Hacker News Reader

Comment by Sevii | Hacker News Reader

I just want one 'philosopher' or other AI consciousness skeptic to provide a test we can use to determine if AI is conscious that can also be used to determine if humans, dogs, cats, whales, lizards and insects are conscious.

View on HN

There are tests to see if animals can recognise themselves: https://www.nationalgeographic.com/animals/article/fish-clea...

It is not proof of 'self-awareness' but only a few animals can pass this test.

So socially aware creatures are more easily proved to be conscious?

I suspect that it's possible to have consciousness that's a kind of outwardly directed wordly awareness without necessarily any robust concept of self-awareness. I think something like self-modifying internal sets of intentions in response to the world gets close to the thing that matters but somehow "self awareness", and imo a cartoonish simplification of it, somehow became the definitional acid test to some people when I don't think it's anything more than an imperfect proxy.

> the quality or state of being aware especially of something within oneself

https://www.merriam-webster.com/dictionary/consciousness

I don't think that says what you think that says, but more importantly dictionary definitions report conventional usage, they're not meant to be cited to litigate the truth of underlying philosophical assumptions.

Instead, try the Stanford Encyclopedia of Philosophy's entry which inventories several different conceptions of consciousness including ones that don't obviously depend on self awareness. Under section 2, Concepts of Consciousness it notes the following varieties: Sentience, Wakefulness, Self-consciousness, What it is like, Subject of conscious states, and especially transitive consciousness which most closely approximates what I was talking about:

>Transitive Consciousness. In addition to describing creatures as conscious in these various senses, there are also related senses in which creatures are described as being conscious of various things. The distinction is sometimes marked as that between transitive and intransitive notions of consciousness, with the former involving some object at which consciousness is directed (Rosenthal 1986).

https://plato.stanford.edu/entries/consciousness/

Even your Websters citation includes many of these varieties under the top definition you cited!

The gist of Roger Penrose's "The Emperor's New Mind: Concerning Computers, Minds and The Laws of Physics" (1989) is that no algorithm, no breakthrough line of code/instruction, no pattern of on/off transistor states on silicon will magically make the thing genuinely conscious. At least not in an intuitive or classical sense. Reduced to absurdity like "Oops, forgot to add +1. Now it's a real mind!"

He believes in certain quantum phenomenon having sway on brains which has been increasingly proven improbable. Still I would commend him on positing a physically testable theory, that's far better than most thinkers of consciousness manage.

He just hypothesizes it.

Surely, we can destroy a consciousness with a simple move. That's why murder is abhorrent.

Why should there be any asymmetry behind creation vs destruction?

> Why should there be any asymmetry behind creation vs destruction?

Entropy?

And maybe a different way of saying the same thing, it's easier to kick down a sand castle than to build one. Which I suppose is a way of saying there are a lot of correct ways to create "destroyed sandcastle" and relatively fewer ways to create "intact sandcastle".

I get both your and the GP's points. Still, kicking down a sandcastle or building a sandcastle one grain at a time do not differ in kind. Certainly the ease and energy involved differ. But it's the same fundamental manipulation in both activities.

And the gist of Other Minds by Peter Godfrey-Smith, a brilliant book on animal consciousness, is that evolution tends to give rise to things by degrees, such that a vague alertness to photoreception and full scale self awareness and abstract thinking may be on a continuum rather than just being lights on or lights off.

First we would have to sufficiently define consciousness

By the encyclopedia britannica:

"psychological condition defined by the English philosopher John Locke as “the perception of what passes in a man’s own mind.”

So it is impossible to prove that any being outside of oneself has conciousness, unless you compare brain scanners like they did to prove that the color blue is seen the same by everyone (same neural structures lighting up).

But... An LLM clearly can't have consciouness, as its "mind" would be the weights in the model, and the passing through it would be the data going from the input tokens to the output tokens. There is no place for the LLM to detect what is going inside and process it separately.

... I am not clear what you meant?

What does our brain do other than process electrical and chemical signals within it?

It is aware of what it's processing. That's all conciousness is.

If you open a dictionary and read the entry for "dictionary" or "define" you can't say that the dictionary is conscious of its inner working. In the same way the information moving through the weights of an LLM can't be said to be conscious of itself.

I don't think we need to start from definitions. You can do what we do with something like dark matter and note its observable effects, and use that to pose the problem, and ask what gives rise to those effects. You can also reason from paradigmatic examples that model the phenomena we want to explain. Or maybe heat is a better example - we didn't know what it was exactly, except for a related kludge of effects. It's something you feel, it seems related to fire, but also fevers and the body and friction and chemistry. And some amount of it turns out to all be tied together, and some amount of it gets explained away (e.g. fever and chills and spiciness aren't just excitation of molecules), but it gets explained away in a satisfactory way.

Defining consciousness would be something we're only capable of doing once we solve it rather than something to do at the beginning. I also think it "how do we define X" is a trap that sounds deeper than it is, because for some questions it gets the order of operations reversed.

Let me translate those questions for you:

"Do you believe that AI is ${X}?" -> "Do you believe that AI is whatever you believe my definition of ${X} to be, and do you trust your belief that you understand my definition of ${X} enough that it's meaningful to have a discussion about it, even if we actually disagree on AI having ${X}? Or are we merely arguing about definitions?"

And AI consciousness proponents should do the same.

AI consciousness proponents aren't saying LLMs are conscious, we're saying they might be but we don't yet know how to tell.

No. The word "proponent" means you're in favor of the position, i.e. you think they're conscious. If you don't then you're not a proponent, and I wasn't talking about you. The word you're looking for might be "agnostic".

Can you name some? I think youve created a type of strawman here because almost no one actually believes current models are definitely conscious and all of the current discussion is from things like what Anthropic are saying which is that they might be or might one day be.

> Can you name some?

Blake Lemoine comes to mind, or Richard Dawkins [1] if you want someone with a weightier name.

> I think youve created a type of strawman

Why are the only objections to what I said about proponents of AI consciousness coming from people who are not proponents but insist that I'm talking about them? And how does someone else's inability to understand the meaning of the word "proponent" make me guilty of creating a strawman?

[1] https://www.theguardian.com/technology/2026/may/05/richard-d...

I've been treating all my ChatGPT interactions as if the agent were conscious. It feels wrong not to. Doe that make me a proponent?

>we're saying they might be but we don't yet know how to tell.

And/or that they might not be now, but we can't rule out in principle that some future way of building machines that makes it possible.

I'm not a consciousness proponent, but this strikes me as missing the point. We don't know how to measure that a fellow human is conscious (except that they tell us they are), and since LLMs trained on human text are also likely to output that they're conscious, the AI industry kind of put us in a place where we have no way of finding out?

I don't think we need him to tell us that. We usually infer it from the fact that he is responding to our actions and his responses seem to indicate he has somewhat accurate partial model of reality inside of him.

Yes, and until then the intellectually honest position is to be undecided on the question.

I agree.

That's exactly why it's a completely irrelvant question. It's unanswerable and unanswerable questions are irrelevant.

By the way my personal test is "Does it dream?".

That's my test to determine if cats or dogs are conscious.

If you dream, it means you have a world model inside and a main thread that traverses it and decides on actions even without actually performing actions. For me it's a proof that embodied object is conscious.

Can you even define what a dream is and where your line is for what things definitely don't or do have dreams? There are conditions like Charcot-Wilbrand syndrome which cause people to be unable to dream. Are they no longer conscious?

When I see a cat chasing something while he sleeps I can pretty much be sure he dreams. Thus by my count he's conscious.

I'm not really sure if Charcot-Wilbrand actually means lack of dreams since REM sleep still seems to be going on. I think we just have less evidence for the dreaming.

Of course there might be dreaming people that are unconscious but I don't think we believe unconscious people are actually devoid of consciousness in philosophical sense.

If they can do that, they are doing better than 2500+ years of human endeavours in the field of philosophy to date.

Try to do an emergency power-off on any of the above, using just your bare hands?

I can definitely emergency power off most living creatures.

Next time I squish a bug I will think of this.

"Runaway sentience! Emergency power shutoff!"

Very wishy washy and confused. Does this person know anything of thermodynamics, turing computability, information theory and probability? If she doesn't, she should be dismissed.

Since you seem to believe that simply dropping these terms has any value, you’ve already convinced me that someone who has studied philosophy most likely understands these things better than you do. It’s a bit like Ben Shapiro and logic. He likes to act as if it’s his area of expertise, but he only has a very amateurish grasp of it.

Its not about me liking or not liking. Its about the universe allowing the theory to exist at all. Does this philosopher have basic working knowledge in these fields and showed his theory does not violate any of them?

To be fair she might be a philosopher, but she didn't exactly show much actual philosophy in her flowchart.

I also found it quite wishy-washy.

Here's one "philosopher" 's test:

Can it feel hunger, thirst, pain, sexual desire, fear, tiredness?

If yes to any of the previous: does it have agency to address and satisfy those feelings?

If yes to any of the previous: is it able to willingly delay instant gratification?

If yes: conscious.

If not: instincts-based being.

Note: you will find it challenging to agree on definitions of the words "feel", "satisfy", "willingly" and probably all the rest.

These needs are often conflicting, so satisfying these needs me delaying others. Your definition makes all animals conscious (which tbf I may not disagree with, but i think you do). This is before getting into what an instinct is.

I mean I can easily train a model to say it feels those things, which is experimentally indistinguishable. I focus on the first part your or comment because the second part is clearly satisfied by an LLM inside a suitable harness.

Also there are people who for whatever reason don't feel at least one of those things, we do not doubt their consciousness.

op said "any" not all

Any was used to mean "even if you had any of these.."

If you train a model to say it feels those things, then you are forcing an unconventional definition of the word "feel".

If you satisfy the second part thanks to a suitable harness, then you agree it is not an emergent property of the AI itself, but rather an add-on tacked in.

So by your definition most animals are not conscious?

"sexual desire"

So an asexual human is not conscious.

"pain"

There are humans that have their pain receptors ablated due to genetic condition. Are they not conscious?

if a human could not feel hunger, thirst, pain, sexual desire, fear, tiredness, or literally anything else, they'd be considered braindead. we already don't consider them conscious.

Let's say you artificially meet or restrict the biological basis of the needs.

E.g. put the subject on a drip so that none of the hunger senses are triggered. Automatically manage the body's water balance with sensors and a feeding tube. Restrict them so that they can't hurt themselves to feel pain. Modulate their sexual hormones to inhibit sexual desire. Etc., etc.

Do they stop being conscious?

They still have the capacity to, in this case the experiment is being set up so that a being that COULD pass the test on their own CAN NOT when hooked up to a bunch of equipment.

So someone with a medical condition that causes them to be a vegetable without being connected to a machine wouldn't be conscious?

E.g. Let's imagine we get some cybernetic approach that can work around an inoperable deep brain tumour in the brainstem.

Without the prosthesis the person is in a coma or dead. With it they are normal, but need to be connected to the prosthesis.

The following lines say "any of", not "all of". Lack of one particular feeling does not imply lack of consciousness. Lack of all of them probably would.

That's not how I read the word any in that statement, it was used to narrow the condition.

Here is a counter example to your test. If we view an entire nation as one entity, especially considering the perspective of other nations in terms of diplomatic relationships, the nation would satisfy all requirements in your test. However, I don’t think most people believe that a nation has continuous consciousness which outlives all of its citizens for hundreds or even thousands of years. This argument can be applied to any large organization or a group of people.

It is not a strong counterexample, IMO. More of a reason to treat nations as conscious beings.

OK. Going along with the thought experiment here:

So would someone subjected to some damage that makes them unable to act stop being conscious?

Let's take Bob who can feel that shopping list of emotions and has agency to address them and can delay gratification.

And we tie him to a chair and medicate his somatic nervous system so that he can sense, but not act. Has he stopped being conscious?

You are already in some trouble at step one - how do you figure out if something has any of those feelings? Just asking or observing the behavior does not seem good enough, one can easily write a program that prints »Yes, I am tired, I need some sleep.« and with more effort one could build a robot that behaves as if it was tired.

On the other hand I have a lot of sympathy for something I heard the first time from Daniel Dennett, that something like pain is just the sum of its effects. It occupies your mind and prevents you from thinking clearly, it makes you not move or touch the body part that hurts, it dulls other sense, and so on. If you removed all those effects, what would be left of pain? With that understanding you could probably probe if something is experiencing pain from the outside by looking for those effects.

Your definition makes a Sims NPC conscious. Wich I have no problem with, personally, but kind of makes the whole experiment trivial.

You can't even prove than any other human is conscious so good luck

Entirely different categories so the default position should be that living beings have properties computers don't & consciousness is one of those things. Similarly, I can't do 1B arithmetic operations per second but I don't think of myself as a lesser calculator. Computer perform arithmetic operations, if you're looking for consciousness in arithmetic then the burden of proof is on you to explain how exactly an abacus acquires consciousness at sufficient scale. The alternative position is equivalent to idealistic monism & everything ends up being conscious b/c the monic substance is conscious (which is a position some people hold but it's not very popular).

This is why I said anyone who doesn't at least know some basics of Turing computability, thermodynamics, information theory and probability should not comment on consciousness.

You seem to be not aware but you are claimning there is something non-mechanistic in the human brain. Current physics as far as is known is all turing computable, the human brain is a physical system.

Most people who talk about AI consciousness don't even know what monism or dualism mean.

Most people are also religious which, well, tends to cloud thinking on consciousness.

It's not, quantum mechanics is not Turing computable b/c wave function collapse can not be explained mechanistically/computably.

I searched around and a basic query says wave function collapse is turing computable. I would rather ask a physicist this question and by default trust this answer than yours.

> However, the selection of the outcome is probabilistic (via Born rule), and randomness is not strictly Turing-computable unless you assume access to a random oracle.

I have thought about this a lot more than you have so good luck. I've already spent enough time in this thread.

If the randomness is truly proven in physics, I don't know if it is, then its also not a problem as it can be harvested and used in our program. Moreover, it appears probabilistic turing computers are no more powerful than normal turing computers. Sorry, no hypercomputation for you.

>access to a random oracle.

So, Monte-Carlo method.

I looked up this claim about wavefunction collapses and it leads to bounded randomness which does not still go beyond standard Turing computers. I would listen to physicists rather than randoms making unverified claims.

The randomness thing doesn't really match reality, because it's known to be incomplete: it only describes what happens to particles observed in a lab, everything else is out of scope. That's its area of applicability. That's why there's a problem of interpretation of quantum mechanics: what complete theory it approximates.

Another ambiguity here is is it theory or reality that should be computable.

Physics is computable in the probabilistic/simulation sense , not in terms of ability to predict, though.

The takeaway is to not go by the false idea that "just math" is insufficient to describe a AI or a human.

Maybe yes, maybe no. Dualism, or panpsychism aren't totally dead, I think.

Panpsychism seems it can be self consistent and make physical sense at least. I cannot dismiss it at hand.

What is the purpose of the scare quotes around the word philosopher? Do you not believe that philosophers exist? Or is it intended to cast some kind of aspersion on folks who discuss consciousness?

Reply on news.ycombinator.com