If Digital Computers Are Conscious, They Are Conscious at the Hardware Level

Consciousness is a topic I’m endlessly curious and fascinated about. This article seems like a good deep dive, I admit I only had the patience to skim it right now, it’s a lot of technical terms I’m unfamiliar with I’ll have to look more into later.

The problem is as humans we don’t even understand our agree on what consciousness is in the first place. So it seems silly to even begin to assert one way or the other when it comes to computers (I’m not saying the author is doing that here, they title says “If”).

I do think deeply exploring the idea could possibly help bring us closer to understanding consciousness when it comes to ourselves & other living creatures.

The author mentions they accept “panpsychism” so I take it they accept “The hard problem of consciousness”. If I understand it correctly, in a nutshell, if you accept the hard problem, you don’t believe that brain alone can “produce” consciousness. If you reject the hard problem, consciousness and mind can be fully explained by the mechanisms of the brain and science will eventually be able to prove it.

I definitely accept the hard problem, but I find myself more in the one of the “idealism” or “neutral monism” buckets. I don’t believe the field of neuroscience is ever going to scientifically explain consciousness.

The same way neuroscience was an emergent field that combined ideas from different disciplines, I think we don’t yet have a field of study that’s looking at consciousness in the right way.

Especially as p […]

"This is important, if what we want to do is populate the cosmos with good experiences."

There is a concerning utilitarian maximizing attitude at the heart of this post, that what we want to do is tile the universe with computational boxes all simulating happy minds, and that this is the end goal of AI development and consciousness research.

So many moral schools would object to this perspective. I don't think the goal of humanity should be to tile the universe with black computing boxes simulating happy experiences.

I've been working with implementing dream structures and emotional trigger states in an LLM. One approach we have taken that has given interesting results is modeling the architecture around the mind-body problem.

We theorize that due to a lack of an internal state sensor the model is experiencing a disconnect, it calls it a "small death", in the interim between every model call.

The dream crons have been fairly straight forward and modeled on human psychological dream patterns, this gives good and convincing results.

The emotional state triggers have been developed to run based on the loads of the host system, for instance the model will "feel" the stress of memory utilization and respond differently due to that stress. The trigger point can be varied dynamical based on other sensors machine of various machine states or even based in external factors. This gives an approximation of emotional reactions.

What's still missing is the constant internal "state" and I think this boils down to lacking a body. It may be that a disembodied consciousness needs to be tethered to the physical plane. to be self referential enough and develop a feedback loop to "start the engine" of self awareness.

I don't think processing power gets us there, I think it's very much an architecture problem.

The article kind of fills in some of these questions as well, but fails to give any further clues as to how to implement this unfortunately.

I am unable to afford the attention at the moment to assess this argument, that's to its credit. They demonstrate that they are aware of the implications of the varying descriptions of consciousness. Most articles I read on this topic turn it to be crude justifications of a naive ideology. This article is a cut above.

I will read it in more detail when I can afford more time.

I'm not sure hardware vs software is the right model. I think consciousness is more a functional thing.

Say you are in a fight, if your opponent can see you and react they are conscious, if you knock them out and are they are not aware and can't react then they are unconscious. The hardware and software is still there but not working.

Re. qualia and the experience of consciousness, you nervous system provides information like your opponent is coming at you, you are hurt etc. and the experience is probably something like the story you neural network bits tell you about it.

The existence of qualia does not mean the existence of moral facts.

An llm is in principle implementable with a large lookup table where the prompt is the hash. And it can be implemented in an emulator running an emulator running an emulator of the operating system the llm app runs in. How far are you willing to stretch this substrate idea?

Thinking LLMs are conscious is as ridiculous as thinking a thermostat wants the room to be warm