludes him through definitional fiat.

⸻

2. The analytic demand for formal coherence presupposes the ontological primacy of propositional logic.

When Carnap or Quine insists that “the nothing nothings” is ill-formed or meaningless, they appeal to a background assumption: that logic exhausts the structure of thought. But Heidegger’s move is precisely to ask what grounds logical order itself. Logic, for Heidegger, is a derivative mode of disclosure that arises only once beings are already manifest as such.

By insisting that the sentence must conform to first-order syntax, the analytic philosopher demands that Being itself be rendered in a schema meant for beings — which is exactly the ontological error Heidegger’s project exposes. The analytic reaction thus exhibits what Heidegger calls Seinsvergessenheit (forgetfulness of Being): a blindness to the pre-logical horizon that makes logic possible.

Therefore, the analytic critique operates without recognizing its own dependence on a pre-logical disclosure of meaning, a phenomenon it cannot thematize because its conceptual apparatus has no place for it.

⸻

3. The rejection of performativity and contextual meaning betrays a narrow conception of linguistic eventhood.

Analytic philosophers who dismiss “the nothing nothings” as an illegitimate performative implicitly assume that meaning arises only from stable intra-linguistic conventions — language games, felicity conditions, rule-governed acts. But Heidegger’s use of language is not a deviation from these norms; it is an exposure of their ontological condition.

Language here is not merely a system of signs or acts; it is the site where Being itself comes to language (die Sprache ist das Haus des Seins). To demand that Heidegger’s utterance conform to existing language-games is to ignore that he is attempting to make visible the founding rupture in which any language-game becomes possible.

Hence, analytic philosophy mistakes a transformative linguistic event for an ill-formed sentence, precisely because it cannot grasp the ontological status of poetic or originary speech. Its categories of “sense” and “nonsense” collapse when faced with language that discloses rather than denotes.

⸻

4. The analytic framework lacks a conceptual ground for ontological questioning.

The analytic critique often appeals to “clarity” and “rigor” — but these are methodological, not ontological, virtues. What is missing is a conceptual ground that could situate what Heidegger means by the Nothing. The analytic philosopher interprets the Nothing as a quasi-object or negation — a “thing” or “operation” — because its conceptual machinery allows only entity-like or functional predicates.

But Heidegger’s Nothing is not an object or process; it names the withdrawal or horizon within which beings appear. To even understand that, one must already have shifted from the question “what exists?” to “how does the appearing of existence occur?” — a shift the analytic tradition’s epistemological orientation never makes.

Thus, analytic philosophy’s critique of “the nothing nothings” does not expose nonsense; it exposes its own incapacity to think beyond the ontic. It lacks the conceptual space for ontological thinking because it has preemptively restricted meaning to what can be stated about beings.

⸻

5. The real issue: an asymmetry of philosophical ground

The analytic tradition’s engagement with Heidegger has, historically, been one of category enforcement rather than category reflection. It treats Heidegger’s discourse as though it were making statements about things, when in fact it is transforming the horizon of what it means to make a statement. The analytic critique presupposes a conceptual ground (logic, empiricism, linguistic convention) that Heidegger is not participating in but interrogating.

Thus, the analytic tradition’s critique is not a counter-argument but a category mistake in its own right: it critiques Heidegger for failing to play by rules whose origin he is precisely trying to bring into question.

In this sense, “the nothing nothings” functions as a philosophical test: it reveals where the analytic tradition ends — where it meets a form of thought that cannot be domesticated by its epistemic protocols.

⸻

Summary: The Poverty of the Analytic Conceptual Ground

Heidegger’s phrase exposes not the emptiness of metaphysical language, but the emptiness of the analytic conception of meaning itself when confronted with ontological disclosure. The analytic tradition’s failure to grasp Heidegger’s “Nothing” is not a triumph of clarity over obscurity, but the sign of its own confinement within the ontic register of beings, its inability to think the horizon in which beings are manifest at all.

In short:

The analytic tradition cannot understand “the nothing nothings” not because the phrase is meaningless, but because it demands a form of meaning that the analytic tradition is conceptually unequipped to recognize

Ok, but what was the prompt used? That's the topic here.

So here is a variant, using much the same prompt re-worded for the "poetic" tradition.

It's really quite good at describing and summarizing these opposing positions. The lawyer in me admires this. I think it will be very useful in preparing and responding to legal arguments. I've chatted with it about it's application in the practice of law.