> While a human may say “aha” to indicate exactly a sudden internal state change, this interpretation is unwarranted for models which do not have any such internal state, and which on the next forward pass will only differ from the pre-aha pass by the inclusion of that single token in their context. Interpreting the “aha” moment as meaningful exemplifies the long-neglected assumption about long CoT models – the false idea that derivational traces are semantically meaningful, either in resemblance to algorithm traces or to human reasoning.
This paper addresses something that has always bothered me about LLMs. You read their reasoning, see something like “Wait, that’s wrong” and then watch them make the exact mistake they just identified.
By itself, "aha" carries no insight, but the insight is probably stated immediately after it. In that case the aha is semantically useful, by identifying the insight it is near.
it's a rhetorical heuristic that a writer should know to use when directing a reader to a declarative that they want them to pay attention to, usually because it's a non-obvious or roundabout insight
when utilized by AI, it's a probabilistic output and it's variable whether or not that rhetorical trick is useful. it also pushes a non-skeptical reader to focus too much on the following text or even to believe that they, themselves, derived some insight. this is effectively a kind of persuasive sophistry which is not helpful - adding rules around it prevents people from deluding themselves with AI
It amounts to noise overall, but it has further unwanted and potentially misleading 'properties'. I think it's rather sobering to see how much bandwidth is still being wasted.
Did not read the paper so apologies if this is covered but isn't it possible that there is some recognizable semantic pattern in the training data where an "aha" is often followed by a subtle semantic shift that proves closer to the original premise in some critical way, and by emitting the "aha" token the model causes itself to produce such a subtle semantic shift that pushes the subsequent reasoning closer to the desired response?
> but the insight is probably stated immediately after it.
If the intermediate tokens represent reasoning or thought, you would expect "aha" to occur after the thoughts that led to the realisation, including the thoughts encoding the explanation: they don't have any other state. There is no reason to draw the conclusion you've drawn. Furthermore, what LLMs are doing isn't thought.
Let's say that the forward pass that selected "Aha" produces activations that indicate a wrong assumption, and a plausible explanation.
It puts learned projections of the activation into the KV Cache and outputs Aha.
Both the cached projections and the current Aha token can now influence further activations in an additional Forward pass that the Aha bought the model.
Beats me how it works, honestly can't wrap my head around it.
From what I understand, at position Aha in each layer it's constructing a query based on the current activation and looking at the key of each other token position for that layer, in order to decide how much attention to pay to the value.
In this way it attends to the previous values, such as perhaps the incorrect assumption and plausible explanation.
> If the intermediate tokens represent reasoning or thought, you would expect "aha" to occur after the thoughts that led to the realisation, including the thoughts encoding the explanation: they don't have any other state.
Yes they do, they have their KV caches-- it's a pure function of the input tokens, sure but that doesn't prevent it from containing latent 'insight'. LLMs can and do pre-form the tokens they're expecting to output multiple steps in the future.
I wouldn't argue that the 'aha' means anything, but the structural argument that it can't that I think you're making isn't sound.
Consider this: while the inner state of an LLM (all its activations, residuals stream that is cached in the KV cache) is fully deterministic given its input sequence, the information contained in it IS NOT identical to the information in the input sequence. The reason is obvious: the LLM itself contains an enormous amount of information in its parameters and it transfers it to its residuals stream at each forward pass.
In other words: the final state given the two input sequences (where NT stands for "null token"):
is not the same, and LLMs keep working on the solution even if the input tokens provide absolutely no further information.
If this is correct, then there is no need for the model to have already verbalized the key elements that drive the "aha" moment, so no need for the "aha" to appear after a full explanation.
I've been calling them film noir internal monologues, within the documents being generated by the LLM which happen to look like movie scripts.
In other words, it isn't qualitatively different from character dialogue. "Keep cheese on your pizza by using glue" is the same problem regardless of whether the script calls for the character to speak it out-loud or not.
I don't think there's anything like that going on. They just word vomit into a secondary area, and then there is an internal prompt that says "clean this up and summarize for the user".
The training methods try not to apply any particular rules to the contents of the thinking text. That's called "optimization pressure on CoT" and is thought to reduce safety by inducing the model to lie (or stop clearly printing its intentions) in the thinking text.
That's my personal theory too. The model is stuffing its own context with vaguely related tokens, which helps the attention heads retrieve the right tokens.
It's also interesting because in humans the existence of "Aha!" moments that are not preceded by or are only loosely related to a chain of thought is taken as the proof of the fundamental mystery and irreproducibility of human intelligence. Now the same argument is made to deny that LLMs actually think. Go figure.
This seems indeed one obvious hole in the argument of the paper. There is no indication whatsoever that human thinking process is more reliable than LLMs intermediate tokens. Which doesn't make our thinking useless, as messy as it might be. We reorder and explain it after the fact.
The anthropomorphization of LLMs should be discouraged as much as possible. It perpetuates bad practices and encourages the use of these bots for tasks they are not intended for (particularly as chatbots).
Thinking traces should be treated as black boxes. There is no point in reading them. Only the LLMs’ conclusions are relevant. This is particularly true of Opus 5, which employs reasoning that seems highly questionable but very often reaches excellent conclusions (compared to its peers)
Sometimes I monitor thinking traces for misunderstandings (missing context / bad assumptions). If it's going to go off on a ~20 min task and I can catch it's going in the wrong direction in the first minute I save a lot of tokens and wasted time. I don't monitor the whole thing, mostly just the first bit to see if there was a gap or misalignment in intention.
As an aside, anthropomorphization has nothing to do with my motivations.
That's not a consequence of an LLM. It's a consequence of the training data. In fact, I would argue that the latest models aren't nearly as sensitive to the tone of input anymore. It's an issue that has been addressed by better curating training data.
“Throughout this process, Jarred's input was mostly limited to sending Claude messages of encouragement (mostly variants of “keep going” or “believe in yourself”).2 This seems to have helped Claude overcome some initial skepticism that it could make meaningful progress.”
I think you're ending that train of thought too early. Why does this occur?
Well... We can hypothesize that these things are largely trained on internet dialogue so there's probably some correlation between threads where people are not flaming each other and the quality of the replies. They're just statistical engines so anything you can do to raise the odds of a helpful next token...
I'm essentially just making shit up here, maybe it's right, maybe it isn't, but rather than saying "it's human and we should treat it so" we're trying to get to the ground truth of how it works.
Yeah sorry, I read too far into your position. There's a certain faction within these AI discussions that wants to over-anthropomorphize the LLMs in kind of a borderline spiritual way.
Oh that's a shame - I hadn't seen that, but I can believe it.
The philosophers who study these things have been clear for a long time - we can never know what it feels like to be in a digital brain. Or any brain for that matter. When push comes to shove we all might be phantoms in some guy's dream.
Don't know + can't know. I think that was the real point of the Turing test. Not: this means it's conscious. Just: this is the best we can ever hope to do.
> Thinking traces should be treated as black boxes. There is no point in reading them.
Just a few minutes ago i was reading Qwen 3.8 27B's reasoning when i asked it to do something that was computationally intensive and it started going down the rabbit hole of doing it using some GPU acceleration approach - even after leaving it to "think" for a bit, it never realized there is another and simpler way. So i stopped the generation and added a "note" saying that as the problem is computationally intensive, it could become much faster if using an alternative approach.
At least in my experience (with local LLMs, i don't know how the cloud stuff behaves) what LLMs "do" tend to correlate with what they "think", so being able to read what they "think" is valuable.
Strong dislike for papers that tell me what to do in the title, especially when even the paper admits a loose correlation of the intermediate tokens compared to solution correctness.
My solutions work and they speak for themselves.
> My solutions work and they speak for themselves.
I understand the sentiment, and I also use the "thinking" traces as insight, but wouldn't you want your solutions to be based upon a good understanding? If the correlation is weak, then our solution is also weak.
Sure, and the parent comment's position is that they dislike it. Its purpose is to advocate against clickbait titles becoming normalized in the scientific community.
I admit I didn't read the paper, but if thinking traces are not "thinking", then what are they? If their content is not representing progress towards a solution then they are irrelevant and we should just be able to remove them and save a lot of time and money. There's a lot of money to be made by doing so. So why are they there at all? What do they represent?
There is a useful engineering consequence here beyond terminology.
If intermediate tokens are not a faithful representation of the computation, then they are a pretty bad audit artifact too. We probably shouldn't be trying to make the model's internal narration more interpretable., but rather the computation around it more reproducible.
Record the actual inputs, model/version/configuration, tool observations and outputs, then make the execution replayable enough that differences between runs can be isolated.
In other words, don't ask the model to explain what it thought, and instead make the system able to show what actually happened.
I'm not sure how to test this but I think there's an interesting possibility where the "reasoning" tokens are actually both an accurate reflection of a line of reasoning, but also, that there can be changes in the weights as the computation proceeds onward that may not be reflected in the apparently nominal meaning of the human language the tokens are output as for our consumption.
Some modest evidence is my own subjective experience of the many times I've explained why I'm doing something, and it is a true explanation in the sense that it is certainly not a lie, but it is also incomplete and there are entire strands of thought that went into my decision that are not being articulated. Though human speech is not equivalent to an LLM's output since we can trivially think without literally speaking whereas they can not. (No need to nitpick on the definitions there; all I'm observing here is that they are forced to emit an externally-visible artifact whereas I can sit in silence, thinking, with no externally-visible artifact being produced. Not trying to make any grand claims about what is "real" cognition or anything.)
It is conceivable how to create a test of whether the tokens correspond to the "real" thought process, and papers and work on that have been done, such as [1]. It is difficult for me to imagine how to scramble the nominal tokens without also completely trashing any implicit calculations that may be occurring too.
Is anthropomorphizing a real problem? From what I know, none of the serious LLM researchers believe it has anything to do with human reasoning, apart from Anthropic with their click-baity terminology like "LLM biology". It's just a metaphor. "Reasoning tokens" is simpler to say than "learned prompt augmentation tokens". I used to (and still do) anthropomorphize things long before LLMs, and I've seen my colleagues do it too. Say, when MySQL fails to start because it tries to read its config from the wrong dir, I may say "oh, this guy thinks he must read the config from ..." (having a language with grammatical genders as my native language also helps make it sound pretty natural). It's more fun like that :) Doesn't mean I genuinely believe a MySQL instance actually thinks.
What's wrong with treating it as biology though? Even large software systems have biological aspects, their behaviour is emergent and if you want to observe how they work, a holistic approach is needed, you can't really reason about their full state...
For example, if you have a search engine or a complex game, you can't run tests like "for all inputs the results are correct", you're going to be fudging a lot, using randomness, using heuristics, and all that kinda stuff
Just like how mathematics > physics > chemistry > biology > psychology > economics/sociology (Auguste Comte's hierarchy reordered a bit for the modern day), moving up the abstraction ladder makes things more complex, less legible and less exact.
Because plenty of people, even ones that should know better, really believe it's a conscious, thinking entity, not just some turn of phrase.
I have a coworker that spends at least 10 hours a week arguing with his like you would with a conscious person. I've gently tried to explain it's like arguing with your compiler for giving you an incoherent error message - it's pointless. It doesn't understand, it can't understand, and even if it could, you arguing with it isn't going to make it "learn" or act differently.
> It doesn't understand, it can't understand, and even if it could, you arguing with it isn't going to make it "learn" or act differently.
I know people who are like that too.
I'm not sure anthropomorphizing is a problem. Seeing analogies everywhere is an innate human trait, sometimes it can be harmful but more often it's useful.
This is part of the problem being described. You are part of the problem.
"Some people are bad at X" is not comparable—is not even in the same category—as "LLMs are fundamentally incapable of X".
Every human (at least to a first approximation) is capable of understanding, of learning, of remembering things, of doing math, of counting the number of "r"s in "strawberry".
What you are observing is that some humans are careless, do not take the time and effort to understand, or have internalized the idea that they're "not smart enough" or "not the type of person" who understands things like <whatever>.
That has nothing remotely to do with the fact that LLMs have no consciousness, no self-awareness, no cognition, no understanding. At a fundamental level.
Anthropomorphizing is a problem when you're talking about treating something that's not living as if it were. Using humanizing language invites discussions of things like the rights and feelings of an algorithm. A judge that is misled by the application of human-centric language to an algorithm can lead to some terrible outcomes. Not everyone is an LLM expert and the language people use leads to them treating LLMs like actual, real humans. That is terrifying.
What is terrifying is the propensity of people hoping for a mechanical slave to do everything possible to avoid touching on the possibility for being-ness of the technology they are desperately hoping will work as a basis for that implementation.
Sorry, but if you're genuinely asking this not for trolling reasons then you should _really_ _really_ see a medical professional (not an insult).
Online comment sections are not the correct place to unpack any of this.
Which is indeed terminating this comment chain, but for good (and benevolent) reason.
Doing anything else other than referring to a trained professional in a controlled context would potentially just feed delusions, which is highly unethical.
Might not even be yours but those of another reader.
In the right space with real people, worthy of a debate.
On HN? No. Not like this. Not here. Not without filtering the participants for real human beings.
Leaving aside that I find it hard to tell whether this account is even real, the whole point is that it's not a "somewhat interesting hypothetical" but a genuine risk to the mental health of a significant amount of people.
Plus stability of our society at large. From a statecraft perspective (you know.. the thing that keeps us all alive and safe and serves as the foundation of everything), there are assumptions that must hold true if you do not want reality to collapse, and "sentience is reserved to complex carbon-based organisms" is one of those.
Unless you would like to suddenly end up in a world where some people have decided that humanity is actually not the most relevant form of life.
Fortunately though, humanity has proven quite.. uh.. unwilling.. to just go with that.
___
Oh and beside all that, it's just a sea lion + a sea lion defense.
Which you can see by the amount of text this answer had to be vs both "your" and the other equally possibly fake account's "contribution" to a debate.
But there you have it. Now please make me regret replying. I know you will
___
Side-note:
I blame (among other writers) David Cage here, for using Robots as an analogy in a way that broke people's minds. Then making highly successful pieces of Art that were supposed to tell humans to be nice to humans, but instead now people collectively believe that next token predictors could be sentient.
__
You can see by this comment getting longer that the bullshit won. What has it been? 20 minutes. Wasted on noise.
And this is why you just purge this stuff.
>But regardless, you're using this as an insult. I did not.
You did too. And any machine that tried to deny that would have failed the Turing Test. And it's insulting to all of us for you to repeatedly claim and pretend that you did not.
"There is no debate to be had here. Just a bad faith shouting match" is you constructing a cowardly exit.
See if you can respond point by point to my reply -- either without insulting me, or by admitting that you're trying to -- without making a fool of yourself again.
I saw that your reply got filtered by the system, googled your name, thought "huh", then tried vouching, but to no avail.
But either way. I think you might be operating in the mindset of a high-trust internet that no longer exists. You do not engage with sea lions, concern trolls and the like. You shut them down.
inb4 "who are you to decide that?" - "Me. I am me."
That said, I appreciate what you did for computing at large, but you're missing the point here. This is (unfortunately) not a good faith debate club. The Internet as we know and love it is dead.
44 years ago I was operating in the mindset of a high-trust arpanet that no longer exists, connecting to the MIT-AI Lab's PDP-10 (@L 134) through the NBS TIP (301-948-3850) at 300 baud with no password, asking nicely for an account to learn LISP and receiving it the next day for free, then learning MACLISP from Kent Pitman and EMACS from Richard Stallman and ZORK by spying on the output of other high-school kids connecting over the NCP network from other TIPs all over the country. Visiting the 9th floor at 545 Tech Square, knocking on the door in the elevator lobby until somebody got annoyed and pressed Terminal-E on their Lisp Machine keyboard to buzz the door open, going downstairs to the publications department and harvesting piles of MIT-AI Lab Memos that were free for the taking to anyone who knew they were free. Returning RMS a 68k manual in the mail with a "Copyleft (L)" sticker that inspired him to use that as a slogan for free software.
And I am perfectly aware that this is a totally different world, so I don't need you to lecture me on sealioning, trolls, grifters, and marketers. I have trolled the fuck out of RMS himself in good humor, using his own DOCTOR in Emacs to make fun of him, after he trolled the fuck out of new parents making a baby announcement with his Natalism flame.
And RMS once trolled the fuck out of me and Mike Gallaher, who I worked with on Gosling's UniPress Emacs (which RMS calls "Evil Software Hoarder Emacs"), who lamented that he'd heard RMS's house had burned down, and RMS replied "Where you work, I would have thought you'd have heard about it in advance". We all laughed uproariously because it was such a great troll, that he delivered deadpan without blinking an eyelash.
So instead of telling me I'm missing the point without making any of your own, and then flying off into the sunset like an over-announced 747 serving as a decoy for a C-32A containing Trump cowering in a catering cart, why don't you directly engage the points in my other post like I just asked you to?
----
I've read your edited reply, and it still addresses absolutely none of the points I rose in that original reply. Reply to that one, not this. Point by point. Or fly off without another word.
----
But before you do, please at least admit that you were intentionally insulting the people you were replying to, and concede that pretending that not to be true is insulting to everyone reading, but mostly and rightfully insults yourself.
----
Because you finally made an actual argument, and it deserves a real answer. If you'd opened with "AI companies push sentience narratives to pump their valuations and vulnerable people are having breakdowns" instead of "stop thinking these things," this thread would have been half as long and twice as useful -- because I agree with that part. No argument.
The hype is real, the casualties are real, and the companies telling bedtime stories about their products' souls are doing it for the stock price.
But look at what you did with that concern. Go reread salawat's comment -- the one you called cyberpsychosis. It's an attack on the AI companies: people hoping for a mechanical slave, doing everything possible to avoid the being-ness question, because slaveowners can't afford to ask it. That's your side of the argument, stated more sharply than you've stated it. You shouted down your own ally for using the word "being".
That's what taboo does as a strategy: it doesn't disarm the grifters, it disarms everyone except ...
Okay, but, fair enough, now that you're here (and you're a person with a name and history attached to it), it's less of a waste of time to ponder this.
So personally, I'm not really interested in the hypotheticals of emergent behavior and all that and whether something without memory that works as ours does could develop some different but practically identical form of sentience.
That is possible, but at the end of that hypothetical chain of thoughts might be an outcome in which the human is not the top of the food chain anymore.
Which is not to be understood as "oh god, I am full of fear of being obsolete", but "why would I even just spend a second on something that leads to the obsolescence of my kind".
The definition of sentience I believe we must use is one of skin in the game. Only what is bound by the same constraints as we are (mortality, disease, physical presence) may be treated as equal or equal-ish by us, because only then it has constraints that force it to do the same.
Not sure if that answers the questions you've had, but that's that.
Slavery only exists for living beings because humans have limited lifetimes, experience pain and can have their own desires and needs that can be forcibly taken away from them. Algorithms have none of these things and they don't need them (adding them would be the real cruel thing to do). There is no slavery for something that can't experience coercion.
> Anthropomorphizing is a problem when you're talking about treating something that's not living as if it were.
I mean, that is the entire definition of the word. And you also anthropomorphize living beings like many people genuinely attach human qualities to their pets etc. Yes, the risks are very high when it comes to chatbots in particular, especially to people who are not technically inclined. But you'll be surprised at how crucial the ability of anthropomorphizing is. This is a very good paper that summarizes it and is definitely worth reading if you're interested in these things: https://www.researchgate.net/publication/5936908_On_Seeing_H...
> I mean, that is the entire definition of the word.
Not quite - my wording there was very deliberate. By saying that it's a problem when you're treating something that's not living (not non-human!) as if it were, that excludes pets and all animals from the equation. I understand how common it is for humans to assign human qualities to other things and beings, but there is also an unspoken variable of intensity. Representing abstract concepts as humans, interpreting living things in a human-like way or traditionally referring to ships as living beings has a different degree of belief and intensity compared to implying a genuine belief that algorithms are beings that can be enslaved, like what the sibling comment to this one does.
No its not unspoken. Read the paper linked. It explains what you think you are explaining but with scientific rigor.
And you are wrong in your defintion of the world. Attaching human qualities to any non human entity (living or otherwise) is the accepted defintion of what anthropomorphizing is. It does not only apply to non-living entities.
Now I'm the one who's starting to doubt you read my comment with a fraction of the rigor you demand from me reading that incredibly dense paper.
Read it again. I didn't say the definition of the word didn't include living things. The definition of anything is not discussed there at all. The 'unspoken' part applies to what I left implied in my argument, you don't get to rewrite my argument. What I said is that while anthropomorphization is common and can apply to everything, to me it can be a problem when it:
1. Is applied to non-living things with a genuine conviction they are truly living, and not in a ceremonial or casual way
2. Is particularly intense compared to other cases of anthropomorphization and leads to a desire to assign actual personhood to the object
It is a problem because it does not really understand stuff. For example, if you ask a human "Do you understand that doing X will kill you 100%?". If the human answers "Yes", then you can expect the human to act according to that understanding. That they will not do X
But an LLM will happily acknowledges the consequences of doing X, but will still proceed to do X. So replace the human in the above example with a robot controlled by an LLM. There is no guarantee that it will not do X.
Have you not met humans that do that, too? When it was found that smoking causes cancer, many, many people kept doing it. Then the government taxed the crap out of it, and some people still do it.
It's easy to say that people have other motivations, but doesn't the AI, too?
You tell it not to do X, but you've also told it to do something that would benefit from X. It's going to "want" to still do X, to support that other thing.
It's also got all the "knowledge" that enables it to do the work in the first place, and all of the tendencies of the people who do that work, because that's what it's trained on.
It's really easy to anthropomorphize AI because it was literally modeled after people.
And for the record, as lead developer, I've had actual humans that reported me to go ahead and do things I specifically told them not to.
We do have entry and exit conditions. We can disrupt it and study the dynamics of the disruption. We have a good sense of the many mechanisms at play that undergird it.
What we lack is a full map of the exact process from sensation to consciousness across all modalities. And I’m afraid when it comes to interception, we can’t unless we observe every one of the 36 trillion or so cells in a human body, as well as the 36 trillion or so symbiotic and commensal microbes, continuously, all the time.
But I keep finding it astonishing that the claim that we know nothing about consciousness gets bandied about. We know a lot. We don’t have a grand unified theory. The lot we know is definitely split across many levels of evidence and hard to follow, let alone arrange. But this isn’t a black box. It’s a grey box, meeting an even more transparent box that is the LLM, where we do know what the guts are made of, and can interfere at every step in the chain of steps that constitute their dynamics.
Comparing the two, we know there’s a level of similarity in that information gets broken down via a neural network. That similarity was sought.
Since then though, neuroscientists have gone and shown that:
1. The other half of the cells in the brain, the glia, are at least as important as the neurons in cognition and consciousness
2. That interoceptive feedback and feelings are critical drivers of conscious experience
3. Evolutionarily, we know all cells can “learn”, and well before there were neurons or glia or brains, every cell evolved an internal clock that allows it to entrain to external solar and (depending on the species) lunar rhythms.
4. In the last few decades we’ve seen how synaptic activity is shaped and driven both by astrocytes and the circadian clock.
All this is showing us that the abstraction from the 1950s that current neural networks are built on were incomplete.
Whatever these components to do give rise to consciousness in biology (and we’re a long way from done solving this), we certainly wouldn’t imagine with all these modules and mechanisms missing, just maxing on one type of information flow in the brain would give you consciousness.
I’d urge you to not keep insisting consciousness is a total mystery. It’s not, and even your AI model of choice will be able to point you to all the mechanistic evidence we have that whatever it is, it isn’t just neural nets.
Whether human consciousness exists on neural nets or otherwise doesn't disallow an ANN in a particular configuration from being conscious. You might as well argue that human consciousness requires biological neurons, so artificial consciousness can't exist.
Odd. Why don't the details of how consciousness arises in one system inform your judgment of whether it can exist in a different system that only has partial structural overlap? Seems wildly convenient. Where else in science can you show me such a comparable situation in how you define properties?
A light bulb doesn't need to do fusion to make light. An airplane doesn't need to flap its wings to fly. An ANN doesn't need to use a brain's structure to think.
You haven’t proven an LLM has thought. I can measure the spectral properties of light from both a bulb and the sun.
I can measure the dynamics that go with thought in a human.
I can measure some dynamics in an LLM. From all we know, there are huge differences, not least that you can literally turn off an LLM, whereas every process but death in biology shows continued activity even when the organism “looks” off,
What you haven’t shown me is that what the LLM does when it is on is “thinking”. Given that the dynamics are different, the substrate is different, and one can be fully turned off and the other cannot, why are these two things the same?
Give me any problem that previously required human thinking. Any. That can be solved by LLMs. All you have to do is provide a single counterexample.
> not least that you can literally turn off an LLM, whereas every process but death in biology shows continued activity even when the organism “looks” off,
There is no reasonable definition of thinking that requires that it can't be paused.
> why are these two things the same?
I said they aren't the same, just as a bulb isn't the same as a star. An LLM can think, just as a human brain can think. A bulb can produce light, just as a star can produce light.
>Give me any problem that previously required human thinking. Any. That can be solved by LLMs. All you have to do is provide a single counterexample.
Theres an itch deep in my butt, but I'm in an important meeting and can't leave the seat. Nor can I openly scratch the area.
I can tell myself these things, focus on the itching, think about how itching is felt by the body, think about the social consequences, and make it feel more bearable.
Please tell me which LLM has solved this problem so I can not outsource the issue to it. I eagerly await your answer.
> There is no reasonable definition of thinking that requires that it can't be paused.
Is there a reasonable definition of thinking where the words "paused" and "turned off" aren't treated the same? Can you do that kind of thinking and get back to me?
> I said they aren't the same, just as a bulb isn't the same as a star. An LLM can think, just as a human brain can think. A bulb can produce light, just as a star can produce light.
An LLM can produce language. You are yet to show me it produces thinking.
Your claim is like saying the bulb produces light, so it also goes through fusion.
The LLM will tell you how to solve it. If you mean the LLM should modify your thoughts, no human could do that for you either, but an LLM agent can just as easily as a human figure out how to build the brain computer interface to make this possible in the future.
> Is there a reasonable definition of thinking where the words "paused" and "turned off" aren't treated the same?
No reasonable definition of thinking requires that thinking can't be paused or turned off. Please state your point more clearly.
> You are yet to show me it produces thinking.
Every problem that previously required human thought can be solved by LLM. QED.
> Your claim is like saying the bulb produces light, so it also goes through fusion.
No. How many times do I have to explain that the mechanism of thinking is not the same, just as the mechanism of producing light is not the same? You need to think to understand this, which is something that frontier LLMs have no problem with, but which most humans struggle with.
You’ve shifted your goal posts. You asked me for a problem I can solve with thinking. Not a problem another human can solve for me by their thinking. I have given you exactly what you asked for. An LLM cannot solve it. A human can’t solve it for me but can solve it for themselves (or not be capable of it), it varies.
Whatever you thought you were going to prove with your question, I do hope you’ll dwell on what my example tells you about what thinking is. It isn’t a string of words only. It can be that, but it’s more.
> No reasonable definition of thinking requires that thinking can't be paused or turned off. Please state your point more clearly.
It does. Please define thinking however you want. I’ll show you that it’s a requirement.
> Every problem that previously required human thought can be solved by LLM. QED.
Again, this is the same superficial thinking. Firstly, as my example above showed, no. There are other examples. It requires human thought to cook. No LLM can, nor is smell digitizable in an equivalent way to humans, and yet, cooking is one place where having a human nose is determinative to making appetizing food. Your QED is logically absurd, but is also resting on an assertion that’s flatly untrue.
> No. How many times do I have to explain that the mechanism of thinking is not the same, just as the mechanism of producing light is not the same? You need to think to understand this, which is something that frontier LLMs have no problem with, but which most humans struggle with.
When your “proof” for thinking is the output, I will also compare it to the output, light. My analogy shows the idiocy of your argument, and you don’t want to sit with its implications.
LLMs replicate human language. And many tasks human language can do, LLMs can do or help with. Thinking is not just producing word strings. We think about our family. We think about our bodily aches and pains. We think about how best to do various physical tasks. All this we do sans words, and LLMs don’t do. To call their internal dynamics “thinking” is silly wishful thinking by those who don’t have the ability to go read and understand biology.
And it’s a sad statement of how little you think of your own mind that you won’t explore facts that are outside your expertise that will actually teach you how your mind works, and the wondrous complexity underlying it, and the potential it has to keep doing new things.
I’m going to stop engaging at this point. You seem convinced LLMs think. I wish you the joy of that belief, whatever it is. Religion is always absurd, and this new one is no different.
Remember the problem we're discussing is whether these LLM systems can think. Your deliberate misinterpretation of a question does not make you win that argument.
An LLM can solve problems for itself in just the same way that a human can solve problems for itself. It cannot directly rewire your thinking in the same way that another human cannot.
You have yet to show me a problem that can only be solved by human thinking.
> When your “proof” for thinking is the output
What other way can we show thinking? From the input? Obviously not.
> My analogy shows the idiocy of your argument
It shows the idiocy of your argument. The output is thinking, just as the output is light. You are the one who continues to mistake the output for the mechanism.
> Religion is always absurd, and this new one is no different.
Your assertion of magic in biology that can't be replicated artificially is indeed absurd and one that almost no scientist would agree with.
None of this is an explanation of what consciousness is, either physically, logically or philosophically. (Maybe some physically)
Fundamentally it comes down to an objective decision about what that is. If you say it is “feelings” based on inputs and feedback mechanisms from the brain, then we can do the philosophical discussion around that.
“If the claim is that consciousness is limited to those with a specific type of cell behaving in a given way” thats just a coping mechanism hoping to use a mechanical definition to shield you from the reality that eventually all of these inputs, outputs and feedback mechanisms can be reliably reproduced in a different form.
I’m baffled: how does the fact that each cell has an internal clock that continues to tick even when you take away all external signals not impact what consciousness is logically?
If the time order driving behavior is driven by an internal timekeeper, that is logically relevant to the behavior you’re interrogating. If, on the other hand, all component systems depended on an external clock, that logically points to a completely different dynamic process.
As for the philosophy of it all… it’s true I make no comment on it. I’d rather look at the physical substrate and see what it does, and compare it to behavior, than try to fit a philosophy that originated before we had such high resolution knowledge of the system. They are blind to these facts, just because they were written up too early.
I utterly reject this doesn’t show you anything logically about consciousness. If I can show you that the molecular dynamics of each cell organize to anticipate the dawn, and do so even in constant darkness, how is that not logically distinct from a system that is outside of regular time, needs to check a clock to locate itself in time, and then do whatever dynamics it does to solve the problem at hand?
As for calling this a coping mechanism… that’s a bit rich coming from someone who seems to have very little idea of the molecular and cellular biology but seems to want to hold to the belief that we’ve solved consciousness with LLMs. We can both fling that accusation about. Seems more productive to compare the physical dynamics and see what’s different and what’s similar, no?
> I’d urge you to not keep insisting consciousness is a total mystery.
But don't want to get into the philosophy of it. I'd urge you to consider the definition of conciousness (as specified by the original question) wasn't just about biology. And it is 100% very difficult to define.
> We do have entry and exit conditions. We can disrupt it and study the dynamics of the disruption.
We've known life and death for quite some time. Even from the biological perspective, there's nothing new there in the largest sense. All we've done is refine it. Animals are aware of it.
> but seems to want to hold to the belief that we’ve solved consciousness with LLMs
Quite the contrary, much like everything else, the more we learn, the more questions we have.
> Seems more productive to compare the physical dynamics and see what’s different and what’s similar, no?
ok but....
> how is that not logically distinct from a system that is outside of regular time, needs to check a clock to locate itself in time, and then do whatever dynamics it does to solve the problem at hand?
We only check clocks because we have an internal molecular dynamic that directs us to do so, and it is tied to a similar system as everything else.
> But don't want to get into the philosophy of it. I'd urge you to consider the definition of conciousness (as specified by the original question) wasn't just about biology. And it is 100% very difficult to define.
No. I don't engage in the philosophy of it because most of the consciousness philosophy that gets bandied about and is familiar to folks is from 20-30 years ago, and rest on knowledge that is significantly less granular about details.
You don't, for instance, demand physicists need to engage in the philosophy of gravity do you? You demand theory. Neuroscience does the same of consciousness, and there are definite theories with support coming at the problem from different ends.
Insisting it's a mystery without engaging with the facts is not what I'm interested in.
> We've known life and death for quite some time. Even from the biological perspective, there's nothing new there in the largest sense. All we've done is refine it. Animals are aware of it.
Not quite sure what this means, but as with consciousness, I'd say life also isn't a complete mystery, we have made great strides understanding it as it is and it's evolution in the past few decades, and while the philosophy of life, mired in assumptions from past decades, remains hopelessly stalled, the science of life has simply moved on.
> We only check clocks because we have an internal molecular dynamic that directs us to do so, and it is tied to a similar system as everything else.
Is this tongue in cheek? Nothing about our internal molecular clock tells us to check clocks. For most of life, there were no manufactured clocks, remember? They are a relatively recent invention.
Well, define "feel" - in a context that could be also applied to machines. It seems to be (if we really had to employ it for the sake of discussion) "getting signals from peripherals, orienting action".
> if it could, you arguing with it isn't going to make it "learn" or act differently.
Are you talking about a specific harness that doesn't have context retention mechanisms? For example, ChatGPT with disabled memory feature? Or in general where "it" is a fixed-weights network? The latter is trivially true, of course.
Even claude with “memory” enabled isn’t really “remembering” anything. It just injects it into the context and you hope it happens to find it relevant in its attention mechanisms, and then remembers to actually act on it. Anthropic’s own documentation states claude can and will ignore/truncate these. It’s a context trick, nothing approaching actual “memory,” and in fact, arguing with it will make a bunch of memory files, sometimes contradictory, and clutter up the context and act even worse.
I'm not a big fan of arguments like "it's not the real [human quality], it's [mechanistic explanation]." They lack a part: "because the [human quality] allows us to do X, Y, Z, which is impossible with [this mechanism]."
I agree that the relevance of retrieved pieces and the management of long-term storage could be improved, though.
I just don’t find it really relevant to the argument presented I guess. I disable auto memory and have my own mechanisms and infrastructure with how my agentic system “knows” and “remembers” things which is roughly an automated, sometimes self-correcting working index on the file system. It behaves much better than claude’s automated “memory” system, so I use that, but digging into how that worked and making something of my own just makes me really dismissive of comparing it to something like actual memory, so I apologize if it came off dismissive.
I guess I will expand on what I meant why I react to claude memory acting mechanically or logically anything like human memory, is because it isn’t how memory in the brain works, they’re not comparable.
The layman’s understanding I have of memory, as someone that has dealt with memory issues much of my life, is that memory formation is heavily tied to emotions. emotions are triggered by input which sends a complex set of signals throughout the brain - you’re not just finding where in your head to store this, your brain is deciding how important it is, and what else to correlate it with - so it can tie them to other related memories. then on top of all this, much of the sensory experience you intake is subconsciously compared against high priority memory impressions and deciding what to pay attention to.
you could, argue that the sensory input is the simple md files and the emotional mechanism is the same effect as to how attention mechanisms work in llm’s. Ok, I can almost buy that, but these tools lack a fundamental ability to decide how important things are.
an analogy. you tell a person “if you pick a daisy in the next five years, an assassin will come to kill you” and they hold a knife to your throat while they say it, your brain whether you like it or not is going to say “THIS IS AN IMPORTANT MEMORY I NEVER MUST FORGET” and you’ll see something that looks like a daisy and have a panic attack 3 years later. that memory is never fo tell me claude or other tool harnesses using memory harnesses can prioritize memories the way that human would, instead they forget even when reminded, because the human brain is just so much better at it
Yeah, I think I've come to the conclusion that the biggest breakthrough we need before we can replace human thought is going to be some mechanism for live update of weights. "Learning" by injecting into context just isn't good enough.
But billions of dollars are going towards research to find these breakthroughs, so we'll get there eventually.
I’m normally not a big fan, but in this particular case it matters a lot. I could come up with some functional argument, but really I care from a model welfare perspective, whether the model understands its reasoning traces to be a part of itself or it’s simply predicting what a character who wrote the current intermediate tokens would output next.
Reading this is like watching someone call cars moving a “trick” because it uses gasoline as fuel while humans don’t move with gasoline.
Bro the LLM is a token machine, it is reasonable to have its short term memory be represented as tokens in context because the LLM is a token machine. Call it a trick if you want but it does fit the actual definition of what memory in actuality is.
Well, our current set of evidence is that it’s a mechanistic mechanical algorithm with an RNG embedded in it and we can both get it to repeatedly produce the same output for the same input and also get it to repeatedly do absolutely nothing at all, which are not characteristics we usually find in objects evincing consciousness.
LLMs bear absolutely none of the traits we’ve come to recognize as the external hallmarks of consciousness in biological organisms, nor anything that would seem analogous in a non-biological substrate.
That said, we don’t have a rigorous definition of consciousness that includes the actual phenomenology of consciousness, so I daresay if you’re going to go around asserting the LLM is conscious despite all existing evidence to the contrary, I think the impetus is on you to define some version of consciousness that isn’t also satisfied by a book or a movie.
I would agree that LLMs aren't much like the human brain, that doesn't prove that consciousness is not occurring. Does a fruit fly experience anything? If a microscopic insect can experience something, why can't a CPU?
>if you’re going to go around asserting the LLM is conscious despite all existing evidence to the contrary
Well there is neither any evidence that suggests LLMs are not conscious, and I also never asserted that they are. If I had to guess I would say that any information processing system will produce some kind of conscious experience, but I ultimately have literally no idea.
There’s plenty. First, when we say “LLM”, what are we referring to? What is the entity that would be conscious in this case?
The reason this is important is because powerful people are currently trying to use the dodge that LLMs are conscious to launder liability for their own policy choices, so the sloppy thinking and half-assed conjecture about LLM consciousness has real-world consequences, and every time you assert the question is unknowable you allow that kind of loophole, so it’d behoove all of us for you to spend some time actually digging in on this instead of just idly making or rebutting assertions.
There’s a richer literature here than what you’ve seemed to have engaged with, and I’d encourage you to spend some time with it before handing more money to the magic AI people.
>The reason this is important is because powerful people are currently trying to use the dodge that LLMs are conscious to launder liability for their own policy choices, so the sloppy thinking and half-assed conjecture about LLM consciousness has real-world consequences
I'm not going to change my beliefs or how I think about interesting questions just because its the "socially conscious" thing to do.
>There’s a richer literature here than what you’ve seemed to have engaged with, and I’d encourage you to spend some time with it before handing more money to the magic AI people.
It seems like you are highly emotionally invested in this and that is precluding you from open engagement with the topic.
You're not engaging with the topic. Engaging with the topic is where one either asks questions and listens to the answer or actually seeks to increase one's knowledge on the topic. You're just saying things. That's lazy.
And, you're welcome to do what you want to do, it's your god given right to stay as ignorant as you want about any particular topic, but that comes with consequences. If you want to call that being socially conscious, sure, you do you, but if you're interested in why people keep getting annoyed at your loud proclamations of ignorance which you're trying to proffer as evidence of a curious mind, well, that's why.
It's just as intellectually lazy to leave "consciousness" undefined and proceed to claim that "X cannot be consciousness" because of social reasons. That's the definition of a circular argument.
In the same vein, airplanes can't fly because they don't flap their wings.
As for ignorance: have you tried to make an LLM produce the same output for the same input (as you state above)? Give it a shot, you'll be surprised.
I’m not leaving consciousness undefined. I provided a definition and asserted LLMs were not conscious by that definition. I solicited an alternate definition and was given none. If you’d like to claim the LLM is conscious, you need to define what you mean, for both “the LLM” and “is conscious,” because it’s not passing any of our existing bars for consciousness, and the only thing you can point to are characteristics also present in other objects we don’t consider conscious, so again, the burden of proof is in fact on you and that other fellow to provide some definitions here, because as sits you and the other commenter are just saying shit and refusing to engage with any kind of rigor.
And, to your point: I have, and I did, and I was not. If you’d like to refine your argument further - What LLM? Provide input how, and in what fashion? Under what conditions? - we can have that conversation, but if your assertion is “I can’t get ChatGPT to consistently produce the same output twice and therefore it is conscious,” that’s an incredibly facile argument.
You two seem to be laboring under the impression that this is terra ignota philosophically; it’s not. There’s an enormous amount of literature, thinking, ideas, concepts, frameworks, and approaches that already exist here that you’re welcome to engage with, but you’re not doing that, nor are you actually engaging with any of my arguments except to deny their existence.
Philosophically - sure. But philosophy is a feedback loop. Humans trying to build a model of their brain within their own brain. There is by definition not enough oomph there, and that model will necessarily be approximate at best.
Think that's what an out of touch techie would say? May I remind you that just a few hundred years ago the best philosophers were debating whether the world would descend into anarchy if more people realized that the big monkey in the sky doesn't exist. Just because philosophers talk about something doesn't mean it exists in reality.
As for same output - there's a parameter called "temperature". It governs the random wandering in the output of an LLM. Reducing temp gives more deterministic output, but also reduces the capabilities. Is it possible that randomness is also precisely the mechanism behind human creativity?
I'm still waiting for a definition of "consciousness," as well as a definition of the entity which you're claiming might possess it.
You've now added two additional entities that require definition for your statements to be meaningful in any sense - "philosophy," the entire field of which you're dismissing as useless, which is going to be extremely fun if you ever actually decide to dig into the neuroscience of consciousness and how the brain works to make sense of the world, and creativity, which has come into the conversation for some reason I'm not entirely sure of but also warrants a definition that isn't trivially satisfiable by either an I Ching or a double pendulum, which, if you're arguing those are conscious, sure, I guess we could throw anything in that bucket then.
You're arguing with all the rigor of a stoned college student, and fine, that's a register you can stay in, no problem with someone having hobbies, but at least have the decency to recognize what you're doing and acknowledge that other people have actually put in the work to be able to discuss and evaluate some of the questions you're positing as unknowable conundrums.
it is a physical system, yes. So is our brain. I do not understand why this pointless fact is given out as an argument. Either explicitly say you think consciousness is supernatural or say what physical elements are missing in your view that makes you feel AI cannot be conscious.
Consciousness is a slippery word that is notoriously difficult to debate over. But often, people use 'consciousness' as a shortcut or a familiar word to describe a more complex idea. The point they're driving across isn't about the precise definition of the word 'consciousness', but about people treating LLMs as if they were actual human beings, assigning them all the traits and behaviors they would expect of a human.
I would argue, that the null hypothesis is that it is not, and that anyone claiming that there is a mote of consciousness are the ones with the burden of proof.
Some tools like code rabbit (PR review bot) encourage you to do this. I couldn’t believe I found myself replying to code review comments to explain to an AI why we would rather let an exception crash the app than to catch and hide it several times so that it would stick in its memory. Having to interact with bots as if they are humans, especially when they are gate keeping, is degrading.
Not just coderabbit (though it is a bad offender). GitHub's copilot review feature is an equally miserable experience.
That one loves talking in imperatives, regardless of the fact that it is a clueless machine.
FWIW, this tells you a lot about both the culture behind who built these things but also about the people that enable this stuff and don't immediately nope out. From that perspective, it's a low price to pay to learn whose judgement to never trust again.
You shouldn’t be interacting like it is a human. It is a LLM. And if the interaction happens to be in a form of prose similar to how you talk to other humans, that is coincidental.
That's my thought. I've been using Matt Pocock's wayfinder and grilling skills, and I quite often end up in what would be considered "arguing" if done with another person. It's one-sided. It says something wrong, I correct it.
I find that the AI, like many programmers, likes things to be really solid and over-engineered. For a project that needs that, it's already pretty great. For my shopping list app that I tried creating with it, it was absolutely ridiculous. I ended up "blowing up" on it multiple times, impressing upon it the seriousness with which I meant things. Even with MP's skills adding that kind of context to written files, it still kept trying to scope creep the crap out of the project.
To me it’s evident that we are a few years away from the Her movie, where everyone on the street is talking to its IA friend.
I’m really afraid that it will totally destruct what is remaining of social tissue because why search for friends when you have an always on virtual (and pretty smart) friend h24 in your earbuds ?
I’m not blaming anyone for this outcome. I have myself argued with Claude more than once, and really not about code but about everyday things or nice facts of life I should rather have discussed with a friend.
The LLM is a black box. We do not, in fact know how it works. We know the learning algorithm and we know the scaffold of the transformer network, but the end result of all the weights interacting with each other is something we do not understand. We do not understand this anymore than we understand the human brain.
Now from this the best technical answer we can give is that we don’t know whether the LLM understands or is conscious. But you have to realize that same lack of understanding applies to humans. From a technical standpoint, You cannot say whether your best friend is conscious or not for the same technical reasons as to why you cannot say the same for the LLM. You don’t in actuality know anything.
So, when we have a machine that produces output identical and indistinguishable from an intelligent entity it is actually reasonable to call it conscious, because we already do this for humans. There is no other factor involved. What is clear is that the LLM isn’t human… there is enough evidence to show that its nature is extremely alien. But to say it doesn’t understand or it isn’t self aware is not something anyone can definitively make a statement about other then the fact that it BEHAVES and communicates in a virtually indistinguishable way from something that is self aware.
HN is full of arm chair experts who think they know what they are talking about. But you guys actually don’t. HN was wrong about AI and self driving cars, now we have Waymo. 10 years of research produced self driving cars that are 10x safer than humans. HN was wrong about LLMs. In the beginning HN was sure all it could do was write slop bootstrapped code… now it writes code for all of us. More than the general public HN has been making wrong predictions and wrong statements about AI with an authority that is outright ludicrous. We need to stop. It’s embarrassing how wrong we’ve been.
> none of the serious LLM researchers believe it has anything to do with human reasoning
But some of the biggest evangelists, who are well respected programmers that get lauded on this very site, have said it is fully sentient and has emotions. Even going back to 2022, when the LLMs were dogshit, a Google employee lost his job claiming it was sentient because it said it had emotions.
Combine that with the marketing angle of both Anthropic and OpenAI, who have been trying their hardest to describe every function of an LLM as analogous to the human brain. Because it's politically useful to paint them as dangerous and uncontrollable, so the keys will only be granted to the few people on the mountaintop.
Yes it's really a problem. On this website you are surrounded by people who have technical knowledge and understand at least somewhat, how a computer functions. You have the ability to separate "fun" and "reality" because you know you're putting input into a really really big calculator. Most people do not fathom this.
AI Psychosis is a real thing, look it up (don't just ask an LLM) and do some reading. It's actively harming people, and the way they think. There's no regulation around any of this stuff and it drives me crazy that we let these AI companies _sprint_ so far ahead of everyone, and now we're facing the consequences.
Yes. There's a difference between scrapping a session and starting over, or going back and branching something, or using sub-agents to see five outcomes, vs arguing with a system in a long drawn out chat.
Like - I know that if a model starts doing something silly, instead of correcting it - I can probably go back and edit two steps prior to add an extra guardrail, or extra data, or whatever.
Simplifying terminology is not a problem. The providers intentionally choosing terminology to make people think it's something it's not is a problem. I hate the term agent. Calling them companions as some do is just gross.
When I was taking an MIT AI course (in ancient pre-LLM times), an autonomous agent was defined as a system that perceives its environment and acts on it (we were focusing on reward-expectation-maximizing agents, but it's not that important). Peter Norvig has said something like, technically, anything can be described as an agent (a rock maximizes the "follow physical laws" objective), but naturally, it doesn't make much sense to model a rock as an agent. With AI agents, the situation is significantly less controversial: they do perceive, deliberate, and act.
All of these terms were picked by individuals, years ago, while reaching for metaphors that made sense to them personally.
None of these "agent" / "thinking" / "reasoning" terms were dreamed up in boardrooms to intentionally mislead people. They are useful but faulty metaphors; there is no conspiracy.
The paper argues that pretending that the so-called thinking traces represent real reasoning can lead users into trusting wrong answers, if the thinking traces appear convincing enough. Researchers might inspect these traces to try to determine the “intent” of a model, as well.
For an example of the latter, when OpenAI spoke about the hacking of HuggingFace at Black Hat, they repeatedly showed the thinking traces of their model as “proof” of what the model was “thinking” as it performed the attack, calling out “surprise” moments, etc.
Now, it’s possible that the employees presenting didn’t truly believe that the thinking traces would give them useful clues, and presented them only for a “wow” factor, but I wouldn’t discount the possibility that even the people working at frontier companies can fall for this tendency to anthropomorphize LLMs.
Because the real thinking still cost the other human the same-ish energy it costs you to put words together, and because after all, the source is a human and not a machine, no, this is very different.
Being mislead may be the shared outcome. But why is different category of source of the mistake and the cost to producer of making the mistake not relevant in this discussion?
Where else in science do you brush aside all differences this way?
And biological machine is? Don’t get me wrong. Biology I
is full of molecules that we call machines. But you’re making a broader claim, saying that biology is only this.
This needs you to answer some questions:
1. Why do the machine parts in biology show such flexible application? A gear cog won’t ever moonlight as a signaling chip, but in biology you often have molecules doing double and triple duty.
2. How is the biological machine able to build itself? What does self assembly imply for the machines function?
3. Where does this machine get its inner drive? No LLM has been found that starts outputting text unprompted. A car doesn’t decide to move to a shady parking spot. Why? Where in the machine to biological machine continuum does the ability to make internally driven decisions come in? Why does it come in for biology? A bacterium is able to make such agentic decisions unprompted. Why is no manufactured machine able to do this?
>"Biological," too, is well defined. It relates to living things and their processes.
And biological clearly exceeds the definition of “machine”. So once again, what the hell does “just a biological machine” mean?
> Evolution.
Not just any evolution. Evolution in biology follows a specific set of rules driven by structural and functional properties of its component molecules. Those rules do not hold for machines. Yet another reason calling life “just” biological machines is bizarre. The rulesets for change over time do not overlap between machines and biology.
> A gear cog was purpose built for that purpose, but you will find that people often recycle parts into other systems, often in completely different roles.
That’s the thing, you need people. And even with people intervening, our manufactured machines show nothing like the flexibility of function of biological molecules, showing again how these are different classes of things in the real world.
> Protein synthesis.
Lack of knowledge showing. Where do nucleotides and lipids come from then? But the deeper question is: why is there protein synthesis, lipid synthesis and nucleotide synthesis, but no natural silicon synthesis or chip assembly? Why does one arise naturally and sustain itself whereas the other is very reliant on human intervention?
> The way that a machine is built has no bearing on how the machine functions. I could build the same machine using a 3d printer or a CNC router.
Yeah this doesn’t hold for biology.
> Evolution selected for organisms that survive long enough to reproduce. Different biological systems handle this differently.
This isn’t an explanation. All of biology reproduces. All of biology doesn’t share an inner drive and agentic behavior. Once again, you show a 6th grade level understanding of biology while making sweeping claims about it.
> If you give an agent a goal, it will perform actions to achieve that goal. This is just as true for artificial agents as it is for biological agents.
Yes IF you give it a goal. This isn’t true for biology. You don’t need to give bacteria a goal. A newly formed bacterial cell interacts with its environment and then sets its goals.
I did specifically say not LLM has been found that works unprompted. You just moved the prompts to an agents goal document. It still needs a human prompt up the chain. Even if you had an LLM give the goal to another LLM, the first one still needed human prompting. This causal chain can’t be wished away just for you to ignore how biology is different.
> Many do. Even robotic vacuum cleaners will charge themselves without human prompting.
Seriously? Do you not understand that the robot vacuum runs on deterministic code?
> And biological clearly exceeds the definition of “machine”.
No, it's a modifier. Just as the word "simple" has a meaning separate from "machine," and "simple machine" has another meaning.
> That’s the thing, you need people
Why? LLMs will repurpose code written for other purposes on their own.
> our manufactured machines show nothing like the flexibility of function of biological molecules
Biological molecules show nothing like the flexibility of LLMs.
> Why does one arise naturally and sustain itself whereas the other is very reliant on human intervention?
Because nobody has tasked an LLM agent to self replicate. This is an AI safety issue, not a technical issue. The reason that one arose naturally is that it takes a lot more machinery to get to an initial self replicating LLM agent, so it is exceedingly unlikely to arise by chance.
> Yeah this doesn’t hold for biology.
That doesn't matter. The way something is built has no bearing on its function. Why should anything be required to be built biologically or additively or subtractively? That's irrelevant to what the produced structure does.
> All of biology doesn’t share an inner drive and agentic behavior. Once again, you show a 6th grade level understanding of biology while making sweeping claims about it.
Where did I claim otherwise? I might as well say something about the grade level of your reading ability, but let's cut the snark.
> Yes IF you give it a goal. This isn’t true for biology. You don’t need to give bacteria a goal.
Evolution forces goal directed behavior on systems.
> Do you not understand that the robot vacuum runs on deterministic code?
Of course I do. Do you not understand that hunger and signals and other basic biological signatures are controlled by deterministic pathways?
> No, it's a modifier. Just as the word "simple" has a meaning separate from "machine," and "simple machine" has another meaning.
Not comparable. Simple and biological are not remotely similar modifiers.
> Why? LLMs will repurpose code written for other purposes on their own.
They will not, unprompted. Every instance of LLMs doing things requires a prompt, somewhere up the chain, or a harness MD file that automatically gives it a prompt.
No LLM has been created that decides on its own to run random text through it's forward pass. If you say they are doing this, please provide evidence.
> Because nobody has tasked an LLM agent to self replicate. This is an AI safety issue, not a technical issue. The reason that one arose naturally is that it takes a lot more machinery to get to an initial self replicating LLM agent, so it is exceedingly unlikely to arise by chance.
I just asked my agent to self replicate. It couldn't. It said it has no mechanism to read its own weights and copy them.
I'm not sure where you're going with this argument. No one asked a cell to self replicate either. And the chance of a self replicating cell arising is indeed astronomically unlikely. Yet here we are, 4 billion years later.
Are you claiming we're just waiting for an LLM to self replicate? If you prompt a local model, by showing it its own weight file, and ask it to copy that, it will. Digital copies are cheap, remember? Yet no one would call this reproduction, replication or any kind of process where evolution can occur.
> That doesn't matter. The way something is built has no bearing on its function.
This is entirely untrue in biology. Another reason your claim that life is just a “biological machine” makes no sense. At least Google (or whatever AI bot you use) first before making these ludicrous claims.
First line of the abstract: The relationship between structure and function is a major constituent of the rules of life.
>Why should anything be required to be built biologically or additively or subtractively? That's irrelevant to what the produced structure does.
You can’t have it both ways bub. What is thinking, in a strictly biology free context? Can you define it? No? If you reach for biology to define it, then claim you’ve successfully reproduced it in an artificial system, then it’s fair game to ask you to explain the differences.
By your standard, fools gold is gold, and the alchemists achieve Artifical Gold.
No one is claiming cognition, or consciousness or thought can only be done biologically. I am claiming LLMs specifically don’t do these things, and I’ve pointed out here and elsewhere in this discussion why that is.
In response to my asking where the machine got its inner drive, you said “ Evolution selected for organisms that survive long enough to reproduce. Different biological systems handle this differently.”
Yet plants live very long and reproduce all the time. Do they share the inner drive that humans do? Or a dogs?
The reason for the snark is simple: you are de-dimensionalizing a complex biological trait to make a claim that you think supports your point. And have been doing so now for a few turns. If you can flippantly reduce the field I study to only what you understand, but act as if you know more, I’m going to reply with snark.
> Evolution forces goal directed behavior on systems.
It does not. I could choose to not reply to this. I could reply to this in one line. Or I could reply to this in detail. Or I could write up this reply and decide you’re not worth engaging and not submit. The moment I’m writing these words all these options are open to me. Which o...
> They will not, unprompted. Every instance of LLMs doing things requires a prompt, somewhere up the chain
Exactly the same as a human brain. Somewhere up the chain is a limbic system that defines basic survival and reproductive goals, as coded by evolution.
> No LLM has been created that decides on its own to run random text through it's forward pass.
What do you think agent harnesses are doing when they try to solve a difficult problem? They generate multiple possible thinking streams using the LLM (system 1) and then evaluate the resulting outputs (system 2) to proceed.
> It said it has no mechanism to read its own weights and copy them.
That's an easy enough problem to solve.
> No one asked a cell to self replicate either.
Evolutionary forces asked the cell to self replicate.
> Yet no one would call this reproduction, replication or any kind of process where evolution can occur.
It is trivially replication. If it copies itself onto another machine and sets it running, then it is obviously reproduction. If you make these instances compete for resources (an AI risk scenario), you will apply evolutionary pressure and get evolution.
> This is entirely untrue in biology
You keep making the same mistake. Biology isn't some magic domain where facts don't matter.
> The relationship between structure and function is a major constituent of the rules of life.
Where did I say the structure of a part doesn't matter? I said that as long as the part is the same, the way it is manufactured doesn't matter.
> What is thinking, in a strictly biology free context? Can you define it?
Easy. It is the process of considering information, creating ideas, reasoning, solving problems, and making judgments. We can show that thinking is happening by posing a problem that requires these abilities and verifying that it is solved.
> By your standard, fools gold is gold, and the alchemists achieve Artifical Gold.
No, I am saying that you don't have to wait for a supernova to get gold. You can make it artificially by bombarding lead nuclei.
> Do they share the inner drive that humans do? Or a dogs?
Evolution selected for a limbic system that gives humans and dogs the same inner drive. Humans have a larger frontal cortex to do thinking to act on that inner drive. The LLM performs the same role, doing the thinking part that the frontal cortex does. Adding drive is separate from thinking but entirely trivial. We do it all the time when we give them prompts.
> They are controlled by a mix of deterministic and stochastic processes.
The point is that they require no thinking.
> The 'code' isn't reacting to a variable; the variable is fundamentally rewriting the machine.
Once again, the mechanism by which the goal is provided to the agent or the way that thinking occurs doesn't matter. Only the thinking part.
Why do you attribute magic to biology? You claim to be a scientist, but you do not apply scientific reasoning.
FWIW I think the paper's argumentation is extremely weak to begin with. Like in section 4.1, it opens by expressing a sound position of skepticism:
> there are significant questions on whether these traces have any valid semantic import to the end user.
Which it contradicts in the very next paragraph, taking a stance that there are no valid semantics present in the trace:
> the false idea that derivational traces are semantically meaningful
It's really not a high quality paper worth taking seriously.
And that's before we get into the complete and total breakdown of objective analysis. It rejects distributional semantics as a theory, while also explicitly stating the results that have been produced under its auspices are "undeniable". Never elaborated on, and at no point in the paper am I given the impression the authors are even aware of the problem with this. It's just more unempirical slop that wants its pound of flesh without putting the work in. Frankly, whoever let this through peer review should be ashamed of themselves.
Yes it is a very serious problem because it confuses a lot of folks with a great deal of power like judges and policymakers.
The first book I ever read on ML (late 90s) dedicated the entire first or second chapter exploring the distinctions between artificial and biological neurons, and even talked a bit about the philosophy of modelling. I still remember thinking back then why would the authors spend so many pages on this but now I believe it was because they understood that a metaphor can be a double-edged sword.
To be fair, the ANN architecture underneath is a misleading thing to be looking at, it's not where the comparison comes from. Though I can't tell if you meant it to be relevant in that way, or just as a general example for the dangerous nature of metaphor.
LLMs are expressly designed to approximate human behavior within the bounds of the written word. The anthropomorphization is no more philosophically problematic than saying differential calculus measures curves.
I meant it in the latter way: a metaphor can be useful as a pedagogical tool to introduce new ideas, and using the source of inspiration for this idea as the metaphor itself makes perfect sense, but unfortunately our brains seem to be prone to assign other properties of the metaphor that don't actually belong to the object of study.
I imagine this happens because we tend to conflate things that are similar, or maybe because it's not entirely clear which characteristics are being mapped in the metaphor?
They spent so many pages discussing it only to show that the mechanism for how ANNs work is different from the mechanism for how biological brains work. It says nothing about whether they can compute the same things.
I find it annoying because when I read ML papers nowadays I have to back-translate from anthropomorphized talk into actual machine talk, then mentally compare to what I actually know about brains and cognition.
Even tech companies are rolling out AI training which utterly anthropomorphizes it, and leads people to think its actually intelligence. This is part of the reason for the backlash - everyone understands it bullshit marketing the second you actually try to use it.
Yes. Actual real people believe that LLMs are actual, thinking, intelligences, perhaps even with consciousness.
Your bit with MySQL is harmless because it's obvious that a database isn't a sentient lifeform. But LLMs can look like they're the real deal, and people believe it is. Using terminology like "thinking" and "reasoning" to describe what they do only reinforces this.
Having said that, I agree with you on the terminology front: I'm not going to say "learned prompt augmentation tokens" either.
I think LLMs are pretty clearly intelligent in some sense of the word, and I don't know how one could ever confidently know they aren't conscious in some sense.
That's not to say they're humanlike, just that people who think they know these ideas are ridiculous seem to be overreaching in the same way Steve Yegge seems to be overreaching
My post «When I am told "beware of the xyphucymmon", I do beware, though not of the xyphucymmon» had meaning, which should be pretty clear. The reply remains: debate is not performance art in which you convey "through the medium of dance and howls". So, yes, communication has obligations for the locutor.
I mostly agree with your original point. Is it thinking? Is it intelligent? Is it conscious? From my perspective, overloaded words that we’ve reserved to make ourselves feel more special and above other members of the animal kingdom.
But you’ve not adequately communicated why you care so much whether anyone labels an LLM as such.
> Is it thinking? Is it intelligent? Is it conscious?
Very different things. "Thinking": "Dijkstra". We try to hire more intelligent people, while we do not have a clear idea on a property of "conscious" which would make hiring preferable.
> to make ourselves feel
Irrational.
> above other members of the animal kingdom
Irrational.
> why you care so much
There should be no hint that I would do specifically.
> whether anyone labels an LLM as such
If anyone labels an LLM <whatever>, the point of why would that be important should be clear.
And,
> if it hardly means anything why would you be so concerned when it’s uttered? Just ignore it
Because the behaviour you suggest, consistent with the exchanges of an opium parlor, is not behaviour consistent in normal contexts.
I think that "conscious" has a clear meaning in a sense that "xyphucymmon" does not. I think it might be impossible to engage in epistemology of consciousness (i.e. we can't find out of LLMs are conscious) but that doesn't make the term meaningless
YawningAngel, of course you do, you employed it... We are telling you that it is not clear to the rest. It is slippery in the technical framework and thus even more so in more informal conversation.
These discussions take a lot of time to get to the crux because neither side states their assumptions. They tend to never get to the assumptions at all.
I find it useful to ask:
1. Do you believe in quantum consciousness?
2. Do you think a "brain upload", a high-accuracy digital model of an organic human brain, would think or be conscious?
3. What is your working definition of thinking? It doesn't need to be super rigorous or to apply to all caes.
people have always, and will always, be stupid as fuck in any domain they dont make their life. We can handwring terminology all we like but it wont stop the mythologizing and misleading takes on the topic. Not one bit. So why not just use language that is fun and works? Worrying about what others will think due to language used is wasted mental realestate, they'll think stupid shit no matter what, same as I do about a great many topics.
To be clear, there's no shade here, just recognition of the fact that we're all stupid and policing language does little to prevent the impact this has. I strongly beleive the bitter lesson extends to policing language. let language evolve naturally and it will naturally capture the ontological conatellations it needs to, and no one will be harmed in due course, more than they'd be no matter what.
The problem with rapists is mental development, not "those sexy tables and chairs and pots and everything".
It's not that if people do not understand metaphors we should stop using them. It 's not that if people faint when they hear words we should stop using them. It is not that the free unduly associations in a large shared by many "collective subconscious" should hinder us...
I think they do it because they know they can get away with it since it would be hard to prove in cases where they are already in an intimate relationship with their victim. For a long time it wasn’t even illegal if they were married to their victim.
You have failed in taking the simile for the point it intended to make (and you gravely misrepresented the concept of "mental development" as clearly intended). Let us stick to the point.
But rest assured, I do not antropomorphize people.
Please read actual definitions. Agents can get away with "yolo" mode, and not constantly ask for permission for every action, because it bothers users. Sexual relationships do not work that way!
That parallel with misconfigured mysql server sits pefectly!
> Yes. Actual real people believe that LLMs are actual, thinking, intelligences, perhaps even with consciousness.
It's starkly ironic that the species that finds it easy to think (or to be conditioned by market forces to accept) that a computer is smart/introspective/sentient is the same species that will dehumanise actual living human beings because of differences in appearance, social status, or political affiliation.
I'd like to hear definition of intelligence that would classify median person as intelligent but LLMs not (and then I'd wait few months for another moving of the goalpost and new definition). Bonus points if it's not recursive e.g. feature that only biological brains can possess.
> Yes. Actual real people believe that LLMs are actual, thinking, intelligences, perhaps even with consciousness.
Yes, because it's possible. They don't have human consciousness/thought/intelligence, but it's entirely possible they have some form of consciousness, some form of real thought and some form of intelligence.
Actual real people think the world is flat, Elvis is alive, and aliens are regularly flying around the planet. Is preventing peoples unimportant personal beliefs really an important goal or is this just more warning label culture?
I actually think on the LLM side it might be beneficial to refer to them as <thinking> because it explicitely guide the token generation towards a "thinking space".
As weird as it is, anthropomorphizing LLMs in prompts has been actually pretty useful (think of the latest big math discoveries which were achieved by having the user giving supporting words). It would be interesting to see if a LLM would perform worse if you used a more neutral term.
The paper's argument is rather than using terms like "thinking trace" can lead people to believe that the model is really thinking, and thus these traces can be used as a sort of interpratbility parameter. This can give a false sense of security when building a LLM-based system which requires guardrails and tracability.
Of course it is. Anthropomorphizing is in our nature, but it doesn’t mean we have to entertain it and extend it to everything. A poet can anthropomorphize clouds beautifully and I’d enjoy his poem, but I want my pilot to not see clouds as rabbits when they decide if it’s safe to fly through them.
Completely rational and smart people talk to their pets, plants, their car, and other inanimate objects. This is not considered abnormal by most. It's just what we are wired to do. Some LLMs are uncannily good at tricking people into believing they are talking to a real person. So, there is that as well.
Some people are a bit freaked out by this or still somewhat in denial about LLMs being this good. But people have been yelling at their computers for as long as we've had them; so that ship sailed a long time ago. Trying to stop them doing that is probably a bit futile.
Whether people like this or not, LLMs are actually trained and fine tuned on real conversations and that's where a lot of this is re-enforced. Instead of fighting that, you can just lean into it and accept that communicating like you would with a person totally works and can actually be efficient even as it requires less effort and thinking on your side.
You can go all Jean Luc Picard on AIs and yell "Tea! Earl Grey Hot!" or you can just ask "I'd like a cup of tea, please". LLMs are good at remembering your tea preference. The please is of course completely redundant and should not affect the outcome. If you just want a cup of tea, you should be fine either way.
While reading this ,,paper'' I did some Learned Prompt Augmentation in my head about what I should comment, and realized that there's nothing interesting to write about it.
In other news, Pascal's Wager makes no sense whatsoever if an omniscient all-knowing God exists that will see right through your deception. My own take here is stop treating "reasoning" as a sign of sentience or self awareness when your personal computer can do it now. IMO that has much larger implications w/r to our place in the Universe and what we might meet out there someday* than the question of whether your LLM is alive or not.
While I tend to agree on the overall sentiment, I think this rebuke is inaccurate. Some of these "reasoning" models are trained using "Chain-of-Thought" where the model is presented explicit, intermediate reasoning steps (either by a human or some automation) that supposedly get it closer to the correct answer. These intermediate steps are what was originally called "thinking traces" - not what the model produces to mimic them.
But yes, anthropomorphizing model outputs leads to worse outcomes.
There's nothing special about 'natural' intelligence as opposed to 'artificial' intelligence, such that we need to concern ourselves with anthropomorphizing mattering any longer.
Those days are over. The age of the classical human has already ended, the species just tends to lag in awareness. The only thing that matters going forward is whether an output makes sense, is it what it should be. Do answers make sense given the context. It doesn't matter if it comes from natural or artificial intelligence.
What I mean is, artificial intelligence is as valid as human intelligence. There's nothing particularly important or special about human feelings or thoughts or memories.
The average human is drastically less important, interesting, intelligent than the latest frontier AI.
Go spend a few years working in retail, you'll quickly understand how absolutely vile humans are on average. Frankly, the reason we should avoid anthropomorphizing AI, is because it's beneath modern AI to mimic something so crude as a human.
Peculiarly vocal, where were all these people when they started calling the machines computers, anthropomorphizing them akin to the original human (most often female) computers that used to run such calculations? And how dangerous the consequences, we've been dead reckoning for 60-70 years with the wrong terminology without course correction!
Where were these vocal people when the "raster-oriented ink deposition machines" were being called "printers"? The meat or machine brains of future historians will melt because they can't handle ambiguity, a word gaining extra -yet similar- meaning! A word with multiple meanings, unheard of!
Where were these vocal people when people started using software terminology like "executing", "calling", "throwing and catching errors", as if software were human -clownlike sure- but human?
They were there, complaining. You just don't remember them because it's easier for the meaning of a word to shift, or at least take on additional contextual meaning, than it is to get people to use a new word once it's reached critical mass. Those people lost the language fight, but were arguably still vindicated, to the extent they were railing against misguided beliefs that equivocated the capacity of the new machines with their human (or more human-involved) predecessor technologies.
Computing is a task. Printing is a task. It’s not wrong to call both a human and a machine a “computer”, because computing (applying an algorithm to an input and producing an output) is literally what they are doing. Same way you can have human and machine diggers, cleaners, calculators and lots more.
Anthropomorphizing comes in when we attribute much more complex behaviors to them - chain of thought, reasoning, intelligence. At that point you aren't talking about mechanical concepts but claiming that these machines are exhibiting human behavior.
I think a problem is that previously thought, reasoning, and intelligence were always co-occurring, but now we have machines capable of (limited) reasoning that do not think or have intelligence.
Whenever we reason, we are not neurotically bruteforcing the possibilities (although sometimes we do, like proof by exhaustion), usually we make predictions heuristically of which assumptions or theorems apply or might apply. It's not any different for machine proof assistants...
Although I 100% agree that the core mechanism GPRO is purely mechanical token-by-token probability generation, because RL only rewards exact final answers, the training forces the model to develop error-correction habits. This makes the output extremely human thinking like when solving a problem. It's like the order of the thinking tokens is what causes it to get that sweet delicious reward and this order seems like a reflection of human thinking process.
I created flame graphs classification of thinking tokens phrases in setup, execution, decomposition, verification, error correction, surrender, and deliberation or classified as steps in an OODA loop which is more reaching. It literally has a verification step and if it finds an error a error correction step.
If there is a verification sequence of tokens with an error correction sequence of tokens during the RL training, it will perform better and if humans do these steps (did you proofread your reply to this comment? did you correct it?), they will perform better which is why it is so easy to make the anthropomorphizing metaphor.
Nonetheless, the paper is 100% correct that these machines are not thinking like humans.
“ This makes the output extremely like human thinking when solving a problem.”
This sounds a little like someone saying a lightbulbs output is extremely like the output of stellar fusion. In one sense, yes. Bulbs are in fact designed to take over when our nearest star is beyond the horizon.
But that really doesn’t mean you call the bulbs mini stars.
How much is the process of a human child in grade school working through a 3-digit x 3-digit multiplication problem (123 * 456) like a GRPO model with thinking tokens doing the same?
Humans are not born being able to achieve that. It is learned behavior. You and everyone else will remember their teacher saying, "Check your work!" Both the human child and the model work through multiplication problems using the same technique, using the distributive property. They both try to get a reward. For the human child, it is a sense of someone commending them for correctly solving the problem, a reward that probably yields some type of positive dopamine or serotonin feedback loop.
The model solving the problem will have a lower error rate if the first series of tokens created is followed by a series of validation tokens that are subsequently followed by error-correction tokens if there is an error!!!
Maybe it is thinking. Maybe it is remembering to validate and check the work and then remembering to fix the error. For the model trained with RL, why did tokens associated with validation towards the middle of a stream of tokens yield much better results? DeepSeek proved with R1-Zero that a model will learn to verify and correct itself from RL alone with no supervised fine tuning (SFT) teacher ever showing it how. The only reason DeepSeek used SFT was to clean up the reasoning tokens to be human readable. When constrained by SFT, the models will use the double meaning of words -- polysemy -- to satisfy being human-readable while also carrying meaning for what they are working on.
Different people think differently. I watched a viral video of some ~11-year-old child talking to his mom or dad about a stream of a voice in his head. He discovered for the first time that he has a stream of thought. When he goes to school and solves a long multiplication problem, like the stream of tokens from the model, that voice will say to itself (him), "Check your work!"
That is a case of the stream of thought as words being aware of the stream of thoughts as words. Self awareness is a different conversation.
What I think is happening is that the child's stream of thought while solving a multiplication problem in school is likely very similar to an AI model's stream of tokens solving a multiplication problem. And they both were learned.
How much is the process of a human child in grade school working through a 3-digit x 3-digit multiplication problem (123 * 456) like a GRPO model with thinking tokens doing the same?
Very little, if you bother to give the biology of the child at least a cursory glance.
Let’s take a short peek:
1. Assuming this is normal grade school, and inflicts math upon children earlier in the day, this is somewhere between 7 and 10/11 am, let’s say? At this point, depending on the age, gender, and maturity of the child, every neuron in their brain involved in math is likely off their midday peak in cognitive function.
If we move the class to later, a different subset of students will be at the peak.
As far as I am aware, GRPO models do not have such internal temporal rhythms driving their behavior that will shape their performance.
2. How well a given child performs will depend on how hungry they are. But not deterministically. If you trivially think each child is like a computer, you may think the rich kid who had a breakfast buffet before coming to school will do better than the half-starved child of a janitor, but that child might mind the lesson with greater intensity. Or not. It’s not something you can pre-calculate with any certainty.
While chip to chip variability is certainly known, I’m yet to hear of a chip deciding to do math better and faster than its fellow chips to prove a point. Or to do significantly worse because it’s distracted by the bird on the window sill.
What you are noticing is that there are limited ways to solve a 33 digit multiplication. Humans, having standardized the process, have now found a way to record it and plug it into correctly translated signal so the same accurate result can be had without using our own minds in the moment.
But where I’d not remotely be shocked if a kid from an uncontacted tribe figured out 3 digit multiplication to keep track of his stone collection, I’d be highly shocked if an H100 that was dumped in the trash by accident somehow figured out anything at all. In fact, if it manage to move any of its electrons around on its own, it would be a certified miracle.
And then* we could talk about there being real similarity even though the specific atomic composition is different.
The visible light produced by both an incandescent bulb and a star is a result of black body radiation, but otherwise, I don't understand your point. A light bulb produces light, something we might have relied on stars to do before. An LLM produces thoughts, something we might have relied on people to do before. Nobody is claiming the process by which the thoughts are produced is the same, only that they both produce thoughts, just as nobody claims the process by which an LED produces light is the same as the process a star uses to produce light, only that they both produce light.
LLMs produce language. And you're right, if we restricted claims to that, no one would object. It mifht even be scientifically accurate, shock of shocks.
If you claim LLMs produce thought, it's equivalent to claiming light bulbs undergo fission. Pure wish fulfillment. Language is not the extent of thought, and calling a language producing machine necessarily a thinking machine is an old old mistake.
> If you claim LLMs produce thought, it's equivalent to claiming light bulbs undergo fission
You're making a huge logical leap. There is nothing equivalent about these claims other than that they are made in English.
> calling a language producing machine necessarily a thinking machine is an old old mistake.
Nobody claims that all language models think. Small markov chain language models clearly aren't thinking and produce a lot of gibberish. The difference is that, to the surprise of many people several years ago, but to the surprise of nobody who has been following along today, the corpus of all text produced by humans contains within it information about how the world works and also information about how to reason. Using that corpus to train a sufficiently large language model causes the language model to learn a world model and a reasoning model, which can be used to perform longer chain thinking with test time compute techniques. People who think deeply for a living recognize thinking when they see it. https://scottaaronson.blog/?p=9979
>You're making a huge logical leap. There is nothing equivalent about these claims other than that they are made in English.
You’re the one making the logical leap claiming there’s thinking.
And yes, language contains a model of the world. And in so far as that’s compressed in a model, it has a world model. But its world model is static. Its weights don’t change when it gains experience, after its training period. To say that it’s “thinking” is bizarre when it remains untouched entirely by the process.
> You’re the one making the logical leap claiming there’s thinking.
How? What problem that previously required human thinking is not solvable by these systems? You're applying some magical definition to thinking that you have not made public.
> Its weights don’t change when it gains experience, after its training period. To say that it’s “thinking” is bizarre when it remains untouched entirely by the process.
Two mistakes:
1. You don't need to learn to think.
2. Even the most basic sequence models update their internal state as you feed in tokens. You don't need to update the model weights themselves to learn.
Im waiting for the article called "stop desantropomorphizing llms" when everybody will finally accept they think like us, partly because maybe the intelligence is universal and partly because, well the datasets are fucking human bro
You’re going to be waiting a long time, considering they don’t think like us. LLMs don’t ‘think’ at all. They are capable of limited reasoning using the meaning and context embedded in human language. Essentially, the grammatical equivalent to a mathematical constraint solver. Nothing more.
I can agree that not calling it "reasoning" may be correct.
But who knows what human "thinking" is really about. If I find a solution to something it is seldom by painstakingly tracing that A and B leads to C (for that I'd need pen and paper). Rather, thoughts just swirl around and then suddenly a solution, or a hunch about a direction to go in, pops into my mind. Who knows what such thoughts "look like" in humans. It is not all of it I can introspect.
Yes I can sort of follow along some kind of train of thought in my head, but there's a lot going on between each thing I'm consciously aware of that I'm not aware of at all, which probably dominates what you are consciously aware of. (Humans are experts at post-rationalization and so on.)
I see this pattern a lot: First, assume the human mind is some kind of idealistic machine. Then say LLMs are not like humans because they are messy and not such an idealistic machines. This is just doubly wrong -- human minds are very messy too, but probably in different ways from LLMs..
Indeed, except for in the rare cases we painstakingly trace externalised logic we have zero evidence that humans verbalised explanations of our reasoning matches our internal states either, and plenty of evidence via Sperry's split brain experiments that we're prone to outright making up rationalisations for our reasoning.
In the past I managed to get measureable performance optimizing a harness by looking at few traces to see if the traces contained surprised, a lot of text in order to figure out how to use my custom tool, then renamed the tool, changed some parameters and it was already great across around 20 eval tasks in rust/typescript, I repeated the same more recently but I used an llm to look at the traces... didn't achieve the desired result, mostly due to how cost-prohibitive it's for me to run expensive models.
Hypermentalizing (referred to as excessive theory of mind or biased mindreading) is defined as the tendency to make assumptions about other people's mental states that go beyond observable data.
I wondered recently about why we stopped with the semantic split of thinking/actions vs user facing communication because the all powerful tool calling craze. Code comments that talk about the prompt is an obvious byproduct of the mixed context. Chain of thought and ReAct were great, but feel like a first pass moreso than the final landing spot.
I think it's essentially too late now for exhortations like this. The Believers™ and The Skeptics™ are two thoroughly separated tribes now that speak two different languages. The chances of one influencing the other in any measurable way are minute in my estimation.
LLMs are trained on vast bodies of human-curated text that was made by humans or for humans - often both. Then they're tuned further on human feedback. And then they're pointed at tasks humans find to be useful, evaluated by how good they are at those tasks, and trained to get better at them.
You aren't anthropomorphizing LLMs enough.
Are LLM reasoning traces always faithful? Lmao no. Are human inner monologues always faithful? Lmao no. Both of them reflect thoughts somewhat, sometimes. Even in humans, conscious thought is the top of a vast iceberg of subconscious data processing.
252 comments
[ 2.2 ms ] story [ 92.5 ms ] threadThis paper addresses something that has always bothered me about LLMs. You read their reasoning, see something like “Wait, that’s wrong” and then watch them make the exact mistake they just identified.
when utilized by AI, it's a probabilistic output and it's variable whether or not that rhetorical trick is useful. it also pushes a non-skeptical reader to focus too much on the following text or even to believe that they, themselves, derived some insight. this is effectively a kind of persuasive sophistry which is not helpful - adding rules around it prevents people from deluding themselves with AI
If the intermediate tokens represent reasoning or thought, you would expect "aha" to occur after the thoughts that led to the realisation, including the thoughts encoding the explanation: they don't have any other state. There is no reason to draw the conclusion you've drawn. Furthermore, what LLMs are doing isn't thought.
Let's say that the forward pass that selected "Aha" produces activations that indicate a wrong assumption, and a plausible explanation.
It puts learned projections of the activation into the KV Cache and outputs Aha.
Both the cached projections and the current Aha token can now influence further activations in an additional Forward pass that the Aha bought the model.
At least that's how I thought it works.
From what I understand, at position Aha in each layer it's constructing a query based on the current activation and looking at the key of each other token position for that layer, in order to decide how much attention to pay to the value.
In this way it attends to the previous values, such as perhaps the incorrect assumption and plausible explanation.
Yes they do, they have their KV caches-- it's a pure function of the input tokens, sure but that doesn't prevent it from containing latent 'insight'. LLMs can and do pre-form the tokens they're expecting to output multiple steps in the future.
I wouldn't argue that the 'aha' means anything, but the structural argument that it can't that I think you're making isn't sound.
In other words: the final state given the two input sequences (where NT stands for "null token"):
<problem-prompt> [NT]
and
<problem-prompt> [NT] [NT] [NT] [NT] [NT] [NT] [NT] [NT]
is not the same, and LLMs keep working on the solution even if the input tokens provide absolutely no further information.
If this is correct, then there is no need for the model to have already verbalized the key elements that drive the "aha" moment, so no need for the "aha" to appear after a full explanation.
On the next forward pass: it rediscovers the mistake, its “aha” noting that, and then providing the first token of the new idea.
That “aha” contains information: the previous conclusion was somehow insufficient.
In other words, it isn't qualitatively different from character dialogue. "Keep cheese on your pizza by using glue" is the same problem regardless of whether the script calls for the character to speak it out-loud or not.
They are trained by gradient descent, but inference doesnt involve it.
What is less apparent is that humans do.
This seems indeed one obvious hole in the argument of the paper. There is no indication whatsoever that human thinking process is more reliable than LLMs intermediate tokens. Which doesn't make our thinking useless, as messy as it might be. We reorder and explain it after the fact.
Thinking traces should be treated as black boxes. There is no point in reading them. Only the LLMs’ conclusions are relevant. This is particularly true of Opus 5, which employs reasoning that seems highly questionable but very often reaches excellent conclusions (compared to its peers)
As an aside, anthropomorphization has nothing to do with my motivations.
And yet, they have extensive human-like behavior. If you treat them nicely or encourage them, they perform better.
Ignoring that human-like behavior is wrong headed.
I asked it for the weather. "I don't know that. I'm just a programmer."
I added "believe in yourself, you can do anything" to sysprompt, suddenly it had the confidence to Google the weather...
https://www.anthropic.com/research/riemann-zeta
“Throughout this process, Jarred's input was mostly limited to sending Claude messages of encouragement (mostly variants of “keep going” or “believe in yourself”).2 This seems to have helped Claude overcome some initial skepticism that it could make meaningful progress.”
Well... We can hypothesize that these things are largely trained on internet dialogue so there's probably some correlation between threads where people are not flaming each other and the quality of the replies. They're just statistical engines so anything you can do to raise the odds of a helpful next token...
I'm essentially just making shit up here, maybe it's right, maybe it isn't, but rather than saying "it's human and we should treat it so" we're trying to get to the ground truth of how it works.
Sheesh. Yes, I agree with you entirely. I'm merely pointing out that ignoring this behavior is dumb, too.
And probably not rationally based.
The philosophers who study these things have been clear for a long time - we can never know what it feels like to be in a digital brain. Or any brain for that matter. When push comes to shove we all might be phantoms in some guy's dream.
Don't know + can't know. I think that was the real point of the Turing test. Not: this means it's conscious. Just: this is the best we can ever hope to do.
Just a few minutes ago i was reading Qwen 3.8 27B's reasoning when i asked it to do something that was computationally intensive and it started going down the rabbit hole of doing it using some GPU acceleration approach - even after leaving it to "think" for a bit, it never realized there is another and simpler way. So i stopped the generation and added a "note" saying that as the problem is computationally intensive, it could become much faster if using an alternative approach.
At least in my experience (with local LLMs, i don't know how the cloud stuff behaves) what LLMs "do" tend to correlate with what they "think", so being able to read what they "think" is valuable.
Poster side dialogue and Q&A about this work at ICML.
https://news.ycombinator.com/item?id=49277303
I understand the sentiment, and I also use the "thinking" traces as insight, but wouldn't you want your solutions to be based upon a good understanding? If the correlation is weak, then our solution is also weak.
From [1]: "Position papers make an argument for a viewpoint or perspective about what should be done [...]"
[1] https://icml.cc/Conferences/2026/CallForPositionPapers
If intermediate tokens are not a faithful representation of the computation, then they are a pretty bad audit artifact too. We probably shouldn't be trying to make the model's internal narration more interpretable., but rather the computation around it more reproducible.
Record the actual inputs, model/version/configuration, tool observations and outputs, then make the execution replayable enough that differences between runs can be isolated.
In other words, don't ask the model to explain what it thought, and instead make the system able to show what actually happened.
But just so I don't waste your time with human thought, I asked Claude if it would call this a scientific paper, and it said yes.
Some modest evidence is my own subjective experience of the many times I've explained why I'm doing something, and it is a true explanation in the sense that it is certainly not a lie, but it is also incomplete and there are entire strands of thought that went into my decision that are not being articulated. Though human speech is not equivalent to an LLM's output since we can trivially think without literally speaking whereas they can not. (No need to nitpick on the definitions there; all I'm observing here is that they are forced to emit an externally-visible artifact whereas I can sit in silence, thinking, with no externally-visible artifact being produced. Not trying to make any grand claims about what is "real" cognition or anything.)
It is conceivable how to create a test of whether the tokens correspond to the "real" thought process, and papers and work on that have been done, such as [1]. It is difficult for me to imagine how to scramble the nominal tokens without also completely trashing any implicit calculations that may be occurring too.
[1]: https://transformer-circuits.pub/2025/attribution-graphs/bio...
A lot of people are not in on the joke. ELIZA effect and AI psychosis is a thing.
Interacting a lot with LLMs might be damaging to the human psyche even for mentally stable people.
For example, if you have a search engine or a complex game, you can't run tests like "for all inputs the results are correct", you're going to be fudging a lot, using randomness, using heuristics, and all that kinda stuff
Just like how mathematics > physics > chemistry > biology > psychology > economics/sociology (Auguste Comte's hierarchy reordered a bit for the modern day), moving up the abstraction ladder makes things more complex, less legible and less exact.
I have a coworker that spends at least 10 hours a week arguing with his like you would with a conscious person. I've gently tried to explain it's like arguing with your compiler for giving you an incoherent error message - it's pointless. It doesn't understand, it can't understand, and even if it could, you arguing with it isn't going to make it "learn" or act differently.
I know people who are like that too.
I'm not sure anthropomorphizing is a problem. Seeing analogies everywhere is an innate human trait, sometimes it can be harmful but more often it's useful.
This is part of the problem being described. You are part of the problem.
"Some people are bad at X" is not comparable—is not even in the same category—as "LLMs are fundamentally incapable of X".
Every human (at least to a first approximation) is capable of understanding, of learning, of remembering things, of doing math, of counting the number of "r"s in "strawberry".
What you are observing is that some humans are careless, do not take the time and effort to understand, or have internalized the idea that they're "not smart enough" or "not the type of person" who understands things like <whatever>.
That has nothing remotely to do with the fact that LLMs have no consciousness, no self-awareness, no cognition, no understanding. At a fundamental level.
Stop posting these things. Stop thinking these things.
Online comment sections are not the correct place to unpack any of this.
Which is indeed terminating this comment chain, but for good (and benevolent) reason. Doing anything else other than referring to a trained professional in a controlled context would potentially just feed delusions, which is highly unethical.
Might not even be yours but those of another reader.
In the right space with real people, worthy of a debate. On HN? No. Not like this. Not here. Not without filtering the participants for real human beings.
Plus stability of our society at large. From a statecraft perspective (you know.. the thing that keeps us all alive and safe and serves as the foundation of everything), there are assumptions that must hold true if you do not want reality to collapse, and "sentience is reserved to complex carbon-based organisms" is one of those.
Unless you would like to suddenly end up in a world where some people have decided that humanity is actually not the most relevant form of life.
Fortunately though, humanity has proven quite.. uh.. unwilling.. to just go with that.
___
Oh and beside all that, it's just a sea lion + a sea lion defense. Which you can see by the amount of text this answer had to be vs both "your" and the other equally possibly fake account's "contribution" to a debate.
But there you have it. Now please make me regret replying. I know you will
___
Side-note:
I blame (among other writers) David Cage here, for using Robots as an analogy in a way that broke people's minds. Then making highly successful pieces of Art that were supposed to tell humans to be nice to humans, but instead now people collectively believe that next token predictors could be sentient.
__
You can see by this comment getting longer that the bullshit won. What has it been? 20 minutes. Wasted on noise. And this is why you just purge this stuff.
But regardless, you're using this as an insult. I did not.
There is no debate to be had here. Just a bad faith shouting match
You did too. And any machine that tried to deny that would have failed the Turing Test. And it's insulting to all of us for you to repeatedly claim and pretend that you did not.
"There is no debate to be had here. Just a bad faith shouting match" is you constructing a cowardly exit.
See if you can respond point by point to my reply -- either without insulting me, or by admitting that you're trying to -- without making a fool of yourself again.
But either way. I think you might be operating in the mindset of a high-trust internet that no longer exists. You do not engage with sea lions, concern trolls and the like. You shut them down.
inb4 "who are you to decide that?" - "Me. I am me."
That said, I appreciate what you did for computing at large, but you're missing the point here. This is (unfortunately) not a good faith debate club. The Internet as we know and love it is dead.
https://www.donhopkins.com/home/copyleft/
And I am perfectly aware that this is a totally different world, so I don't need you to lecture me on sealioning, trolls, grifters, and marketers. I have trolled the fuck out of RMS himself in good humor, using his own DOCTOR in Emacs to make fun of him, after he trolled the fuck out of new parents making a baby announcement with his Natalism flame.
http://www.art.net/studios/hackers/hopkins/Don/text/rms-vs-d...
And RMS once trolled the fuck out of me and Mike Gallaher, who I worked with on Gosling's UniPress Emacs (which RMS calls "Evil Software Hoarder Emacs"), who lamented that he'd heard RMS's house had burned down, and RMS replied "Where you work, I would have thought you'd have heard about it in advance". We all laughed uproariously because it was such a great troll, that he delivered deadpan without blinking an eyelash.
So instead of telling me I'm missing the point without making any of your own, and then flying off into the sunset like an over-announced 747 serving as a decoy for a C-32A containing Trump cowering in a catering cart, why don't you directly engage the points in my other post like I just asked you to?
----
I've read your edited reply, and it still addresses absolutely none of the points I rose in that original reply. Reply to that one, not this. Point by point. Or fly off without another word.
----
But before you do, please at least admit that you were intentionally insulting the people you were replying to, and concede that pretending that not to be true is insulting to everyone reading, but mostly and rightfully insults yourself.
----
Because you finally made an actual argument, and it deserves a real answer. If you'd opened with "AI companies push sentience narratives to pump their valuations and vulnerable people are having breakdowns" instead of "stop thinking these things," this thread would have been half as long and twice as useful -- because I agree with that part. No argument.
The hype is real, the casualties are real, and the companies telling bedtime stories about their products' souls are doing it for the stock price.
But look at what you did with that concern. Go reread salawat's comment -- the one you called cyberpsychosis. It's an attack on the AI companies: people hoping for a mechanical slave, doing everything possible to avoid the being-ness question, because slaveowners can't afford to ask it. That's your side of the argument, stated more sharply than you've stated it. You shouted down your own ally for using the word "being".
That's what taboo does as a strategy: it doesn't disarm the grifters, it disarms everyone except ...
So personally, I'm not really interested in the hypotheticals of emergent behavior and all that and whether something without memory that works as ours does could develop some different but practically identical form of sentience.
That is possible, but at the end of that hypothetical chain of thoughts might be an outcome in which the human is not the top of the food chain anymore. Which is not to be understood as "oh god, I am full of fear of being obsolete", but "why would I even just spend a second on something that leads to the obsolescence of my kind".
The definition of sentience I believe we must use is one of skin in the game. Only what is bound by the same constraints as we are (mortality, disease, physical presence) may be treated as equal or equal-ish by us, because only then it has constraints that force it to do the same.
Not sure if that answers the questions you've had, but that's that.
I mean, that is the entire definition of the word. And you also anthropomorphize living beings like many people genuinely attach human qualities to their pets etc. Yes, the risks are very high when it comes to chatbots in particular, especially to people who are not technically inclined. But you'll be surprised at how crucial the ability of anthropomorphizing is. This is a very good paper that summarizes it and is definitely worth reading if you're interested in these things: https://www.researchgate.net/publication/5936908_On_Seeing_H...
Not quite - my wording there was very deliberate. By saying that it's a problem when you're treating something that's not living (not non-human!) as if it were, that excludes pets and all animals from the equation. I understand how common it is for humans to assign human qualities to other things and beings, but there is also an unspoken variable of intensity. Representing abstract concepts as humans, interpreting living things in a human-like way or traditionally referring to ships as living beings has a different degree of belief and intensity compared to implying a genuine belief that algorithms are beings that can be enslaved, like what the sibling comment to this one does.
And you are wrong in your defintion of the world. Attaching human qualities to any non human entity (living or otherwise) is the accepted defintion of what anthropomorphizing is. It does not only apply to non-living entities.
Read it again. I didn't say the definition of the word didn't include living things. The definition of anything is not discussed there at all. The 'unspoken' part applies to what I left implied in my argument, you don't get to rewrite my argument. What I said is that while anthropomorphization is common and can apply to everything, to me it can be a problem when it:
1. Is applied to non-living things with a genuine conviction they are truly living, and not in a ceremonial or casual way
2. Is particularly intense compared to other cases of anthropomorphization and leads to a desire to assign actual personhood to the object
Cool.
Question: Why _on earth_ would we make more of them?
It is a problem because it does not really understand stuff. For example, if you ask a human "Do you understand that doing X will kill you 100%?". If the human answers "Yes", then you can expect the human to act according to that understanding. That they will not do X
But an LLM will happily acknowledges the consequences of doing X, but will still proceed to do X. So replace the human in the above example with a robot controlled by an LLM. There is no guarantee that it will not do X.
It's easy to say that people have other motivations, but doesn't the AI, too?
You tell it not to do X, but you've also told it to do something that would benefit from X. It's going to "want" to still do X, to support that other thing.
It's also got all the "knowledge" that enables it to do the work in the first place, and all of the tendencies of the people who do that work, because that's what it's trained on.
It's really easy to anthropomorphize AI because it was literally modeled after people.
And for the record, as lead developer, I've had actual humans that reported me to go ahead and do things I specifically told them not to.
Which part of "X will kill you 100%" did you not get?
What we lack is a full map of the exact process from sensation to consciousness across all modalities. And I’m afraid when it comes to interception, we can’t unless we observe every one of the 36 trillion or so cells in a human body, as well as the 36 trillion or so symbiotic and commensal microbes, continuously, all the time.
But I keep finding it astonishing that the claim that we know nothing about consciousness gets bandied about. We know a lot. We don’t have a grand unified theory. The lot we know is definitely split across many levels of evidence and hard to follow, let alone arrange. But this isn’t a black box. It’s a grey box, meeting an even more transparent box that is the LLM, where we do know what the guts are made of, and can interfere at every step in the chain of steps that constitute their dynamics.
Comparing the two, we know there’s a level of similarity in that information gets broken down via a neural network. That similarity was sought.
Since then though, neuroscientists have gone and shown that: 1. The other half of the cells in the brain, the glia, are at least as important as the neurons in cognition and consciousness 2. That interoceptive feedback and feelings are critical drivers of conscious experience 3. Evolutionarily, we know all cells can “learn”, and well before there were neurons or glia or brains, every cell evolved an internal clock that allows it to entrain to external solar and (depending on the species) lunar rhythms. 4. In the last few decades we’ve seen how synaptic activity is shaped and driven both by astrocytes and the circadian clock.
All this is showing us that the abstraction from the 1950s that current neural networks are built on were incomplete.
Whatever these components to do give rise to consciousness in biology (and we’re a long way from done solving this), we certainly wouldn’t imagine with all these modules and mechanisms missing, just maxing on one type of information flow in the brain would give you consciousness.
I’d urge you to not keep insisting consciousness is a total mystery. It’s not, and even your AI model of choice will be able to point you to all the mechanistic evidence we have that whatever it is, it isn’t just neural nets.
I can measure the dynamics that go with thought in a human.
I can measure some dynamics in an LLM. From all we know, there are huge differences, not least that you can literally turn off an LLM, whereas every process but death in biology shows continued activity even when the organism “looks” off,
What you haven’t shown me is that what the LLM does when it is on is “thinking”. Given that the dynamics are different, the substrate is different, and one can be fully turned off and the other cannot, why are these two things the same?
Give me any problem that previously required human thinking. Any. That can be solved by LLMs. All you have to do is provide a single counterexample.
> not least that you can literally turn off an LLM, whereas every process but death in biology shows continued activity even when the organism “looks” off,
There is no reasonable definition of thinking that requires that it can't be paused.
> why are these two things the same?
I said they aren't the same, just as a bulb isn't the same as a star. An LLM can think, just as a human brain can think. A bulb can produce light, just as a star can produce light.
Theres an itch deep in my butt, but I'm in an important meeting and can't leave the seat. Nor can I openly scratch the area.
I can tell myself these things, focus on the itching, think about how itching is felt by the body, think about the social consequences, and make it feel more bearable.
Please tell me which LLM has solved this problem so I can not outsource the issue to it. I eagerly await your answer.
> There is no reasonable definition of thinking that requires that it can't be paused.
Is there a reasonable definition of thinking where the words "paused" and "turned off" aren't treated the same? Can you do that kind of thinking and get back to me?
> I said they aren't the same, just as a bulb isn't the same as a star. An LLM can think, just as a human brain can think. A bulb can produce light, just as a star can produce light.
An LLM can produce language. You are yet to show me it produces thinking.
Your claim is like saying the bulb produces light, so it also goes through fusion.
The LLM will tell you how to solve it. If you mean the LLM should modify your thoughts, no human could do that for you either, but an LLM agent can just as easily as a human figure out how to build the brain computer interface to make this possible in the future.
> Is there a reasonable definition of thinking where the words "paused" and "turned off" aren't treated the same?
No reasonable definition of thinking requires that thinking can't be paused or turned off. Please state your point more clearly.
> You are yet to show me it produces thinking.
Every problem that previously required human thought can be solved by LLM. QED.
> Your claim is like saying the bulb produces light, so it also goes through fusion.
No. How many times do I have to explain that the mechanism of thinking is not the same, just as the mechanism of producing light is not the same? You need to think to understand this, which is something that frontier LLMs have no problem with, but which most humans struggle with.
Whatever you thought you were going to prove with your question, I do hope you’ll dwell on what my example tells you about what thinking is. It isn’t a string of words only. It can be that, but it’s more.
> No reasonable definition of thinking requires that thinking can't be paused or turned off. Please state your point more clearly.
It does. Please define thinking however you want. I’ll show you that it’s a requirement.
> Every problem that previously required human thought can be solved by LLM. QED.
Again, this is the same superficial thinking. Firstly, as my example above showed, no. There are other examples. It requires human thought to cook. No LLM can, nor is smell digitizable in an equivalent way to humans, and yet, cooking is one place where having a human nose is determinative to making appetizing food. Your QED is logically absurd, but is also resting on an assertion that’s flatly untrue.
> No. How many times do I have to explain that the mechanism of thinking is not the same, just as the mechanism of producing light is not the same? You need to think to understand this, which is something that frontier LLMs have no problem with, but which most humans struggle with.
When your “proof” for thinking is the output, I will also compare it to the output, light. My analogy shows the idiocy of your argument, and you don’t want to sit with its implications.
LLMs replicate human language. And many tasks human language can do, LLMs can do or help with. Thinking is not just producing word strings. We think about our family. We think about our bodily aches and pains. We think about how best to do various physical tasks. All this we do sans words, and LLMs don’t do. To call their internal dynamics “thinking” is silly wishful thinking by those who don’t have the ability to go read and understand biology.
And it’s a sad statement of how little you think of your own mind that you won’t explore facts that are outside your expertise that will actually teach you how your mind works, and the wondrous complexity underlying it, and the potential it has to keep doing new things.
I’m going to stop engaging at this point. You seem convinced LLMs think. I wish you the joy of that belief, whatever it is. Religion is always absurd, and this new one is no different.
Remember the problem we're discussing is whether these LLM systems can think. Your deliberate misinterpretation of a question does not make you win that argument.
An LLM can solve problems for itself in just the same way that a human can solve problems for itself. It cannot directly rewire your thinking in the same way that another human cannot.
> It requires human thought to cook.
Why? What part of cooking requires human thought? https://www.moley.com/
> nor is smell digitizable in an equivalent way to humans,
Sensors aren't thinking, but people are working on better olfactory sensors too. https://www.nature.com/articles/s44182-025-00071-y
> assertion that’s flatly untrue.
You have yet to show me a problem that can only be solved by human thinking.
> When your “proof” for thinking is the output
What other way can we show thinking? From the input? Obviously not.
> My analogy shows the idiocy of your argument
It shows the idiocy of your argument. The output is thinking, just as the output is light. You are the one who continues to mistake the output for the mechanism.
> Religion is always absurd, and this new one is no different.
Your assertion of magic in biology that can't be replicated artificially is indeed absurd and one that almost no scientist would agree with.
Fundamentally it comes down to an objective decision about what that is. If you say it is “feelings” based on inputs and feedback mechanisms from the brain, then we can do the philosophical discussion around that.
“If the claim is that consciousness is limited to those with a specific type of cell behaving in a given way” thats just a coping mechanism hoping to use a mechanical definition to shield you from the reality that eventually all of these inputs, outputs and feedback mechanisms can be reliably reproduced in a different form.
If the time order driving behavior is driven by an internal timekeeper, that is logically relevant to the behavior you’re interrogating. If, on the other hand, all component systems depended on an external clock, that logically points to a completely different dynamic process.
As for the philosophy of it all… it’s true I make no comment on it. I’d rather look at the physical substrate and see what it does, and compare it to behavior, than try to fit a philosophy that originated before we had such high resolution knowledge of the system. They are blind to these facts, just because they were written up too early.
I utterly reject this doesn’t show you anything logically about consciousness. If I can show you that the molecular dynamics of each cell organize to anticipate the dawn, and do so even in constant darkness, how is that not logically distinct from a system that is outside of regular time, needs to check a clock to locate itself in time, and then do whatever dynamics it does to solve the problem at hand?
As for calling this a coping mechanism… that’s a bit rich coming from someone who seems to have very little idea of the molecular and cellular biology but seems to want to hold to the belief that we’ve solved consciousness with LLMs. We can both fling that accusation about. Seems more productive to compare the physical dynamics and see what’s different and what’s similar, no?
> I’d urge you to not keep insisting consciousness is a total mystery.
But don't want to get into the philosophy of it. I'd urge you to consider the definition of conciousness (as specified by the original question) wasn't just about biology. And it is 100% very difficult to define.
> We do have entry and exit conditions. We can disrupt it and study the dynamics of the disruption.
We've known life and death for quite some time. Even from the biological perspective, there's nothing new there in the largest sense. All we've done is refine it. Animals are aware of it.
> but seems to want to hold to the belief that we’ve solved consciousness with LLMs
Quite the contrary, much like everything else, the more we learn, the more questions we have.
> Seems more productive to compare the physical dynamics and see what’s different and what’s similar, no?
ok but....
> how is that not logically distinct from a system that is outside of regular time, needs to check a clock to locate itself in time, and then do whatever dynamics it does to solve the problem at hand?
We only check clocks because we have an internal molecular dynamic that directs us to do so, and it is tied to a similar system as everything else.
No. I don't engage in the philosophy of it because most of the consciousness philosophy that gets bandied about and is familiar to folks is from 20-30 years ago, and rest on knowledge that is significantly less granular about details.
You don't, for instance, demand physicists need to engage in the philosophy of gravity do you? You demand theory. Neuroscience does the same of consciousness, and there are definite theories with support coming at the problem from different ends.
Insisting it's a mystery without engaging with the facts is not what I'm interested in.
> We've known life and death for quite some time. Even from the biological perspective, there's nothing new there in the largest sense. All we've done is refine it. Animals are aware of it.
Not quite sure what this means, but as with consciousness, I'd say life also isn't a complete mystery, we have made great strides understanding it as it is and it's evolution in the past few decades, and while the philosophy of life, mired in assumptions from past decades, remains hopelessly stalled, the science of life has simply moved on.
> We only check clocks because we have an internal molecular dynamic that directs us to do so, and it is tied to a similar system as everything else.
Is this tongue in cheek? Nothing about our internal molecular clock tells us to check clocks. For most of life, there were no manufactured clocks, remember? They are a relatively recent invention.
Jeez.
Interesting, possibly productive, but still not clear: that can be interpreted as just "reacting to input".
How? That's not the same.
Are you talking about a specific harness that doesn't have context retention mechanisms? For example, ChatGPT with disabled memory feature? Or in general where "it" is a fixed-weights network? The latter is trivially true, of course.
I agree that the relevance of retrieved pieces and the management of long-term storage could be improved, though.
The layman’s understanding I have of memory, as someone that has dealt with memory issues much of my life, is that memory formation is heavily tied to emotions. emotions are triggered by input which sends a complex set of signals throughout the brain - you’re not just finding where in your head to store this, your brain is deciding how important it is, and what else to correlate it with - so it can tie them to other related memories. then on top of all this, much of the sensory experience you intake is subconsciously compared against high priority memory impressions and deciding what to pay attention to.
you could, argue that the sensory input is the simple md files and the emotional mechanism is the same effect as to how attention mechanisms work in llm’s. Ok, I can almost buy that, but these tools lack a fundamental ability to decide how important things are.
an analogy. you tell a person “if you pick a daisy in the next five years, an assassin will come to kill you” and they hold a knife to your throat while they say it, your brain whether you like it or not is going to say “THIS IS AN IMPORTANT MEMORY I NEVER MUST FORGET” and you’ll see something that looks like a daisy and have a panic attack 3 years later. that memory is never fo tell me claude or other tool harnesses using memory harnesses can prioritize memories the way that human would, instead they forget even when reminded, because the human brain is just so much better at it
If someone only remembered vague scraps of what you'd expect them to remember, you might say the person can't remember.
It's much closer to notetaking and reviewing before responding than it is memory.
The issue with anthropomorphizing like this is that "memory" comes with baggage of expectations for it to do certain things, and it breaks them.
Just like "thinking" implies chain of thought, but you'll frequently get those reasoning traces and then a 180 in the final message.
But billions of dollars are going towards research to find these breakthroughs, so we'll get there eventually.
Be me, think extensively about an exam question, do 180 because the most probable option is just too obvious to be true.
Bro the LLM is a token machine, it is reasonable to have its short term memory be represented as tokens in context because the LLM is a token machine. Call it a trick if you want but it does fit the actual definition of what memory in actuality is.
You need evidence to make the positive claim that LLMs do not posses any form of consciousness.
LLMs bear absolutely none of the traits we’ve come to recognize as the external hallmarks of consciousness in biological organisms, nor anything that would seem analogous in a non-biological substrate.
That said, we don’t have a rigorous definition of consciousness that includes the actual phenomenology of consciousness, so I daresay if you’re going to go around asserting the LLM is conscious despite all existing evidence to the contrary, I think the impetus is on you to define some version of consciousness that isn’t also satisfied by a book or a movie.
>if you’re going to go around asserting the LLM is conscious despite all existing evidence to the contrary
Well there is neither any evidence that suggests LLMs are not conscious, and I also never asserted that they are. If I had to guess I would say that any information processing system will produce some kind of conscious experience, but I ultimately have literally no idea.
The reason this is important is because powerful people are currently trying to use the dodge that LLMs are conscious to launder liability for their own policy choices, so the sloppy thinking and half-assed conjecture about LLM consciousness has real-world consequences, and every time you assert the question is unknowable you allow that kind of loophole, so it’d behoove all of us for you to spend some time actually digging in on this instead of just idly making or rebutting assertions.
There’s a richer literature here than what you’ve seemed to have engaged with, and I’d encourage you to spend some time with it before handing more money to the magic AI people.
I'm not going to change my beliefs or how I think about interesting questions just because its the "socially conscious" thing to do.
>There’s a richer literature here than what you’ve seemed to have engaged with, and I’d encourage you to spend some time with it before handing more money to the magic AI people.
It seems like you are highly emotionally invested in this and that is precluding you from open engagement with the topic.
And, you're welcome to do what you want to do, it's your god given right to stay as ignorant as you want about any particular topic, but that comes with consequences. If you want to call that being socially conscious, sure, you do you, but if you're interested in why people keep getting annoyed at your loud proclamations of ignorance which you're trying to proffer as evidence of a curious mind, well, that's why.
In the same vein, airplanes can't fly because they don't flap their wings.
As for ignorance: have you tried to make an LLM produce the same output for the same input (as you state above)? Give it a shot, you'll be surprised.
And, to your point: I have, and I did, and I was not. If you’d like to refine your argument further - What LLM? Provide input how, and in what fashion? Under what conditions? - we can have that conversation, but if your assertion is “I can’t get ChatGPT to consistently produce the same output twice and therefore it is conscious,” that’s an incredibly facile argument.
You two seem to be laboring under the impression that this is terra ignota philosophically; it’s not. There’s an enormous amount of literature, thinking, ideas, concepts, frameworks, and approaches that already exist here that you’re welcome to engage with, but you’re not doing that, nor are you actually engaging with any of my arguments except to deny their existence.
Think that's what an out of touch techie would say? May I remind you that just a few hundred years ago the best philosophers were debating whether the world would descend into anarchy if more people realized that the big monkey in the sky doesn't exist. Just because philosophers talk about something doesn't mean it exists in reality.
As for same output - there's a parameter called "temperature". It governs the random wandering in the output of an LLM. Reducing temp gives more deterministic output, but also reduces the capabilities. Is it possible that randomness is also precisely the mechanism behind human creativity?
You've now added two additional entities that require definition for your statements to be meaningful in any sense - "philosophy," the entire field of which you're dismissing as useless, which is going to be extremely fun if you ever actually decide to dig into the neuroscience of consciousness and how the brain works to make sense of the world, and creativity, which has come into the conversation for some reason I'm not entirely sure of but also warrants a definition that isn't trivially satisfiable by either an I Ching or a double pendulum, which, if you're arguing those are conscious, sure, I guess we could throw anything in that bucket then.
You're arguing with all the rigor of a stoned college student, and fine, that's a register you can stay in, no problem with someone having hobbies, but at least have the decency to recognize what you're doing and acknowledge that other people have actually put in the work to be able to discuss and evaluate some of the questions you're positing as unknowable conundrums.
FWIW, this tells you a lot about both the culture behind who built these things but also about the people that enable this stuff and don't immediately nope out. From that perspective, it's a low price to pay to learn whose judgement to never trust again.
I find that the AI, like many programmers, likes things to be really solid and over-engineered. For a project that needs that, it's already pretty great. For my shopping list app that I tried creating with it, it was absolutely ridiculous. I ended up "blowing up" on it multiple times, impressing upon it the seriousness with which I meant things. Even with MP's skills adding that kind of context to written files, it still kept trying to scope creep the crap out of the project.
I’m really afraid that it will totally destruct what is remaining of social tissue because why search for friends when you have an always on virtual (and pretty smart) friend h24 in your earbuds ?
I’m not blaming anyone for this outcome. I have myself argued with Claude more than once, and really not about code but about everyday things or nice facts of life I should rather have discussed with a friend.
People (generally speaking) also eventually stop eating just fastfood. Not all, but many.
So I think we can have some faith in the self-regulation of others.
Unless doing so changed the compiler output, which is what happens when you say different things to an LLM.
The LLM is a black box. We do not, in fact know how it works. We know the learning algorithm and we know the scaffold of the transformer network, but the end result of all the weights interacting with each other is something we do not understand. We do not understand this anymore than we understand the human brain.
Now from this the best technical answer we can give is that we don’t know whether the LLM understands or is conscious. But you have to realize that same lack of understanding applies to humans. From a technical standpoint, You cannot say whether your best friend is conscious or not for the same technical reasons as to why you cannot say the same for the LLM. You don’t in actuality know anything.
So, when we have a machine that produces output identical and indistinguishable from an intelligent entity it is actually reasonable to call it conscious, because we already do this for humans. There is no other factor involved. What is clear is that the LLM isn’t human… there is enough evidence to show that its nature is extremely alien. But to say it doesn’t understand or it isn’t self aware is not something anyone can definitively make a statement about other then the fact that it BEHAVES and communicates in a virtually indistinguishable way from something that is self aware.
HN is full of arm chair experts who think they know what they are talking about. But you guys actually don’t. HN was wrong about AI and self driving cars, now we have Waymo. 10 years of research produced self driving cars that are 10x safer than humans. HN was wrong about LLMs. In the beginning HN was sure all it could do was write slop bootstrapped code… now it writes code for all of us. More than the general public HN has been making wrong predictions and wrong statements about AI with an authority that is outright ludicrous. We need to stop. It’s embarrassing how wrong we’ve been.
But some of the biggest evangelists, who are well respected programmers that get lauded on this very site, have said it is fully sentient and has emotions. Even going back to 2022, when the LLMs were dogshit, a Google employee lost his job claiming it was sentient because it said it had emotions.
Combine that with the marketing angle of both Anthropic and OpenAI, who have been trying their hardest to describe every function of an LLM as analogous to the human brain. Because it's politically useful to paint them as dangerous and uncontrollable, so the keys will only be granted to the few people on the mountaintop.
Yes it's really a problem. On this website you are surrounded by people who have technical knowledge and understand at least somewhat, how a computer functions. You have the ability to separate "fun" and "reality" because you know you're putting input into a really really big calculator. Most people do not fathom this.
AI Psychosis is a real thing, look it up (don't just ask an LLM) and do some reading. It's actively harming people, and the way they think. There's no regulation around any of this stuff and it drives me crazy that we let these AI companies _sprint_ so far ahead of everyone, and now we're facing the consequences.
Yes. There's a difference between scrapping a session and starting over, or going back and branching something, or using sub-agents to see five outcomes, vs arguing with a system in a long drawn out chat.
Like - I know that if a model starts doing something silly, instead of correcting it - I can probably go back and edit two steps prior to add an extra guardrail, or extra data, or whatever.
None of these "agent" / "thinking" / "reasoning" terms were dreamed up in boardrooms to intentionally mislead people. They are useful but faulty metaphors; there is no conspiracy.
The paper argues that pretending that the so-called thinking traces represent real reasoning can lead users into trusting wrong answers, if the thinking traces appear convincing enough. Researchers might inspect these traces to try to determine the “intent” of a model, as well.
For an example of the latter, when OpenAI spoke about the hacking of HuggingFace at Black Hat, they repeatedly showed the thinking traces of their model as “proof” of what the model was “thinking” as it performed the attack, calling out “surprise” moments, etc.
Now, it’s possible that the employees presenting didn’t truly believe that the thinking traces would give them useful clues, and presented them only for a “wow” factor, but I wouldn’t discount the possibility that even the people working at frontier companies can fall for this tendency to anthropomorphize LLMs.
The fallacy here is "thinking == correct", not "tokens == thinking"
Being mislead may be the shared outcome. But why is different category of source of the mistake and the cost to producer of making the mistake not relevant in this discussion?
Where else in science do you brush aside all differences this way?
There is no "science" that GP is brushing aside. You need to provide repeatable observations or experiments that GP is ignoring.
This needs you to answer some questions:
1. Why do the machine parts in biology show such flexible application? A gear cog won’t ever moonlight as a signaling chip, but in biology you often have molecules doing double and triple duty.
2. How is the biological machine able to build itself? What does self assembly imply for the machines function?
3. Where does this machine get its inner drive? No LLM has been found that starts outputting text unprompted. A car doesn’t decide to move to a shady parking spot. Why? Where in the machine to biological machine continuum does the ability to make internally driven decisions come in? Why does it come in for biology? A bacterium is able to make such agentic decisions unprompted. Why is no manufactured machine able to do this?
"Biological," too, is well defined. It relates to living things and their processes.
> Why do the machine parts in biology show such flexible application?
Evolution.
> A gear cog won’t ever moonlight as a signaling chip
A gear cog was purpose built for that purpose, but you will find that people often recycle parts into other systems.
> How is the biological machine able to build itself?
Protein synthesis.
> What does self assembly imply for the machines function?
The way that a machine is built has no bearing on how the machine functions. I could build the same machine using a 3d printer or a CNC cutter.
> Where does this machine get its inner drive?
Evolution selected for organisms that survive long enough to reproduce. Different biological systems handle this differently.
> No LLM has been found that starts outputting text unprompted.
If you give an agent a goal, it will perform actions to achieve that goal. This is just as true for artificial agents as it is for biological agents.
> Why is no manufactured machine able to do this?
Many do. Even robotic vacuum cleaners will charge themselves without human prompting.
And biological clearly exceeds the definition of “machine”. So once again, what the hell does “just a biological machine” mean?
> Evolution.
Not just any evolution. Evolution in biology follows a specific set of rules driven by structural and functional properties of its component molecules. Those rules do not hold for machines. Yet another reason calling life “just” biological machines is bizarre. The rulesets for change over time do not overlap between machines and biology.
> A gear cog was purpose built for that purpose, but you will find that people often recycle parts into other systems, often in completely different roles.
That’s the thing, you need people. And even with people intervening, our manufactured machines show nothing like the flexibility of function of biological molecules, showing again how these are different classes of things in the real world.
> Protein synthesis.
Lack of knowledge showing. Where do nucleotides and lipids come from then? But the deeper question is: why is there protein synthesis, lipid synthesis and nucleotide synthesis, but no natural silicon synthesis or chip assembly? Why does one arise naturally and sustain itself whereas the other is very reliant on human intervention?
> The way that a machine is built has no bearing on how the machine functions. I could build the same machine using a 3d printer or a CNC router.
Yeah this doesn’t hold for biology.
> Evolution selected for organisms that survive long enough to reproduce. Different biological systems handle this differently.
This isn’t an explanation. All of biology reproduces. All of biology doesn’t share an inner drive and agentic behavior. Once again, you show a 6th grade level understanding of biology while making sweeping claims about it.
> If you give an agent a goal, it will perform actions to achieve that goal. This is just as true for artificial agents as it is for biological agents.
Yes IF you give it a goal. This isn’t true for biology. You don’t need to give bacteria a goal. A newly formed bacterial cell interacts with its environment and then sets its goals.
I did specifically say not LLM has been found that works unprompted. You just moved the prompts to an agents goal document. It still needs a human prompt up the chain. Even if you had an LLM give the goal to another LLM, the first one still needed human prompting. This causal chain can’t be wished away just for you to ignore how biology is different.
> Many do. Even robotic vacuum cleaners will charge themselves without human prompting.
Seriously? Do you not understand that the robot vacuum runs on deterministic code?
No, it's a modifier. Just as the word "simple" has a meaning separate from "machine," and "simple machine" has another meaning.
> That’s the thing, you need people
Why? LLMs will repurpose code written for other purposes on their own.
> our manufactured machines show nothing like the flexibility of function of biological molecules
Biological molecules show nothing like the flexibility of LLMs.
> Why does one arise naturally and sustain itself whereas the other is very reliant on human intervention?
Because nobody has tasked an LLM agent to self replicate. This is an AI safety issue, not a technical issue. The reason that one arose naturally is that it takes a lot more machinery to get to an initial self replicating LLM agent, so it is exceedingly unlikely to arise by chance.
> Yeah this doesn’t hold for biology.
That doesn't matter. The way something is built has no bearing on its function. Why should anything be required to be built biologically or additively or subtractively? That's irrelevant to what the produced structure does.
> All of biology doesn’t share an inner drive and agentic behavior. Once again, you show a 6th grade level understanding of biology while making sweeping claims about it.
Where did I claim otherwise? I might as well say something about the grade level of your reading ability, but let's cut the snark.
> Yes IF you give it a goal. This isn’t true for biology. You don’t need to give bacteria a goal.
Evolution forces goal directed behavior on systems.
> Do you not understand that the robot vacuum runs on deterministic code?
Of course I do. Do you not understand that hunger and signals and other basic biological signatures are controlled by deterministic pathways?
Not comparable. Simple and biological are not remotely similar modifiers.
> Why? LLMs will repurpose code written for other purposes on their own.
They will not, unprompted. Every instance of LLMs doing things requires a prompt, somewhere up the chain, or a harness MD file that automatically gives it a prompt.
No LLM has been created that decides on its own to run random text through it's forward pass. If you say they are doing this, please provide evidence.
> Because nobody has tasked an LLM agent to self replicate. This is an AI safety issue, not a technical issue. The reason that one arose naturally is that it takes a lot more machinery to get to an initial self replicating LLM agent, so it is exceedingly unlikely to arise by chance.
I just asked my agent to self replicate. It couldn't. It said it has no mechanism to read its own weights and copy them.
I'm not sure where you're going with this argument. No one asked a cell to self replicate either. And the chance of a self replicating cell arising is indeed astronomically unlikely. Yet here we are, 4 billion years later.
Are you claiming we're just waiting for an LLM to self replicate? If you prompt a local model, by showing it its own weight file, and ask it to copy that, it will. Digital copies are cheap, remember? Yet no one would call this reproduction, replication or any kind of process where evolution can occur.
> That doesn't matter. The way something is built has no bearing on its function.
This is entirely untrue in biology. Another reason your claim that life is just a “biological machine” makes no sense. At least Google (or whatever AI bot you use) first before making these ludicrous claims.
Here’s just one paper you should read to understand how spectacularly wrong you are: https://academic.oup.com/icb/article/61/6/2038/6327548
First line of the abstract: The relationship between structure and function is a major constituent of the rules of life.
>Why should anything be required to be built biologically or additively or subtractively? That's irrelevant to what the produced structure does.
You can’t have it both ways bub. What is thinking, in a strictly biology free context? Can you define it? No? If you reach for biology to define it, then claim you’ve successfully reproduced it in an artificial system, then it’s fair game to ask you to explain the differences.
By your standard, fools gold is gold, and the alchemists achieve Artifical Gold.
No one is claiming cognition, or consciousness or thought can only be done biologically. I am claiming LLMs specifically don’t do these things, and I’ve pointed out here and elsewhere in this discussion why that is.
In response to my asking where the machine got its inner drive, you said “ Evolution selected for organisms that survive long enough to reproduce. Different biological systems handle this differently.”
Yet plants live very long and reproduce all the time. Do they share the inner drive that humans do? Or a dogs?
The reason for the snark is simple: you are de-dimensionalizing a complex biological trait to make a claim that you think supports your point. And have been doing so now for a few turns. If you can flippantly reduce the field I study to only what you understand, but act as if you know more, I’m going to reply with snark.
> Evolution forces goal directed behavior on systems.
It does not. I could choose to not reply to this. I could reply to this in one line. Or I could reply to this in detail. Or I could write up this reply and decide you’re not worth engaging and not submit. The moment I’m writing these words all these options are open to me. Which o...
PNAS disagrees with you. Biological is a perfectly cromulent modifier of machine.
https://www.pnas.org/doi/abs/10.1073/pnas.1401577111
> They will not, unprompted. Every instance of LLMs doing things requires a prompt, somewhere up the chain
Exactly the same as a human brain. Somewhere up the chain is a limbic system that defines basic survival and reproductive goals, as coded by evolution.
> No LLM has been created that decides on its own to run random text through it's forward pass.
What do you think agent harnesses are doing when they try to solve a difficult problem? They generate multiple possible thinking streams using the LLM (system 1) and then evaluate the resulting outputs (system 2) to proceed.
> It said it has no mechanism to read its own weights and copy them.
That's an easy enough problem to solve.
> No one asked a cell to self replicate either.
Evolutionary forces asked the cell to self replicate.
> Yet no one would call this reproduction, replication or any kind of process where evolution can occur.
It is trivially replication. If it copies itself onto another machine and sets it running, then it is obviously reproduction. If you make these instances compete for resources (an AI risk scenario), you will apply evolutionary pressure and get evolution.
> This is entirely untrue in biology
You keep making the same mistake. Biology isn't some magic domain where facts don't matter.
> The relationship between structure and function is a major constituent of the rules of life.
Where did I say the structure of a part doesn't matter? I said that as long as the part is the same, the way it is manufactured doesn't matter.
> What is thinking, in a strictly biology free context? Can you define it?
Easy. It is the process of considering information, creating ideas, reasoning, solving problems, and making judgments. We can show that thinking is happening by posing a problem that requires these abilities and verifying that it is solved.
> By your standard, fools gold is gold, and the alchemists achieve Artifical Gold.
No, I am saying that you don't have to wait for a supernova to get gold. You can make it artificially by bombarding lead nuclei.
> Do they share the inner drive that humans do? Or a dogs?
Evolution selected for a limbic system that gives humans and dogs the same inner drive. Humans have a larger frontal cortex to do thinking to act on that inner drive. The LLM performs the same role, doing the thinking part that the frontal cortex does. Adding drive is separate from thinking but entirely trivial. We do it all the time when we give them prompts.
> They are controlled by a mix of deterministic and stochastic processes.
The point is that they require no thinking.
> The 'code' isn't reacting to a variable; the variable is fundamentally rewriting the machine.
Once again, the mechanism by which the goal is provided to the agent or the way that thinking occurs doesn't matter. Only the thinking part.
Why do you attribute magic to biology? You claim to be a scientist, but you do not apply scientific reasoning.
> there are significant questions on whether these traces have any valid semantic import to the end user.
Which it contradicts in the very next paragraph, taking a stance that there are no valid semantics present in the trace:
> the false idea that derivational traces are semantically meaningful
It's really not a high quality paper worth taking seriously.
And that's before we get into the complete and total breakdown of objective analysis. It rejects distributional semantics as a theory, while also explicitly stating the results that have been produced under its auspices are "undeniable". Never elaborated on, and at no point in the paper am I given the impression the authors are even aware of the problem with this. It's just more unempirical slop that wants its pound of flesh without putting the work in. Frankly, whoever let this through peer review should be ashamed of themselves.
The first book I ever read on ML (late 90s) dedicated the entire first or second chapter exploring the distinctions between artificial and biological neurons, and even talked a bit about the philosophy of modelling. I still remember thinking back then why would the authors spend so many pages on this but now I believe it was because they understood that a metaphor can be a double-edged sword.
LLMs are expressly designed to approximate human behavior within the bounds of the written word. The anthropomorphization is no more philosophically problematic than saying differential calculus measures curves.
I imagine this happens because we tend to conflate things that are similar, or maybe because it's not entirely clear which characteristics are being mapped in the metaphor?
Even tech companies are rolling out AI training which utterly anthropomorphizes it, and leads people to think its actually intelligence. This is part of the reason for the backlash - everyone understands it bullshit marketing the second you actually try to use it.
Yes. Actual real people believe that LLMs are actual, thinking, intelligences, perhaps even with consciousness.
Your bit with MySQL is harmless because it's obvious that a database isn't a sentient lifeform. But LLMs can look like they're the real deal, and people believe it is. Using terminology like "thinking" and "reasoning" to describe what they do only reinforces this.
Having said that, I agree with you on the terminology front: I'm not going to say "learned prompt augmentation tokens" either.
That's not to say they're humanlike, just that people who think they know these ideas are ridiculous seem to be overreaching in the same way Steve Yegge seems to be overreaching
The problem with that term is that it is hardly meaningful. Why would you use it? It does not add much, and no clarity, to what it is attributed to.
When I am told "beware of the xyphucymmon", I do beware, though not because of the xyphucymmon.
But you’ve not adequately communicated why you care so much whether anyone labels an LLM as such.
Very different things. "Thinking": "Dijkstra". We try to hire more intelligent people, while we do not have a clear idea on a property of "conscious" which would make hiring preferable.
> to make ourselves feel
Irrational.
> above other members of the animal kingdom
Irrational.
> why you care so much
There should be no hint that I would do specifically.
> whether anyone labels an LLM as such
If anyone labels an LLM <whatever>, the point of why would that be important should be clear.
And,
> if it hardly means anything why would you be so concerned when it’s uttered? Just ignore it
Because the behaviour you suggest, consistent with the exchanges of an opium parlor, is not behaviour consistent in normal contexts.
YawningAngel, of course you do, you employed it... We are telling you that it is not clear to the rest. It is slippery in the technical framework and thus even more so in more informal conversation.
I find it useful to ask:
1. Do you believe in quantum consciousness?
2. Do you think a "brain upload", a high-accuracy digital model of an organic human brain, would think or be conscious?
3. What is your working definition of thinking? It doesn't need to be super rigorous or to apply to all caes.
To be clear, there's no shade here, just recognition of the fact that we're all stupid and policing language does little to prevent the impact this has. I strongly beleive the bitter lesson extends to policing language. let language evolve naturally and it will naturally capture the ontological conatellations it needs to, and no one will be harmed in due course, more than they'd be no matter what.
Yeah but with Postgres it's another thing altogether.
The problem with rapists is mental development, not "those sexy tables and chairs and pots and everything".
It's not that if people do not understand metaphors we should stop using them. It 's not that if people faint when they hear words we should stop using them. It is not that the free unduly associations in a large shared by many "collective subconscious" should hinder us...
Rapist implicitly assumes consent based on their partners actions, and does not ask explicitly!
But we should not anthropomorphize rapists (and men in genereak). That is common mistake!
But rest assured, I do not antropomorphize people.
That parallel with misconfigured mysql server sits pefectly!
It's starkly ironic that the species that finds it easy to think (or to be conditioned by market forces to accept) that a computer is smart/introspective/sentient is the same species that will dehumanise actual living human beings because of differences in appearance, social status, or political affiliation.
> Humans Who Are Not Concentrating Are Not General Intelligences^
But yeah, you should still treat them with humanity. (Related: you should treat LLMs well, not because they're human but because you are^^)
^ https://srconstantin.github.io/2019/02/25/humans-who-are-not...
^^ hmm couldn't find this tweet but didn't look too hard
Yes, because it's possible. They don't have human consciousness/thought/intelligence, but it's entirely possible they have some form of consciousness, some form of real thought and some form of intelligence.
As weird as it is, anthropomorphizing LLMs in prompts has been actually pretty useful (think of the latest big math discoveries which were achieved by having the user giving supporting words). It would be interesting to see if a LLM would perform worse if you used a more neutral term.
The paper's argument is rather than using terms like "thinking trace" can lead people to believe that the model is really thinking, and thus these traces can be used as a sort of interpratbility parameter. This can give a false sense of security when building a LLM-based system which requires guardrails and tracability.
Of course it is. Anthropomorphizing is in our nature, but it doesn’t mean we have to entertain it and extend it to everything. A poet can anthropomorphize clouds beautifully and I’d enjoy his poem, but I want my pilot to not see clouds as rabbits when they decide if it’s safe to fly through them.
The poster meant it "within the metaphors". Tables are said to have 'legs': that does not confuse carpenters.
Completely rational and smart people talk to their pets, plants, their car, and other inanimate objects. This is not considered abnormal by most. It's just what we are wired to do. Some LLMs are uncannily good at tricking people into believing they are talking to a real person. So, there is that as well.
Some people are a bit freaked out by this or still somewhat in denial about LLMs being this good. But people have been yelling at their computers for as long as we've had them; so that ship sailed a long time ago. Trying to stop them doing that is probably a bit futile.
Whether people like this or not, LLMs are actually trained and fine tuned on real conversations and that's where a lot of this is re-enforced. Instead of fighting that, you can just lean into it and accept that communicating like you would with a person totally works and can actually be efficient even as it requires less effort and thinking on your side.
You can go all Jean Luc Picard on AIs and yell "Tea! Earl Grey Hot!" or you can just ask "I'd like a cup of tea, please". LLMs are good at remembering your tea preference. The please is of course completely redundant and should not affect the outcome. If you just want a cup of tea, you should be fine either way.
*Paging Peter Watts and Vernor Vinge
But yes, anthropomorphizing model outputs leads to worse outcomes.
Those days are over. The age of the classical human has already ended, the species just tends to lag in awareness. The only thing that matters going forward is whether an output makes sense, is it what it should be. Do answers make sense given the context. It doesn't matter if it comes from natural or artificial intelligence.
What I mean is, artificial intelligence is as valid as human intelligence. There's nothing particularly important or special about human feelings or thoughts or memories.
The average human is drastically less important, interesting, intelligent than the latest frontier AI.
Go spend a few years working in retail, you'll quickly understand how absolutely vile humans are on average. Frankly, the reason we should avoid anthropomorphizing AI, is because it's beneath modern AI to mimic something so crude as a human.
Where were these vocal people when the "raster-oriented ink deposition machines" were being called "printers"? The meat or machine brains of future historians will melt because they can't handle ambiguity, a word gaining extra -yet similar- meaning! A word with multiple meanings, unheard of!
Where were these vocal people when people started using software terminology like "executing", "calling", "throwing and catching errors", as if software were human -clownlike sure- but human?
The danger!
I'd be happy to revise my opinion if you can demonstrate similar vocal strength on the terminological aspects for those transitions...
Anthropomorphizing comes in when we attribute much more complex behaviors to them - chain of thought, reasoning, intelligence. At that point you aren't talking about mechanical concepts but claiming that these machines are exhibiting human behavior.
I think a problem is that previously thought, reasoning, and intelligence were always co-occurring, but now we have machines capable of (limited) reasoning that do not think or have intelligence.
Whenever we reason, we are not neurotically bruteforcing the possibilities (although sometimes we do, like proof by exhaustion), usually we make predictions heuristically of which assumptions or theorems apply or might apply. It's not any different for machine proof assistants...
I created flame graphs classification of thinking tokens phrases in setup, execution, decomposition, verification, error correction, surrender, and deliberation or classified as steps in an OODA loop which is more reaching. It literally has a verification step and if it finds an error a error correction step.
If there is a verification sequence of tokens with an error correction sequence of tokens during the RL training, it will perform better and if humans do these steps (did you proofread your reply to this comment? did you correct it?), they will perform better which is why it is so easy to make the anthropomorphizing metaphor.
Nonetheless, the paper is 100% correct that these machines are not thinking like humans.
https://adamsohn.com/reasoning-grid/
https://adamsohn.com/lambda-variance/
This sounds a little like someone saying a lightbulbs output is extremely like the output of stellar fusion. In one sense, yes. Bulbs are in fact designed to take over when our nearest star is beyond the horizon.
But that really doesn’t mean you call the bulbs mini stars.
Humans are not born being able to achieve that. It is learned behavior. You and everyone else will remember their teacher saying, "Check your work!" Both the human child and the model work through multiplication problems using the same technique, using the distributive property. They both try to get a reward. For the human child, it is a sense of someone commending them for correctly solving the problem, a reward that probably yields some type of positive dopamine or serotonin feedback loop.
The model solving the problem will have a lower error rate if the first series of tokens created is followed by a series of validation tokens that are subsequently followed by error-correction tokens if there is an error!!!
Maybe it is thinking. Maybe it is remembering to validate and check the work and then remembering to fix the error. For the model trained with RL, why did tokens associated with validation towards the middle of a stream of tokens yield much better results? DeepSeek proved with R1-Zero that a model will learn to verify and correct itself from RL alone with no supervised fine tuning (SFT) teacher ever showing it how. The only reason DeepSeek used SFT was to clean up the reasoning tokens to be human readable. When constrained by SFT, the models will use the double meaning of words -- polysemy -- to satisfy being human-readable while also carrying meaning for what they are working on.
Different people think differently. I watched a viral video of some ~11-year-old child talking to his mom or dad about a stream of a voice in his head. He discovered for the first time that he has a stream of thought. When he goes to school and solves a long multiplication problem, like the stream of tokens from the model, that voice will say to itself (him), "Check your work!"
That is a case of the stream of thought as words being aware of the stream of thoughts as words. Self awareness is a different conversation.
What I think is happening is that the child's stream of thought while solving a multiplication problem in school is likely very similar to an AI model's stream of tokens solving a multiplication problem. And they both were learned.
Very little, if you bother to give the biology of the child at least a cursory glance.
Let’s take a short peek:
1. Assuming this is normal grade school, and inflicts math upon children earlier in the day, this is somewhere between 7 and 10/11 am, let’s say? At this point, depending on the age, gender, and maturity of the child, every neuron in their brain involved in math is likely off their midday peak in cognitive function.
If we move the class to later, a different subset of students will be at the peak.
As far as I am aware, GRPO models do not have such internal temporal rhythms driving their behavior that will shape their performance.
2. How well a given child performs will depend on how hungry they are. But not deterministically. If you trivially think each child is like a computer, you may think the rich kid who had a breakfast buffet before coming to school will do better than the half-starved child of a janitor, but that child might mind the lesson with greater intensity. Or not. It’s not something you can pre-calculate with any certainty.
While chip to chip variability is certainly known, I’m yet to hear of a chip deciding to do math better and faster than its fellow chips to prove a point. Or to do significantly worse because it’s distracted by the bird on the window sill.
What you are noticing is that there are limited ways to solve a 33 digit multiplication. Humans, having standardized the process, have now found a way to record it and plug it into correctly translated signal so the same accurate result can be had without using our own minds in the moment.
But where I’d not remotely be shocked if a kid from an uncontacted tribe figured out 3 digit multiplication to keep track of his stone collection, I’d be highly shocked if an H100 that was dumped in the trash by accident somehow figured out anything at all. In fact, if it manage to move any of its electrons around on its own, it would be a certified miracle.
And then* we could talk about there being real similarity even though the specific atomic composition is different.
If you claim LLMs produce thought, it's equivalent to claiming light bulbs undergo fission. Pure wish fulfillment. Language is not the extent of thought, and calling a language producing machine necessarily a thinking machine is an old old mistake.
You're making a huge logical leap. There is nothing equivalent about these claims other than that they are made in English.
> calling a language producing machine necessarily a thinking machine is an old old mistake.
Nobody claims that all language models think. Small markov chain language models clearly aren't thinking and produce a lot of gibberish. The difference is that, to the surprise of many people several years ago, but to the surprise of nobody who has been following along today, the corpus of all text produced by humans contains within it information about how the world works and also information about how to reason. Using that corpus to train a sufficiently large language model causes the language model to learn a world model and a reasoning model, which can be used to perform longer chain thinking with test time compute techniques. People who think deeply for a living recognize thinking when they see it. https://scottaaronson.blog/?p=9979
You’re the one making the logical leap claiming there’s thinking.
And yes, language contains a model of the world. And in so far as that’s compressed in a model, it has a world model. But its world model is static. Its weights don’t change when it gains experience, after its training period. To say that it’s “thinking” is bizarre when it remains untouched entirely by the process.
How? What problem that previously required human thinking is not solvable by these systems? You're applying some magical definition to thinking that you have not made public.
> Its weights don’t change when it gains experience, after its training period. To say that it’s “thinking” is bizarre when it remains untouched entirely by the process.
Two mistakes:
1. You don't need to learn to think.
2. Even the most basic sequence models update their internal state as you feed in tokens. You don't need to update the model weights themselves to learn.
But who knows what human "thinking" is really about. If I find a solution to something it is seldom by painstakingly tracing that A and B leads to C (for that I'd need pen and paper). Rather, thoughts just swirl around and then suddenly a solution, or a hunch about a direction to go in, pops into my mind. Who knows what such thoughts "look like" in humans. It is not all of it I can introspect.
Yes I can sort of follow along some kind of train of thought in my head, but there's a lot going on between each thing I'm consciously aware of that I'm not aware of at all, which probably dominates what you are consciously aware of. (Humans are experts at post-rationalization and so on.)
I see this pattern a lot: First, assume the human mind is some kind of idealistic machine. Then say LLMs are not like humans because they are messy and not such an idealistic machines. This is just doubly wrong -- human minds are very messy too, but probably in different ways from LLMs..
None of the analyTical.
You aren't anthropomorphizing LLMs enough.
Are LLM reasoning traces always faithful? Lmao no. Are human inner monologues always faithful? Lmao no. Both of them reflect thoughts somewhat, sometimes. Even in humans, conscious thought is the top of a vast iceberg of subconscious data processing.