Live data from Hacker News

Stop Anthropomorphizing Intermediate Tokens as Reasoning/Thinking Traces (2025)

arxiv.org

281–290 of 296 posts

Re: Stop Anthropomorphizing Intermediate Tokens as Reasoning/Thinking Traces (2025)

#281

Earlier quoted context omitted.

Well this requires you to buy the very bullshit argument that comparisons of two physically distinct systems just because they share outputs is meaningful. If I call a lightbulb an artificial star, the onus is on me to show the behavior under the hood is star like, not just to point at the light and say “you must see it’s a a star since it’s emitting light!”.

> Well this requires you to buy the very bullshit argument Sorry, no. The only thing it requires you to buy is basic logic. If you argue that B is true because of A, the fact that A is false invalidates your argument (I repeat: not B but your argument). There is no question about it.

Maybe if you the argument was that B is only true because of A, and only for that reason. That’s hardly the case when comparing LLMs and humans. The population behavior of humans isn’t the only thing where there’s both overlap and sharp distinction. The underlying mechanism and substrate are also completely different.

To say the same process is occurring with all this different is bizarre, and that is why the OP is right about which direction the argument of similarity has meaning.

You don’t disagree that our only pre-LLM exemplars of conscious thinking systems is from biology right?

If you’re introducing a new member, you have to compare it across all levels before making a similarity claim. It’s the height of ridiculousness to think otherwise.

Re: Stop Anthropomorphizing Intermediate Tokens as Reasoning/Thinking Traces (2025)

#282

Earlier quoted context omitted.

LLMs produce language. And you're right, if we restricted claims to that, no one would object. It might 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. The small markov chain language models of old clearly aren't thi…

>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.

Re: Stop Anthropomorphizing Intermediate Tokens as Reasoning/Thinking Traces (2025)

#283

Earlier quoted context omitted.

> Ability to feel Interesting, possibly productive, but still not clear: that can be interpreted as just "reacting to input".

> that can be interpreted as just "reacting to input" How? That's not the same.

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".

Re: Stop Anthropomorphizing Intermediate Tokens as Reasoning/Thinking Traces (2025)

#284

Earlier quoted context omitted.

> 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. The small markov chain language models of old clearly aren't thi…

>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…

> 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.

Re: Stop Anthropomorphizing Intermediate Tokens as Reasoning/Thinking Traces (2025)

#285

Earlier quoted context omitted.

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…

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…

You said (originally):

> 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.

Re: Stop Anthropomorphizing Intermediate Tokens as Reasoning/Thinking Traces (2025)

#286

Earlier quoted context omitted.

> 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? 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 proven an LLM has thought

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.

Re: Stop Anthropomorphizing Intermediate Tokens as Reasoning/Thinking Traces (2025)

#287

Earlier quoted context omitted.

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…

You said (originally): > 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 l…

> 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.

Jeez.

Re: Stop Anthropomorphizing Intermediate Tokens as Reasoning/Thinking Traces (2025)

#288

Earlier quoted context omitted.

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 proven an LLM has thought 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 b…

>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.

Re: Stop Anthropomorphizing Intermediate Tokens as Reasoning/Thinking Traces (2025)

#289
post #170

Earlier quoted context omitted.

We know quite a lot about consciousness. You may not, but we know enough to know the informational dynamics in a brain are vastly different from an LLMs. Exactly what kind of certainty are you looking for? Happy to provide it at a molecular, cellular, tissue or whole brain level.

What causes consciousness? Why aren't we all p-zombies?

Let me address the p-zombie first: it's a biological impossibly. Saying a p-zombie can be conceived of that has no inner feeling is like saying I can conceive of a philosophical star that radiates dark. Very nice that you can do that, but it's physically meaningless.

Why does biology preclude a philosophical zombie? Because every year we find new evidence of how utterly interdependent brain processes are and how tied to the experiential history of an organism.

We have mapped out the initial engrams that form in response to a new salient memory, and seen that 1. Time of day, 2. Physical location 3. Internal state all unique to the organism drive it's specific response, the specific way it saves the memory, etc.

That is, the organisms path history, it's interactions with the environment over space and time, shape it specifically based on the spaces and times IT experienced.

Take circadian rhythms, the internal timekeeping system all animals have. You feel it go haywire when you have jetlag. That is quite literally a history dependent response from your circadian clock to unexpected light.

Your p-zombie, if you specify it to have exactly your rhythms, will then need to have identical molecules being produced at identical times in every single cell, because that is how circadian rhythms are instantiated in all life, it's in each cell, and these cells can be synchronized, or, due to events like long distance travel or shift work, desynchronize. When desynchronized, you feel it, you feel different parts of your body adjusting, your meals shift, your taste and mood for food shifts...

Now, to put this in perfective, a human has about 36 trillion of their own cells, and an equal quantity of single cells symbiotes and commensal organisms, which give off all kinds of chemicals that shape, among other things, the circadian rhythms we talked about.

Now can you tell me: does the p zombie have not judt an identical compliment of 70 trillion odd cells, and they will all be in the same phase all the time as the cells in the non-zombie conscious person?

If so... How is this masterful phase synchrony across space achieved? What physical process allows for this?

If you cannot conceive of a way to do this synchrony (and you won't, basic physics forbids it), I think the sensible conclusion is to stop worrying about the philosophical zombies, and start looking at what information we have about actual humans and animals.

I brought up clocks to make a point, but actually, the evidence is building the biological clock is foundational for consciousness:

Some clinical signs: https://academic.oup.com/sleep/article/45/7/zsac094/6571981

And a broader theory: https://pubmed.ncbi.nlm.nih.gov/34382225/

Re: Stop Anthropomorphizing Intermediate Tokens as Reasoning/Thinking Traces (2025)

#290

Earlier quoted context omitted.

> And biological machine is? "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, often in completely different roles. > How is the biol…

>"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…

> 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?

Post reply on HN