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

And arguing changes LLM responses, especially when they are wrong

No. You’re the one who is ignorant.

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.

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.

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 (and all this is well established.. there was a Nobel for the field in 2017) 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?

Nope. It’s got a genuine off state, when it’s out of a cell, where it lacks agency. It’s dormant and can be taken up by a cell only by chance, not through its own active efforts. It bears none of the descriptive hallmarks of consciousness, nor is there any internal physical dynamic inherent to a virus. By definition it needs a host to start having a dynamic, and ant that point, it anctivates its drive, which is singular: reproduction and transmission, which it must balance.

And this is where you see viruses show the beginning of agency, in the making of this choice. They do show some signs of sensing their environment , even communicating with each other, through a process called quorum sensing, to decide if they should follow a lysogeny (integrate and stay quiet) or lysis (rapidly replicate and destroy the cell).

Note, this requires a host, so in so far as we can talk of a viral consciousness, it’s restricted to finding a suitable host.

There’s also recent work on viruses upon host entry showing some sensing. Usually a single molecule for which they already have a receptor. So you can begin to see the thin levels of awareness a virus has. But it still can’t do anything on its own beyond deciding to not infect.

I’d argue viruses are right at the edge of consciousness, just as they are right at the edge of life. They can hijack life and demonstrate much more life like properties, including a proto consciousness.

But they have no internal clock. They are always sensing the environment through multiple rich channels, nor do they have an active biochemistry they need to maintain when they’re dormant.

Consciousness adjacent? Consciousness-compatible? Both seem to fit viruses. And also LLMs, funnily enough.