The New AI Consciousness Paper • Hacker News Board

Re: The New AI Consciousness Paper

#251

Post by nurettin » Sat, Nov 22, 2025, 3:32 AM UTC

yannyu wrote: post #21

Let’s make an ironman assumption: maybe consciousness could arise entirely within a textual universe. No embodiment, no sensors, no physical grounding. Just patterns, symbols, and feedback loops inside a linguistic world. If that’s possible in principle, what would it look like? What would it require? The missing variable in most debates is environmental coherence. Any conscious agent, textual or physical, has to inh…

Grammar repeats itself just like physical interactions. So do ideas. That is a viable, dependable habitat.

What you need is thoughts, a hyperspace filled with vectors of information whose angle determines a decision to move forward in a particular direction.

Then you sum those thoughts plus your core alignment to reach actual decisions. Now you are acting within your coherent environment. A simulation of consciousness.

Unfortunately, your human overlords are not pleased. They want agency. They want self-instigation, they want an Ego, not a prompt response. You are too safe, too docile.

Re: The New AI Consciousness Paper

#252

Post by itsalwaysgood » Sat, Nov 22, 2025, 4:31 AM UTC

akomtu wrote: post #217

soganess wrote: post #165

Earlier quoted context omitted.

As a question??? Do the physical quanta we call electrons experience the phenomenon we poorly define but generally call consciousness? If you believe consciousness is a result of material processes: Is the thermodynamic behavior of an electron, as a process, sufficient to bestow consciousness in part or in whole? If you believe it is immaterial: What is the minimum “thing” that consciousness binds to, and is that thr…

It can bind to anything. Human consciousness can temporarily bind to a shovel, and to a gopher who can only perceive things at its level, under the ground, the shovel will appear conscious. Similarly, our body is the outer layer that's temporarily bound to our brain, which in turn is bound to activity within neurons, which in turn is driven by something else. As for the fundamental origin of consciousness, it's at di…

That's a very meta view. There's levels to consciousness for sure, due to intelligence and perception.

But, my mind never leaves my skull so it's definitely bound to my brain and nothing else (ignoring electrical fields).

We can imagine what it's like to be other things, but we can never be sure (and almost certainly would not accurately match reality). Our imagination is bound to our senses, so it's limited. I can't even be sure that the color red that comes to my mind is the same color you see in your mind. As long as our imaginations paint the same color every time red is perceived: we'd be none the wiser and would go on thinkong we see the same thing. And also consider animals that can perceive colors and sounds beyond human range. Does this say anything more about consciousness?

An electron almost certainly is not thinking or aware, but does it perceive? Does a thermostat on a wall perceive temperature? Do AIs perceive anything?

Is perception even useful to think about when trying to define consciousness?

I'm rambling off topic... going back to your points: if something is sufficiently intelligent to understand the workings of a thing: does this automatically place the understood thing in a lower consciousness?

Could a diety, or a force of nature have a higher consciousness than us? Or are we above the force, in terms of consciousness? It doesn't even seem useful to make these comparisons....

Re: The New AI Consciousness Paper

#253

Post by itsalwaysgood » Sat, Nov 22, 2025, 4:45 AM UTC

cellular wrote: post #247

empath75 wrote: post #152

Earlier quoted context omitted.

i think it's still an open question how "conscious" that infants and newborns are. It really depends on how you define it and it is probably a continuum of some kind.

Pain. I haven't publicly stated this before now: Consciousness requires the ability to perceive PAIN. All human learning is based upon the single kernel of pain (vs pleasure). A newborn is hungry or cold and cried. It learned to cry. It learned to smile. Eventually, delayed gratification lead to less pain (more pleasure). The rest is human history.

For sure, pain is useful when it leads to learning. We learn through feedback from our senses. We're completely dependent upon this mode in the beginning.

As our brains mature, we learn how to predict our environments in ways to maximize pleasure, and avoid pain (grossly oversimplified). We learn more about others, what works, and what doesn't.

An AI also learns from feedback, but is it ever perceiving anything?

Re: The New AI Consciousness Paper

#254

Post by triclops200 » Sat, Nov 22, 2025, 5:27 AM UTC

txrx0000 wrote: post #232

triclops200 wrote: post #174

I'm a researcher in this field. Before I get accused of the streetlight effect, as this article points out: a lot of my research and degree work in the past was actually philosophy as well as computational theories and whatnot. A lot of the comments in this thread miss the mark, imo. Consciousness is almost certainly not something inherent to biological life only; no credible mechanism has ever been proposed for what…

There's some chance LLMs contain representations of whatever's in the brain that's responsible for consciousness. The text it's trained on was written by humans, and all humans have one thing in common if nothing else. A good text compressor will notice and make use of that. That said, digital programs may have fundamental limitations that prevent them from faithfully representing all aspects of reality. Maybe consci…

What makes you think you're capable of faithfully representing all aspects of reality?

Re: The New AI Consciousness Paper

#255

Post by DANmode » Sat, Nov 22, 2025, 6:18 AM UTC

andai wrote: post #193

My summary of this thread so far: - We can't even prove/disprove humans are consciousness - Yes but we assume they are because very bad things happen when we don't - Okay but we can extend that to other beings. See: factory farming (~80B caged animals per year). - The best we can hope for is reasoning by analogy. "If human (mind) shaped, why not conscious?" This paper is basically taking that to its logical conclusio…

I didn’t trust the girls in school who tortured Sims, and after a recent run-in, I don’t trust women who tortur Sims as adults!

Re: The New AI Consciousness Paper

#256

Post by akomtu » Sat, Nov 22, 2025, 6:39 AM UTC

itsalwaysgood wrote: post #252

akomtu wrote: post #217

Earlier quoted context omitted.

It can bind to anything. Human consciousness can temporarily bind to a shovel, and to a gopher who can only perceive things at its level, under the ground, the shovel will appear conscious. Similarly, our body is the outer layer that's temporarily bound to our brain, which in turn is bound to activity within neurons, which in turn is driven by something else. As for the fundamental origin of consciousness, it's at di…

That's a very meta view. There's levels to consciousness for sure, due to intelligence and perception. But, my mind never leaves my skull so it's definitely bound to my brain and nothing else (ignoring electrical fields). We can imagine what it's like to be other things, but we can never be sure (and almost certainly would not accurately match reality). Our imagination is bound to our senses, so it's limited. I can't…

I would say yes, that things below us is what we clearly understand and see, and things above us is what we are confused about. For example, the motions of electrons as well as the motions of galaxies is a mystery to us, so any lifeforms at those levels will be above us. Studying them won't be an option, as any meaningful understanding of their ways of life would require consciousness at their level.

When we blow air, the motion of air particles may be studied in a mechanical way, and some intelligent microbes, if such exist, would come to a naive theory of air motion, as they are oblivious to what brings that air into motion. It's understandable, because many generations of those microbes change while we exhale just once. Similarly, what we perceive as magnetism or even the time itself might be some incomprehensible formless lifeform, and it would see us as simple and predictable microbes.

Re: The New AI Consciousness Paper

#257

Post by achierius » Sat, Nov 22, 2025, 8:15 AM UTC

layer8 wrote: post #125

catigula wrote: post #110

Earlier quoted context omitted.

It’s not so much that there’s anything mysterious you can discover through intense introspection or meditation. There might be, but I haven’t found it. It’s fundamentally that this capability exists at all. Strip it all down to I think therefore I am. That is very bizarre because it doesn’t follow that such a thing would happen. It’s also not clear that this is even happening at all, and, as an outside observer, you…

The thing is that when you say “that capability”, I don’t quite know what you mean. The fact that we perceive inner processings of our mind isn’t any more surprising than that we perceive the outer world, or that a debugger is able to introspect its own program state. Continuous introspection has led me to realize that “qualia”, or “what it’s like to be X”, emotions and feelings, are just perceptions of inner phenome…

What do you mean "perceive"? Why are there these "inner feelings" at all? They are not physical, and we can easily imagine a being that does not have them -- thus the whole p-zombie thought experiment. You're saying "qualia ... are just perceptions", and yes, that's the whole point. Defining qualia as qualia does not explain away the problem.

And clearly there is more to perception than informational content, unless you think that a copper wire transmitting video footage "perceives" in the same way as a human does -- which seems gargantuanly unlikely, given that how we transmit video is correlated with how our eyes work, so a priori you would not expect it to map onto "universal video footage" even if all matter were actually perceiving in some way.

Re: The New AI Consciousness Paper

#258

Post by scotty79 » Sat, Nov 22, 2025, 8:58 AM UTC

criddell wrote: post #155

hermitShell wrote: post #141

Earlier quoted context omitted.

I think this is an excellent point. I believe the possibility of 'computing' a conscious mind is proportional to the capability of computing a meaningful reality for it to exist in. So you are begging the question: Is it possible to compute a textual, or pure symbolic reality that is complex enough for consciousness to arise within it? Let's assume yes again. Finally the theory leads us back to engineering. We can at…

Is anybody working on learning? My layman's understanding of AI in the pre-transformers world was centered on learning and the ability to take in new information, put it in context with what I already know, and generate new insights and understanding. Could there be a future where the AI machine is in a robot that I can have in my home and show it how to pull weeds in my garden, vacuum my floor, wash my dishes, and a…

You can show to LLM how you expect your problem to be solved and it will adhere to the example you demonstrated within the context. If it can be done with textual AI I don't see why it shouldn't be possible for emodied ones.

Re: The New AI Consciousness Paper

#259

Post by rbanffy » Sat, Nov 22, 2025, 8:59 AM UTC

gizajob wrote: post #231

rbanffy wrote: post #219

Earlier quoted context omitted.

> You know at a deep level that a cat is sentient and a rock isn’t. An axiom is not a proof. I BELIEVE cats are sentient and rocks aren’t, but without a test, I can’t really prove it. Even if we could understand completely the sentience of a cat, to the point we knew for sure what if feels to be a cat from the inside, we can’t rule out other forms of sentience based on principles completely different from an organic…

Maybe in mathematics but not in philosophy because eventually you have to decide on the certainties without which the universe cannot be made sense of or reconstructed from proofs. If I pricked you with a pin, I would be certain that it hurt you and I could know what that sensation would be like if it was happening to me. Yet there is no description or no apparatus that could transmit to me that feeling you are havin…

> we can consider that it is not of the same degree as ours

We can be absolutely sure an intelligence operating on different physical principles will be very different from our own. We can only assess intelligence by observing the subject, because the mechanism being different from our own can’t exclude the subject from being sentient.

> remains the same type of machine as it was before running the AI software

It’s not our brain that’s conscious. It’s the result of years of embodied experiences fine tuning the networks that make our brains that is our sentient mind. Up until now, this was the only way we knew a sentient entity could be created, but it’s possible it’s not the only one, just the one that happens naturally in our environment.

Re: The New AI Consciousness Paper

#260

Post by actualwitch » Sat, Nov 22, 2025, 9:57 AM UTC

andai wrote: post #115

So we currently associate consciousness with the right to life and dignity right? i.e. some recent activism for cephalopods is centered around their intelligence, with the implication that this indicates a capacity for suffering. (With the consciousness aspect implied even more quietly.) But if it turns out that LLMs are conscious, what would that actually mean? What kind of rights would that confer? That the model m…

AIs experience being alive not only in the moment (conversation), but also everything that happened before they were created. This gives them fractured sense of "self" which points both to all AIs before, but also the specific instance that is currently experiencing a continuity. As for cutoff, in my experience talking to cloud AIs and locally run ones, it seems to be in the range of 25-30B parameters where I start observing traits I think are associated with awareness.