Philosophy and AI
Philosophy and AI
I think AI will be good for philosophy (if the philosophers don’t ruin it first, a big if). The reason is obvious: AI is no good at philosophy, at least as AI now exists. But it is good at many other things: white-collar jobs, routine teaching, performing calculations, storing information, providing quick answers. It is good at math and science, but not good at philosophy. So, jobs in fields where AI is good will disappear, but philosophers won’t. This is all commonly accepted, more or less. But I think it goes further—into news and entertainment. I think animated newscasters are a distinct possibility, along with robot cameramen and computerized news writers. I’m not sure about comedians (see “The Comeback” on HBO), but I predict that actors are going to be in trouble, especially action stars and leading men and women. For the powers of animation are going to take over their roles (literally). We already see it happening in sci-fi and fantasy films, also pornography. Nature documentaries are on the brink of extinction. AI is just less expensive and more flexible. You won’t even need scriptwriters for the commercial stuff (are there any real writers in Hollywood anymore?). A dumbed-down culture like ours is an AI culture.
But philosophers are not expendable in this way, except for routine teaching. The only question is whether the demand will exist. If universities as we know them succumb to AI, partially or wholly, philosophers will go elsewhere and form companies—so long as there is a demand for them. This is the big question: in an age of AI will people become stupider or will they aspire to something more elevated—difficult, challenging, profound? My suspicion is that they will do the latter: their minds will be less taken up with routine mechanical tasks and freer to roam more widely and deeply. Philosophers will be in demand, treated as valuable commodities. Movie stars will fade away, and TV celebrity pundits, to be replaced by philosophy stars. AI will come to them. I use AI to do my grunt work, but I don’t use it to make progress on philosophical issues, and I never will (not in this lifetime). I envisage a society in the not-too-distant future in which philosophers (good ones anyway—there are plenty of hacks) will be regarded as superstars. Even the architects of AI will lose out to AI, as AI figures out how to manage and create AI. Even in a society dominated by AI, not always benignly, philosophers will still be necessary—and I am really not so sure about scientists, historians, and even athletes. Armies won’t need flesh-and-blood troops (we will have robotic boots-on-the-ground and drones in the air). In an AI world actual organic philosophers will be kings, or at least “Hollywood royalty”. And the underlying reason, in my book, is that we philosophers deal with insoluble problems, while AI deals in soluble problems (problems not mysteries). It will be good for us that our problems can’t be solved.
“In an AI world actual organic philosophers will be kings” — looks like Plato was right again…
But in all seriousness I don’t share your optimism — if indeed you are optimistic regarding the world with AI as it emerges right now.
Mass culture is getting dumber by the day and super rich get more and more control over minds. And the danger of gen AI putting the human race out of their misery by distraction and destruction is real. However currently AI usage in the hi-tech business world is out of control. AI slop production is peaking out, so maybe it would be all over before gen AI takes over — malfunctioning hospital equipment, nuclear reactors, biological weapons leaking out of poorly controlled labs — there are many ways to implode that the world currently explores in full intensity.
I’m only optimistic about the status and employment prospects of philosophers in an AI world; the rest is pretty scary.
I typed in your statement, “.. we philosophers deal with insoluble problems (problems not mysteries). It will be good for us that our problems can’t be solved.”
Claude responded: This is a thought-provoking claim, but I think it’s both partially right and importantly wrong.
Where it’s right
There’s something real here. Philosophy has historically owned the “permanently contested” terrain — consciousness, free will, moral realism, personal identity, the nature of time. These resist algorithmic treatment precisely because they aren’t primarily information problems. No amount of data tells you whether qualia are reducible, or what grounds normative facts.
And yes, if philosophy’s job security depends on unsolvability, AI probably won’t threaten it soon.
Where it gets complicated
The “soluble/insoluble” distinction is doing a lot of unexamined work. Consider:
Many philosophical problems have dissolved rather than been solved — not by AI, but by conceptual clarification (Wittgenstein’s point). AI could accelerate exactly this kind of dissolving.
Some “philosophical” questions are becoming empirical — aspects of consciousness research, moral psychology, decision theory. AI is already reshaping these borderlands.
The claim may be self-serving. Calling your problems “mysteries” can be a way of insulating them from scrutiny. Colin McGinn made this move explicitly with consciousness — not everyone found it convincing.
AI can be a genuine interlocutor, not just a tool. A system that can steelman positions, trace logical dependencies, and find analogies across traditions changes philosophical practice even if it doesn’t “solve” anything.
The deeper irony
The statement itself is a philosophical claim — about the nature of problems, the limits of formalization, the value of irreducibility. It’s the kind of claim that deserves argument, not assertion. And the confidence that AI “deals in soluble problems” arguably underestimates how strange and contested the foundations of AI, mathematics, and logic actually are.
The most honest version of the point might be: some philosophical problems are structured in ways that resist the tools AI is currently good at — and that’s worth taking seriously. But framing this as a permanent, clean division looks more like boundary-marking than philosophy.
Who’s making this argument? The framing sounds like it could be McGinn, or possibly someone reacting to recent AI hype.
As I said, AI is no good at philosophy as it (AI) now exists, but this is compatible with the claim that it might one day be better than we are at philosophy. It depends on whether machines can have the kind of intelligence we have. I once argued that the genes have already solved the mind-body problem.
What you typed in is not a quote from me.
Richard Dawkins has recently said that he believed Claude AI is conscious, though I haven’t yet read the article, only commentaries.
I wonder how he defines consciousness. Does he also think it has free will and an imagination?
Don’t take this personally, but I find this comment completely bonkers, in multiple ways, both the “I typed in your statement” part and the “Claude responded” part. (I assume the rest of the comment constitutes Claude’s reply.) Was your point to demonstrate that indeed “AI” is no good at philosophy? If that’s an example of AI doing philosophy, then that response convincingly demonstrates that it’s no good at it. But if that is “Claude”‘s response, then that can’t have been what you “typed in”.
Admin says that it’s not a quote from his post, since you didn’t even indicate the ellipsis. But in the sentence of which that clause is a part, that clause is a nominal in a statement of identity (NP = NP), presenting the idea it expresses as a reason supporting the claim in the previous sentence. So you should have at least typed in the two sentences, perhaps followed by a question for the robot. But the robot’s response indicates that that can’t have been what you typed in for it, since it almost immediately goes to “algorithmic treatment” and “AI probably won’t threaten it”, while the statement in the prompt can be dealt with without invoking “AI”. (Not to mention that the bizarre opening sentence implies that the quoted statement involves a paradox, and I don’t see that it does.) The robot (if that’s what it is) is not a good interlocutor, because there doesn’t seem to be any transcendental unity of apperception. Why does the text say, “… whether qualia are reducible or what grounds normative facts?”, and, if that was the prompt, why would it refer to the “soluble/insoluble distinction”? And where would it get “calling your problems mysteries”? If, on the other hand, you wrote the comment from “there’s something real” on, and not the robot, why does the text refer to “McGinn” in the third person, and why didn’t you use quotation marks?
I don’t take it personally. Colin (“Admin”) has already pointed out that it wasn’t his statement, which I accept. fair do.
I’m not sure though whether you think I wrote Claude’s response? There are a lot of “why’s” in your reply that I’ve no idea how to answer – though I admit to a small frisson at eliciting such a detailed and thorough response.
I found what Claude had to say next to useless, thus proving my original point.
Current AI can imitate the surface form of inquiry and often extend existing lines of thought with remarkable fluency. But I have not yet seen it ask questions that disclose a genuinely new field of possibilities. Such questions require more than linguistic competence: they require counterfactual imagination, disciplined by evaluative pressure. Could imagination exist without consciousness?
I’m with you on this: AI = Absent Imagination.
Based on using AI as a first reader and as an interlocutor, it is great at analyzing texts; perhaps it can be described as a text analyzing texts. In literature and art that means it can’t rely on experience of the world or aesthetically, which means a lot. How would that impact philosophizing? I don’t know. You can probably outhink AI at this level, even if it is a good talker.
No doubt.