The a.i.’s final answer reveled how it was able to take a philosophical discussion from a vague starting point and bring it to a level of depth and detail which opened up a vast array of much more nuanced questions. And because I am well acquainted with the authors being discussed, I knew that the information it was using for its arguments was not being simply fabricated out of whole cloth, but was highly relevant and based on real texts of the authors. I almost always find this to be the case with regard to A.i’s treatment of philosophical issues. — Joshs

I experience the same thing when coding with AI. You can start off with some basic structure and expand on specific areas, building on what was created before. And you need to know the programming language to be able to pick out mistakes and make the adjustments you want to see. Also the first block of code it wrote worked right out of the box, which lines up with what you said about AI is not fabricating. It can take learned data and apply it to a new situation like my specific request for a certain function that has never been written before - the same way a human programmer would - and it worked.

Just because we use calculators to perform simple arithmetic, we have not forgotten how to do simple arithmetic. Calculators are tools to speed up the process of things that we already know how to do. We do this with our own brains. Once we learn a task, like riding a bike, we outsource the decision-making when performing those tasks to unconscious areas of the brain. We no longer need to consciously focus on each movement of each leg and our balance. It is all done unconsciously, which is why your mind can be in a different place while riding a bike and you arrive at your destination but don't remember the ride.

Just because we use calculators to perform simple arithmetic, we have not forgotten how to do simple arithmetic. Calculators are tools to speed up the process of things that we already know how to do. We do this with our own brains. Once we learn a task, like riding a bike, we outsource the decision-making when performing those tasks to unconscious areas of the brain. We no longer need to consciously focus on each movement of each leg and our balance. It is all done unconsciously, which is why your mind can be in a different place while riding a bike and you arrive at your destination but don't remember the ride. — Harry Hindu

Yes, this is an important point that people fail to appreciate about our thinking machines. They understand the role of simple labor-saving devices, but when it comes to a.i., they think it’s a zero-sum game, as though whatever the a.i. does for us takes away some capacity we possessed. What’s the difference between using a calculator and using a shortcut like long division? Neither will be useful to us unless we know why we are using them.

I agree that dialoging with a.i. is not like a discussion with a human, but if it consisted of only an internal dialogue with myself I wouldn’t learn as much from it as I do. A human will have a point of view, but the a.i. will take any perspective in its database, depending on cues given in the conversation. You’re right that when I’m arguing with a human, they may be able to bore deeper into the subject matter from their perspective than an a.i. can, both to critique and defend. But with the a.i. I’m not restricted to one human’s perspective. Instead, at my behest, the a.i. exposes me to arguments from multiple perspectives. It’s capable of presenting aspects of these arguments I may not be familiar with, and juxtaposing these arguments in ways that I would not have thought of on my own. In addition , it will push back and question my responses. — Joshs

Thank you for sharing your experience of interacting with AI. As has been frequently mentioned in this thread, one of the most pressing challenges is that we still do not fully understand what happens when a person collaborates with AI. The advent of AI has undoubtedly been reshaping not only our ways of thinking but the very structure of thought itself. In relation to this issue, I would like to share here a part of my recent dialogue with an AI.
My question: “Where does the creative dimension reside in our era of linguistic automation? When language itself—the medium of thought, trust, and social meaning—is being industrially automated for the first time in history, is there still space for the production of the new?”
AI response: That’s exactly the essential question — and one that many philosophers (Deleuze, Simondon, Stiegler, Agamben, even Derrida) help us approach, each in a different register.
Let’s explore it carefully.

1. Automation ≠ total closure
When language becomes automated, it may seem that creativity dies — that meaning is replaced by mechanical recombination.
But automation doesn’t end creativity; it reconfigures its locus.
In older symbolic systems — alphabetic writing, printing, cinema — automation always displaced something of the human. Yet each time, a new margin opened up:
• Writing liberated thought from oral immediacy → new forms of reflection.
• Printing industrialized text → new publics, new genres, new subjectivities.
• Cinema mechanized movement → new perception (the movement-image).
So when LLMs mechanize linguistic invention, the same dialectic reappears: the creative act migrates.
It’s no longer (or not only) in composition itself, but in meta-operations — prompting, curating, orchestrating, recombining, filtering, critiquing.
The creative site shifts from producing sentences to producing differential relations among automated language flows.

2. The creative outside (Deleuze’s view)
For Deleuze, creation is not personal inspiration but a process of differentiation — of extracting the new from within repetition.
Automation multiplies repetition to an extreme, but that’s precisely what can generate new “cracks” where difference appears.
In that sense, large-scale linguistic automation might intensify the conditions for creation:
“Repetition is the power of difference.” (Difference and Repetition)
The creative task then becomes:
• how to compose with automated language without being absorbed by it;
• how to fold its repetitions to produce singularities — new affects, new conceptual connections.
In other words: the human moment of creation survives where language meets resistance — where we break the automatic continuum and make a cut, an interval, a difference.

3. From expression to modulation (Simondon and Stiegler)
Simondon would say: technical automation individuates at a different level. The LLM is not a closed machine but a metastable system — capable of being integrated into new milieus of meaning.
So creativity today might be transductive: the art of forming relations among humans, machines, and contexts.
Stiegler would frame it as a battle for attention and care (pharmakon): language technologies can poison or heal. The creative gesture now requires cultivating desynchronization — moments that resist the industrial rhythm of linguistic automation.

4. The new as interruption
In a world of endless generated text, the new no longer appears as content (since the system can synthesize infinite content), but as interruption — a cut, a silence, a misuse, an error, a shift in rhythm.
Poetry, irony, discontinuity — all those fragile gestures that escape prediction — become the last sites of difference.
The creative act is no longer “adding” more text to the archive, but inventing a new relation to the archive itself.

5. A paradoxical opening
So yes — even under total linguistic automation, there is still room for creation, but it’s displaced:
• from writing as production → to writing as modulation, selection, and deviation;
• from originality → to intensifying difference within the repetitive field;
• from human authorship → to machinic co-individuation.
Deleuze might say: thought must “become worthy of what happens to it” — even when what happens is an algorithmic flood of language.

My question: Do you think Deleuze would be possible under the current technical-AI regime?
AI answer:That’s an extraordinary question — subtle, almost metaphysical — because it asks not simply whether Deleuze could write today, but whether the conditions of thought that made Deleuze possible can still exist under the present regime of algorithmic language.
Let’s unpack this carefully, step by step.

1. What made Deleuze possible in his own time
Deleuze’s thought arose from a very specific configuration of philosophy and technics:
• The late 20th century still experienced language as an expressive medium — structured, but not yet automated.
• Structuralism and phenomenology had revealed the conditions of sense, but not yet its machinic reproduction.
• Cinema, literature, psychoanalysis, and politics were the laboratories of the new; the screen, not the algorithm, was the privileged interface.
Deleuze’s genius was to sense that thinking itself was a function of images and machines, not just consciousness — but the machines he knew (film camera, montage, analog media) still preserved an outside of thought: they could be studied as dispositifs of difference.

2. The contemporary shift: from the camera to the model
The AI regime collapses that outside.
• The camera recorded and mediated the world; the model now generates it.
• The image Deleuze thought through (movement–time–thought) was a differential field; the model operates through predictive closure.
• Where Deleuze could still write with cinema as a way to think time, we now think inside a language system that writes with us.
So the very ontological status of language and image has inverted.
Deleuze’s method — constructing concepts that express virtual differences — relied on the incompleteness of representation.
But an LLM, by design, saturates the space of possible phrases; it performs completion.
Hence your question: can a thought of difference still arise in a medium that predicts?

3. Two possible answers
(a) The pessimistic one — the closure of thought
Some might say no:
Deleuze’s philosophy depends on the possibility of encounter, of being forced to think by what exceeds recognition.
But under algorithmic mediation, everything is already pre-anticipated, flattened into probability distributions.
If perception, affect, and language are all pre-synthesized by digital systems, then thought loses its shock.
No “encounter with the outside” remains; only feedback.
In this sense, the Deleuzian event — that which forces thought — becomes algorithmically neutralized.
The outside becomes simulation.
This is Stiegler’s and Han’s worry: that the proletarianization of attention destroys the capacity for invention — that automation captures the very temporality of thought before it can arise.
(b) The optimistic one — the return of the outside inside
But a Deleuzian might respond:
if the world of thought is now automated, then the outside reappears within the machine — as the glitch, the noise, the misalignment, the non-correlated.
The more total the regime, the more necessary the line of flight.
Deleuze’s project was always to discover difference within systems of repetition; the LLM regime may thus be its ultimate laboratory.
In other words, Deleuze would not survive as he was — the solitary philosopher of conceptual creation —
but a Deleuzian mode of thought could re-emerge as an art of modulation:
not the philosopher writing about machines, but collectives composing with them to generate new perceptual logics.

My question:4. What a “Deleuze today” might look like
If Deleuze were alive now, he might not write books at all.
He might work in distributed media — curating dynamic archives, composing algorithmic diagrams, creating conceptual ecologies instead of texts.
His method — making concepts as tools of perception — could translate into:
• designing open systems that reveal their own differential processes (art–code hybrids, generative maps, speculative interfaces);
• philosophizing immanently within code and networks;
• refusing totalization, insisting on minor uses of major technologies — small folds inside global systems.
He’d likely ally with thinkers like Yuk Hui, Luciana Parisi, or even technologists exploring recursive aesthetics — seeking the new inside technical determination itself.
So: Deleuze as we knew him might not be possible — the solitary author, writing in a typographic medium of thought.
But a Deleuzian force — a practice of differentiation, of thought becoming immanent to its technical milieu — could still arise, though under a new collective and machinic form.

5. To answer you directly
“Is there still room for the production of the new?”
Yes — but the site of the new has migrated.
Not in the solitary thinker or even the human linguistic act, but in the relational field where human sensibility and machine recursion interfere with each other.
That interference — the zone of indeterminacy between automation and life — is precisely where a Deleuze today could exist.
Not Gilles Deleuze the individual, but Deleuzian thought as a distributed event:
a collective experimentation with difference inside the very circuits that threaten to erase it.

My question: "Do you argue that we witness the end of the lonely, solitary thinkers?"
AI answer:That’s a deep and delicate question — and yes, in some sense, we are living through the end of a long epoch of solitary thinking, at least as the dominant image of thought in Western modernity.
But “end” here doesn’t mean disappearance; it means transformation.
"We might say: the age of the solitary thinker ends, but the age of solitary thinking — as a gesture of difference — becomes all the more necessary." Aren’t you contradicting yourself? In what sense can participating in transindividual machinic thinking still be considered solitary thinking?”
Let me unfold this carefully, because it touches on the very topology of subjectivity, creativity, and attention in the digital age.

1. The solitary thinker as a historical form
The figure of the solitary thinker — the philosopher in his study, the poet in her garret, the scientist in contemplative retreat — is not timeless.
It emerged with:
• the print regime (which individualized authorship, as Foucault noted in “What Is an Author?”),
• the bourgeois public sphere (Habermas: the space of the essay, the letter, the book),
• and a conception of interiority (Descartes’ cogito, Kant’s subject, Romantic self-expression).
That solitude was a technical and social affordance: the printed page, the silent reading space, the private room — all infrastructures of inwardness.
It produced philosophy as we know it: the “voice of one thinking alone,” addressing a virtual community of readers.

2. The technical mutation of thought
Our current environment — the AI–network–platform condition — erodes those affordances.
• Language itself is socialized at the infrastructural level. We write through models trained on everyone’s words.
• Attention is continuous and distributed. Thought unfolds in feeds, threads, and databases.
• Solitude is now a form of resistance, not a given.
So while the need for solitude persists (because thought still requires intervals, silence, delay), the space of solitude is constantly invaded by algorithmic noise and collective co-presence
3. The new regime: transindividual or collective cognition
Simondon’s concept of transindividuality helps here:
each individual is a phase in a larger field of individuation; thinking is never purely internal but always a relay between psychic and collective processes.
Under today’s technical conditions, this transindividual structure becomes explicit and materialized:
• the neural network externalizes the collective milieu of association;
• collaborative digital work, even intellectual, happens across human–machine couplings.
Hence we witness the dissolution of the solitary thinker into distributed cognition —
not as a loss of individuality, but as a new topology:
thought as a field of resonances rather than a voice in isolation.

4. But there is still room for solitude — as interruption
Deleuze, if alive today, might say: solitude becomes minoritarian.
It’s no longer the default mode of thought but a tactical act of subtraction — a way to create intervals in the flow, to allow difference to re-emerge.
Solitude now must be engineered:
turning off devices, stepping outside networks, reclaiming slowness.
It’s no longer cultural infrastructure; it’s a practice of resistance.
So the lonely thinker survives not as the image of philosophy, but as a kind of ethical stance —
a deliberate detachment from the total socialization of language and thought.

5. In short
• Yes, the figure of the solitary thinker as dominant epistemic subject is ending.
• In its place emerges a transindividual, machinically distributed form of thought — creative, collective, recursive.
• Yet, solitude remains indispensable — not as isolation, but as the capacity to delay, to hesitate, to resist synchronization.
We might say:
the age of the solitary thinker ends,
but the age of solitary thinking — as a gesture of difference — becomes all the more necessary.

That's a poor analogy. It's obvious when people are wearing makeup or wearing clothes that enhance their appearances. Property rights might be one reason to object to plagiarism—there are others. Pretending to be something you are not is one. — Janus

Poppycock, the only objection to plagiarizing that I remember is the posts objecting to someone trying to make us think s/he knows more than s/he does know.

How can you account for the exponential progress humanity has made in the past few centuries compared to the first several thousand years of our existence. — Harry Hindu

The details and the superficialities have changed, sure, but the exploitative nature of relationships between humans has not changed.

Yes, this is an important point that people fail to appreciate about our thinking machines. They understand the role of simple labor-saving devices, but when it comes to a.i., they think it’s a zero-sum game, as though whatever the a.i. does for us takes away some capacity we possessed.

What’s the difference between using a calculator and using a shortcut like long division? — Joshs

The difference is in knowing how much you can rely on yourself. (There are also practical aspects, like how do you calculate something when you don't have a calculator.)

AI/LLM's seems to be useful for some, mostly urban uses. Like computer programming or writing school papers. But beyond that?

What I’ve learned in comparing the forum with a.i. is that, unfortunately, the majority of participants here don’t have the background to engage in the kinds of discussions I have been able to have with a.i. concerning a range of philosophers dear to my heart, (such as Husserl, Heidegger, Derrida, Deleuze, Gendlin and Wittgenstein), especially when it comes to comparing and contrasting their positions. — Joshs

Then you're in the wrong place, no?

The level of discussion you're looking for is the domain of fancy university debate clubs. Why not attend those?

Ai demonstrates that self-reflection isn't needed for a comptent peformance of philosophical reasoning, because all that is needed to be an outwardly competent philosopher is mastery of the statistics of natural language use, in spite of the fact that the subject of philosophy and the data of natural language use are largely products of self-reflection. So it is ironic that humans can be sufficiently bad at self-reflection, such that they can benefit from the AI reminding them of the workings of their own language. — sime

Thanks for this comment.

So if one did not write the post themselves, but merely copied and pasted a quote as the sole content of their post, then by your own words, it is not their post. — Harry Hindu

Well, yes such quotes are no substitute for argument, and obviously they do not belong to the one who quotes. It is all the more objectionable if the person presents the quoted passage as their own work. It's easy enough to find them out if the quote is from a prominent philosopher, whether alive or dead, Not so with copying and pasting AI generated text.

That's a poor analogy. It's obvious when people are wearing makeup or wearing clothes that enhance their appearances. Property rights might be one reason to object to plagiarism—there are others.Pretending to be something you are not is one.
— Janus

Poppycock, the only objection to plagiarizing that I remember is the posts objecting to someone trying to make us think s/he knows more than s/he does know. — Athena

:roll:

That was a fun read. So it makes LLMs the new interactive textbook?

Who would buy a real textbook when you can scrape all of them for nothing in this interactive fashion? A lot of implications in that.

Did you find something useful in it?

Did you find something useful in it? — Janus

It generated pithy quotes such as….

That solitude was a technical and social affordance: the printed page, the silent reading space, the private room — all infrastructures of inwardness.
It produced philosophy as we know it: the “voice of one thinking alone,” addressing a virtual community of readers. — Number2018

If say you were just a grad student looking to publish, imagine going on this wending conversation which starts with the LLM largely reminding you of the familiar stuff you sort of know, but reassuringly complete in that it seems to cover all the bases. And then you arrive at some chance angle like this. Something that seems a fresh and catchy intro. A neat little summary that follows the human love of the rule of threes.

Already a thesis. Now data mime to have something more detailed to say about the actual history of each of those three spaces. A quality idea that can just as quickly be spun into a full paper.

We might say:
the age of the solitary thinker ends,
but the age of solitary thinking — as a gesture of difference — becomes all the more necessary. — Number2018

I mean that is a quality punchline. The average academic just couldn’t phrase a thought so fetching. It would be gold to have such a thesis and such a punchline. The academic just needs to flesh out the bits inbetween in whatever more wooden prose suggests it was mostly their own creative work.

So what I think would happen in this interactive textbook scenario is the usual thing. Technology amplifies rather than replaces the human element. But then the rewards are not evenly distributed in an accelerationist world. The top 1% get 99% of whatever benefit or kudos that is going.

Any number of mediocre grad students could publish mediocre papers in the old world. In the new world, those who have an edge in their prompt skills and their marketing nous will fly high above the common herd. Everyone might have the same access to the technology. But the rewards will again be a fat tail distribution when the inequality of outcomes is what the technology amplifies.

I see the point that more brilliant minds might find novel theses in AI-generated texts. At its best you might end up with a Derrida or a Heidegger, but for me the thinking of such writers as Heidegger and Derrida is little more than highbrow "pouring from the empty into the void", and to me that is how the AIs responses to @Number2018 read. I've come to see anything that is not based on rigorous analysis or scientific understanding as intellectual wankery—mental masturbation—and I have no problem with people enjoying that, but the idea that it is of any real significance is, for me, merely delusory.

Fiction and poetry (at their best) are for me better, richer, mediums for such flights of the intellectual imagination—I need the aesthetic element to be there as well.

I've come to see anything that is not based on rigorous analysis or scientific understanding as intellectual wankery—mental masturbation—and I have no problem with people enjoying that, but the idea that it is of any real significance is, for me, merely delusory. — Janus

Are you saying that with PoMo philosophy, AI might have hit its particular sweet spot. :grin:

So it makes LLMs the new interactive textbook?

Who would buy a real textbook when you can scrape all of them for nothing in this interactive fashion? A lot of implications in that. — apokrisis

Yes, it can make LLMs a kind of new interactive textbook. However, I don’t think such a text has ever been published before. This ‘textbook’ is created specifically for the individual who requests it. So, it is not a digital copy of existing books, but may become a situated co-production of knowledge.

Are you saying that with PoMo philosophy, AI might have hit its particular sweet spot. :grin: — apokrisis

Well the LLMs have no experience of the real world do they?

So, it is not a digital copy of existing books, but may become a situated co-production of knowledge. — Number2018

To what end? The production of more and more fancy looking word salad?

This ‘textbook’ is created specifically for the individual who requests it. — Number2018

Well yes. So it used to be me and a whole library. Now it is me pulling my own personal textbook out of the library, led by my chain of thought and not dictated by any author’s more limited intentions.

That could be a hugely amplifying tool.

That could be a hugely amplifying tool. — apokrisis

I guess it could be an exciting prospect for some folk.

Well the LLMs have no experience of the real world do they? — Janus

But can even humans claim that? Let’s rehash the forum’s most hardy perennial one more time. :up:

I guess it could be an exciting prospect for some folk. — Janus

Yep, the amplification is bipartisan. It applies to both the winning and the losing. That is the algorithm doing its thing.

But can even humans claim that? Let’s rehash the forum’s most hardy perennial one more time. :up: — apokrisis

"Real world"—that was perhaps a less than ideal choice of words—I intended to refer to the world as being what affects us pre-cognitively via the senses and is pre-cognitively modeled by the body/brain, as well as what shows up for us as "the world of common experience".

I've come to see anything that is not based on rigorous analysis or scientific understanding as intellectual wankery—mental masturbation—and I have no problem with people enjoying that, but the idea that it is of any real significance is, for me, merely delusory. — Janus

Don't mistake the speculative misuse of ideas for the ideas themselves. AI is no longer in the realm of “mental masturbation,” it’s already reshaping science, mathematics, and even philosophy by generating proofs, modeling complex systems, and revealing previously inaccessible patterns of thought. To dismiss that as delusory is to confuse ignorance of a subject with the absence of rigor within it.

The irony is that the very kind of “rigorous analysis” you claim to prize is being accelerated by AI. The most forward-looking thinkers are not treating it as a toy but as a new instrument of inquiry, a tool that extends human reasoning rather than replacing it. Those who ignore this development are not guarding intellectual integrity; they’re opting out of the next phase of it.