Hacker News Reader

Comment by yannyu | Hacker News Reader

Okay, you're right. There is a world, and some hypotheses, and some falsifiability.

But how rich is this world?

Does this world progress without direct action from another entity? Can the agent in this case form hypotheses and test them without intervention? Can the agent form their own goals and move towards them? Does the agent have agency, or is it simply responding to inputs?

If the world doesn’t develop and change on its own, and the agent can’t act independently, is it really an inhabited world? Or just a controlled workspace?

View on HN

If you accept the premise that the consciousness is computable then pausing the computation can't be observed by the consciousness. So the world being a controlled workspace in my eyes doesn't contradict a consciousness existing?

I agree, evaluation of consciousness is another problem entirely.

However, the point I'm making is that even assuming an agent/thing is capable of achieving consciousness, it would have to have a suitably complex environment and the capability of forming an independent feedback loop with that environment to even begin to display conscious capability.

If the agent/thing is capable of achieving consciousness but is not in a suitable environment, then we'd likely never see it doing things that resemble consciousness as we understand it. Which is something we have seen occur in the real world many times.

I also agree. GP wrote: "It's a fragmented, discontinuous series of words and tokens" which poses an interesting visual. Perhaps there is something like a proto-consciousness while the LLM is executing and determining the next token. But it would not experience time, would be unaware of every other token outside of its context, and it fades away as soon as a new instance takes its place.

Maybe it could be a very abstract, fleeting, and 1-dimensional consciousness (text, but no time). But I feel even that is a stretch when thinking about the energy flowing through gates in a GPU for some time. Maybe it's 1 order above whatever consciousness a rock or a star might have. Actually I take that back - a star has far more matter and dynamicism than an H100, so the star is probably more conscious.

Reply on news.ycombinator.com