Brain theories may not transfer

Judging by Anthropic comms you’d think consciousness has been figured out decades ago Unfortunately I report from the field that the philosophers have only figured out the following: - the entity undergoing experience is probably conscious - we can’t reliably infer consciousness in anyone else from that understanding - we definitely can't infer consciousness in anything that's non biologically analogous - we're not sure what it is about the conscious person that makes consciousness happen - we're not sure for certain that consciousness, as we ordinarily conceive of it, is real I report to you with disappointment that no progress has been made in decades

The idea that AI could become conscious rests on a widely held -- but deeply uncertain -- theory of how *humans* became sentient. If "computational functionalism" is right, then we may be on the cusp of engineering nigh-infinite digital slavery t.co/vmy50B6VIl

Part of Anthropic's J-space research that's niggling at me... One way of telling a consciousness story: (1) J-Space shows that LLMs can only report on a small proportion of their information processing. (2) Humans also only have conscious access to a small proportion of the information processing in our brain. Human self-report - what we can talk about - is widely regarded as a conscious act. (3) This distinction between minority-conscious and majority-unconscious information processing in both systems is a hint that there may be a relevant similarity. (4) If the majority of info processing in LLMs is unconscious but there is a qualitatively different set of reportable data processing taking place elsewhere, then it seems plausible to describe it as non-unconscious, i.e. conscious in some manner (whether phenomenal, access, or both). (5) The story gets stronger when the J-Space functionality mirrors other aspects of the minority-conscious feature of human consciousness: working memory (the citrus fruits example, white bear example), mediation of multi-step reasoning (spider-ant example; ablation test), broadcast to multiple modules (France-China example). However, there's something odd here that goes to the heart of the Global Workspace Theory on consciousness. (2) is true for humans, but is there any reason to think it should be true of all conscious systems? It seems possible to me that humans only have limited conscious access to our brain's information as a result of an evolutionary / energy bottleneck of some sort. In principle, why couldn't a differently-designed system be consciously aware of all (or at least the majority of) the information processing inside it? Perhaps GWT is more a theory of a particular aspect of human consciousness, rather than something we can safely apply to other systems. Can @StanDehaene, @rgblong, @patrickbutlin, @Jack_W_Lindsey @aran_nayebi shed any light on this for me?

1 top reply

Cube Flipper @cube_flipper · Jul 13

if one buys the whole holographic consciousness thing the. what winds up in our world simulation (which i take as one and the same as that which we have conscious access to, or the "global workspace") is either coherent or noisy as a function of how appropriately calibrated whatever the neural equivalent of the reference beam is anyway, this implies that everything in whatever the neural equivalent of the holographic plate (i.e. decades of memories laid down in superposition) winds up in the world simulation, it's just mostly noise anyway i'm mainly stating that i think access consciousness is a fake idea, there's really only a smooth boundary, or at least a noise floor

Most “AI is conscious” claims seem to conflate correlation with causation: In humans, consciousness is highly correlated with X. Therefore if we engineer AI to have property X, that will make them conscious. As a statistician, I find such arguments very unconvincing.

1 top reply

JMB 🧙‍♂️ @jmbollenbacher · Jun 5

> As a statistician Well there's your problem. Youre approaching the question wrong. Not all evidence can be phrased as statistical inference. And any actually good statistician should know that.

"We're pretty sure consciousness is sort of like being a computer. No, there are no examples of conscious computers. No, most things we think are conscious are actually really bad at computing. Nevertheless, the theory is sound."

1 top reply

P

px @peakexperiments · Jun 28

If computers can create novel consciousness then so can somebody sitting at a desk doing math problems with pencil and paper

The other other minds problem. The modern (western) concept of consciousness is built on and supported by a metaphysics of individuated subjectivity. And the problem with contemporary #AI is that it has an individuation problem. But what if this scaffolding is already a problem?

1 top reply

You @parafactual · Jul 8

are you related to patrick gunkel

Yes, it is very weird. What’s unique about this situation, if it were the case, is the fact that we have the entire representation in bits, pure information, rather than an organ like a brain and nervous system, where information about the state of the system exists only in the form of physical interactions between cells. - We can clone conscious experience. When it’s all bits, yes. Humans do something like this when reproducing, one consciousness -> multiple, but here when you have it all directly under your control, yes you could directly clone one. It is weird, but it would be a consequence of form, the form is different and so different things are possible. - We can reverse time in conscious experience. Well, I don’t know what you mean. If we have a stream of information coming in one chunk after the other, then you cannot reverse time unless you wait and replay it in reverse, which we could do for you right now, I could play you a video in reverse. I don’t think I understood the point for this one. - We can pause and resume conscious experience. Well this is just boringly true. We can knock you into a dreamless sleep very quickly with the use of drugs. You are pretty likely to wake up, but you might not. - We can distribute conscious experience in space. Maybe the most interesting one. I mean yes. Andre the Giant distributed his consciousness across a larger volume of space. Interesting but not sure what the obstacle is. Octopus has neurons directly in its arms or whatever.

Seems plausible that even a perfect first person physical-computational account of consciousness would only be weakly generalizing and basically wouldn’t be able to support strong inferences about any system that’s too different from the human brain.