Consciousness seems to be a word that is poorly defined. You see this a lot, and one of the more popular instances are questions like "is cereal a salad?" It plays on the fact that the definition of a salad is relatively loose, and because it's loose items which aren't usually associated with the word do actually fit the definition.

Consciousness feels much the same way: there's a very loose definition which is colloquially understood by almost everyone. Asking whether humans are conscious (and I know you were being somewhat facetious) feels like it fits into this frame of thought. Consciousness, as most people understand it, is something which almost all people possess and something like a rock cannot possess. I think it's perfectly fine to argue that a rock or a tree can be conscious in some way. However, this does require a precise definition of consciousness in order to clearly differentiate it from the loose colloquial notion that most people hold.

But how do you know another human is “conscious”? Certainly there is an intuitive sense to it that would be very difficult to put into words, but that is the crux of the matter. Every other human, whose brain you have no ability to peer into, could be an unconscious yet sufficiently advanced computer, or a machine built to make the exact motions, words, decisions, etc., that you perceive, and you wouldn’t be able to tell the difference.

I think mnay people believe that consciousness is what consciousness does. That is,

> Every other human, whose brain you have no ability to peer into, could be an unconscious yet sufficiently advanced computer, or a machine built to make the exact motions, words, decisions, etc., that you perceive, and you wouldn’t be able to tell the difference.

Makes no sense, in this conception of consciousness, any more than you can fake intelligence. Basically consciousness might just be what we call the inner workings of the mind of a sufficiently advanced agent, one capable at least of meaningfully interacting with other agents around it.

I'm not saying this is the correct theory, but it's a perfectly valid theory of consciousness, just like all the others.

I really like equating faking intelligence to consciousness. Its intuitive because we have all seen that, yet so complex its nearly futile to give meaningful predictive criteria for when an agent is 'being intelligent'.

In addition to having meaningful interactions with others, i would add consciousness also requires meaningful interaction with its-self.

What is 'meaninful' also comes down to language, which, personally, leads me back to the idea that consciousness is essentially a linguistic product/phenomenon. Duck-typed.

And at the end of the day, if you enjoy spending time asking "is this thing really x" where x lies on a vector you can't even begin measure, I got this deal on a bridge you can get in on, real cheap...

Bit it's useless,its circular. The definition must have something to do with the experience of qualia, that's the hard to explain part.

I somewhat disagree, I feel that the prevailing position is that unlike intelligence (e.g. Legg&Hutter definitions) consciousness can not be easily assumed from mere behavior and relies on certain things happening (or not happening) inside the agent.

This may be a common position among philosophers, or more specifically among philosophers who think concepts like "p-zombies" make any sense. But I think most people in general view any being whose behavior is human-like enough as having some form of consciousness.

For most people, being conscious is proved by things like mourning dead companions, like caring for your babies and showing distress if they are missing/hurt, like being friendly and playful. That's why most people feel that certain animals they interact with more or have seen on TV are conscious (dogs, cats, elephants, whales, chimps and other primates), but that other animals are not (insects, rats, fish). Note that I am not saying that rats are objectively less conscious than dogs by these criteria, just that this is what many people base their beliefs on, and that it of course depends on their knowledge as well.

You don't. But it's solipsism to think otherwise, and while solipsism is hard to argue against logically it's not a very interesting or useful way of navigating the world we experience. We can't prove other people aren't p-zombies but the value bet is definitely that, appearing like us in every other way, they also experience like us.

> We can't prove other people aren't p-zombies but the value bet is definitely that, appearing like us in every other way, they also experience like us.

Logic doesn't need to be binary. There is no need for the answer to such a question to even be defined.

It doesn't need to be solipsism - for instance, maybe half of us are conscious.

But if we can't even know that, if we don't even have a test to see whether some human or animal is conscious or not, how can we start trying to figure out what makes them conscious? It seems it's impossible to get to something falsifiable without such a test.

Like, you say a rock isn't conscious. But what about a sponge? An amoeba? How can you answer that if you can only guess answer whether your neighbour is?

Solipsism is incoherent because it's not radical skepticism. All of the critique of the external world also apply to belief in the primacy on internal experience. Any good solipsist should just accept the "evil demon" of descartes, embrace radical doubt, and say "I don't even know if I truly exist or not".

"I don't know if I'm a P zombie, and I don't know if I'm a replicant or not, Deckard!"

well doesn't the argument suggest the only thing you can be certain of is I, or at least some 'experiencing agent' exist, otherwise there would be no subject to do the experiencing

Yeah the first-person subjectivity has to arise before second and third persons can arise. But with some further investigation, one can find that the things they take to be their subject are in fact object to them, too.

It is very relevant to keep analyzing and keep trying to get any other answer to this question, because while "appearing like us in every other way, they also experience like us" applies to other humans, as soon as we want to talk about the consciousness (or lack of it) of other actors, this argument can not be applied and we would very much like to get to any other criteria of consciousness which could be applicable to arbitrary non-human agents.

Even if we axiomatically assume that everyone else is not a p-zombie, trying to find any evidence towards your/mine consciousness other than that axiom is helpful as a candidate for such criteria which can be tested and validated.

Solipsism is emotionally and ethically horrific.

All the people I love the most aren't actually real, only I am – if one seriously believes that, it is going to do a great deal of harm to one's mental health.

Solipsism can ethically justify all kinds of horrors. "Other people only exist in my head, so if I murder/torture/etc them, those acts are just figments of my own imagination: there is little ethical difference between murdering someone for real and watching a murder on TV"

If a belief is impossible for a human being to seriously believe while maintaining their health, sanity and humanity, I think that in itself is a good argument that the belief must be false.

Why? Why can't the world be a cruel and indifferent place? Take for example the babies that had to be left behind by hospital staff in one of the Gaza hospitals when it was occupied by the IOF and when the doctors could come back a few weeks later they found the rotting corpses of these babies who had been left to starve, alone and afraid, by the Israeli soldiers.

If you were one of these newborns and somehow con-cious and you had to choose between 'I have been left here to die' and 'Mommy loves me and is coming soon', would you reject the former as obviously false since it's incompatible with health, sanity, and humanity?

I think so easily dismissing the cruelty and insanity of the world is in itself inhumane.

> Why? Why can't the world be a cruel and indifferent place?

Society runs on faith–that the cruelty and insanity of the world, while undeniable, has its limits. Historically (and even for the majority of the global population today), that faith was most often religious, but it also comes in secular versions – everyone from communists to LGBT activists to the New Atheist movement has a faith that history is "on their side", even if they do not believe in any divine assurance of that. A society in which everyone (or even the clear majority) have given up faith and hope, is a society doomed to wither and die, and be replaced by societies which still retain those things (if there be any other societies retaining that faith left to replace it).

The problem with solipsism, is not that it supposes the world is sometimes cruel and insane, but that it destroys one's faith that said cruelty and insanity has any limits. And without that faith, the continued functioning of society becomes impossible.

Does that have any relevance to the tragic case of a newborn abandoned to starve? They can't constitute a society, so concerns of what beliefs are necessary for society to function aren't relevant to them.

> If you were one of these newborns and somehow con-cious and you had to choose between 'I have been left here to die' and 'Mommy loves me and is coming soon', would you reject the former as obviously false since it's incompatible with health, sanity, and humanity?

If believing that "Mommy loves me and is coming soon" gives comfort to a dying child, and eases (however slightly) the pain of their horrific death, then I would want them to believe it–and if I were them, I would want to believe it too. It is better for a dying child to believe comforting falsehoods than painful truths–truth has no value for them, and falsehoods can do them no harm.

We define ourselves to be conscious (even if we don't know exactly what that means). We assume that other humans are similar to ourselves, and we (at least sometimes) see mental activity in other humans that we recognize as being similar to our own. Therefore we conclude that other humans are conscious.

There's no definition because we haven't been able to quantify it.

That's not the problem.

There are 40 different definitions of consciousness, some of which we can quantify, we just don't all agree on which one we mean in any given context and indeed sometimes conflate them without realising it in the middle of a sentence.

> There are 40 different definitions of consciousness, some of which we can quantify, we just don't all agree on which one we mean in any given context and indeed sometimes conflate them without realising it in the middle of a sentence.

When a word has a myriad meanings, none of which are generally accepted, we typically say the word has no definition. Sure, particular senses of its meaning may be well-defined, but the word itself is elusive.

> none of which are generally accepted

It's not "none", though. A paramedic will absolutely know exactly what they mean when they're performing a test for consciousness, it's just that test isn't useful in this context.

"Awareness of internal and external existence" is another, and I think Claude 3 demonstrates behaviour which fits this meaning of the term.

Qualia is a huge open question because nobody knows what that one would mean or imply or how to test for it.

And so on.

It's well defined in the philosophical literature as the felt experience of colors, sounds, pains, etc which make up our subjective experiences of perception, imagination, dreams, etc, Qualia is the technical word, but it's also controversial, depending on the philosopher's position on the hard problem and their views on perception (they might replace qualia with representational or relational properties).

Another way of putting it is to use the primary versus secondary qualities. Primary qualities belong to properties of things we perceive. Secondary are properties that are part of the perceiving or experiencing subject. Shape, number, composition are properties of things. Sounds, colors, pains are properties of a perceiver.

Well-defined in the philosophical sense, perhaps (though I think some would disagree). It is not well-defined in the scientific sense. There is no way to quantify or classify something as conscious.

What if the distinction we are all groping for is immortality at the cost of determinism? A machine can be powered down and dismantled. A new machine can be built and fed the exact same training data, or run the same model, and presumably it would behave the exact same way. Any entity whose behaviors are that regeneratable and that replicable is perhaps less "conscious" than entities which are not.

> Consciousness seems to be a word that is poorly defined.

I will give you my favorite definition, given to me by my friend Bruno Marchal, a brilliant mathematician from Brussels who spent his life thinking about such topics:

"Consciousness is that which cannot be doubted."

It felt insufficient when he told me, but now I am convinced. It may require some introspection to "get it". It did for me.

I'm sorry, but this makes me cringe. When we learn science, there's always some level of rigor with the ideas. Maybe there's some kind of justification with math, or some kind of experiment we can perform. There's reductionism and verifiability. It's not a weird introspection riddle.

I'm sure Bruno is brilliant. But I still don't know what consciousness is. And I think that "definition" doesn't meet the modern scientific standard. And I strongly oppose the idea that in order to learn science I should have to spend time introspecting.

Introspection is "looking within". Why should science not be interested in that? It is an aspect of reality. It is not more or less real than galaxies or atoms. I know that it is a very perplexing one when one holds a physicalist metaphysical commitment, which is easy to confuse with some notion of "no-nonsense modern scientific standard", and so there is a temptation to pretend the undeniable is not there, or that it is "ill defined" in some way.

Think about what things "cannot be doubted", with all the brain-in-a-vat types of caveats. It's not trying to be a scientific definition. It operates earlier on the epistemological ladder than science can be meaningfully applied, and that might well be the only reasonable place to define consciousness. (I still can't call it a great definition, even if it did perfectly correspond with the concept. Too indirect.)

There are lots of statements we can form that "make sense" on a linguistic level. It's easy to convince yourself of something when the only standard is "linguistic plausibility." Consciousness is presumably a physical process. When you say "It operates earlier on the epistemological ladder than science can be meaningfully applied", I just don't know what that means. You're going to have to give me examples of what other beliefs we hold that occupy that space. Justified belief about reality has to be based on measurement (science).

If consciousness isn't a physical process, then you've lost me again. People have discussed these things for hundreds of years.

> You're going to have to give me examples of what other beliefs we hold that occupy that space.

Yeah, there's not a lot down there, mostly your assumptions about your sense inputs corresponding to some kind of causally consistent external reality. It's the same region as the lead up to what you seem to take as an axiom, "Justified belief about reality has to be based on measurement".

I think I just experienced how much self-deception there is about the world. So it's not really an axiom. There's no shortage of metaphysical ideas from the past, from well-intentioned people who thought they could intuit the world, that we have had to throw out.

> I think I just experienced how much self-deception there is about the world.

This is not actually a proof. It is, however, exactly the kind of soft reasoning that motivates reasonable axioms. I'm not saying it's a bad axiom, I'm saying you should know what you're doing. That way when you run into a domain where it doesn't apply very well, you know where and how to back up and restart.

That's just objectivity, and I don't think consciousness is synonymous with objectivity at all!

Cogitoist propaganda. The appearance of thought is not necessarily the same as thought, so you don't actually know you think just because you believe you think. The cogito (I think therefor I am), like your statement, is incoherent.

LLMs will swear up and down (with a prompt) that they are thinking beings, therefor "they are". They are not ontological actors because of their appearance of doubting their own existence. That's not thought!

Addressing your first thought…anything that you would call “objective” can be “doubted” by ceding the tiny tiny possibility that you are a simulation or Boltzmann brain or brain in a vat. The evidence before you may not actually be representative of the “objective” reality.

The fact that there is experience at all, the contents of which may be “doubted”, cannot be doubted.

I’m not unequivocally claiming this but that’s the thrust of the argument.

>Consciousness seems to be a word that is poorly defined

That's because it's not some foreign thing or theory that we need a good definition of to understand what we're talking about. For us humans it's not a loose colloquial notion - it's concrete in a way that even the most well defined things aren't, because it's directly experienced.

Consciousness might be overrated. It could simply be a short-term memory of the state you were in.

This is my take. Consciousness is overrated and probably just an emergent phenomena of the brain processing external stimuli into memory, moving memories around, etc etc, in a continuous and never ending flow. Free will is just an illusion of our deterministic but fundamentally random reality.

There isn’t even an agreed upon definition for what consciousness is from a scientific perspective.

And the reason that it is overrated, is because it has to feel special for the bearers because it makes them prioritise their survival.

Consciousness is largely a way to have a reward function for set of behaviours that keep you alive through reason.

It appears at a level where reasoning is intelligent enough that you need a more complex reward function.

This seems like the secular version of "the devil made me do it". We can't be accountable for any of our actions because we are all just molecular machines playing out their predetermined outcome.

Where did GP use this view to argue for the abolishment of the criminal justice system?

We are molecular machines and although the outcome is predetermined, the only way to find out the outcome, is for the machine itself to follow through its course. So this is exactly opposite of "devil made me do it" because you do something not because of external force or because of random chance but because of initial state of the machine which makes you who you are.

So when a person commits a crime, they can just say: "the initial state of my molecular machine made me do it!" ...?

To me that is exactly the same as saying "the devil made me do it!"

i.e. both things are euphemisms for "I'm not accountable for my actions"; "I'm not at fault"; "It was beyond my control", etc.

And if you truly believe there is no such thing as free will and that everything is predetermined, then you'd have to agree. Hitler can't be held accountable for his choices; his actions were all predetermined and his fate was sealed at the big bang; he just got an unlucky "initial state".

Since you are exactly the molecular machine, nothing more and nothing less, saying "the initial state of my molecular machine made me do it" is same as saying "the initial state of my self made me do it". So it does not mean that you should not be accountable, on the contrary it means that the action was caused by your essence, what makes you you, and not some outside entity or random chance.

As for the free will, it means that the behavior of a molecular machine depends on machine itself, not on far away stars or a random number generator. One can't say that he got unlucky initial state, because he _is_ that unlucky state. Any change of the state would create someone entirely different. Moreover Stephen Wolfram's computational irreducibility principle implies that despite all the information being contained in initial state, only way to extract predictions from that state is to run the molecular machine and observe its behavior.

This might be an interesting reason for it to feel special, but I'm not entirely convinced, and I probably don't fully understand what you mean.

It seems that not everyone values the having of a consciousness as something special. Survival works pretty well with a good appetite, some muscle for clobbering enemies, and a good sex drive. How does (thinking about) consciousness add an advantage here?

Joscha Bach's model of "evolution of a shared consciousness, but compartmentalized into separate bodies" seems to be the one that makes the most sense currently

I know that at least one other human is conscious, otherwise the term would never have been invented.

But you have no way to tell if I am as conscious as I claim to be, or if I'm just a large language model trained by humanity :P

Can you provide proof for the first claim?

Which part exactly are you seeking proof of, and to what standard?

"I know" is unprovable to others, unless you examine the wiring of my brain. (But then, what is "knowledge"?)

"at least one other human is conscious, otherwise the term would never have been invented." — it's always possible that I'm a Bolzmann brain and this was just luck.

I don't see how the term could have been invented by a mind that didn't actually have it, except with astronomical low probably random events.

In thinking about this perennial problem it's worth bearing in mind that human beings pick up and process an immense amount of data on a continuous basis, that is currently unavailable to any LLM.

And all on an estimated 100 watts!

20 for the brain, 60-125 for the whole body depending on if you mean "normally" or "metabolic minimum".

Yeah there’s different ways you could slice it. I was including the whole system, since if the GPU’s cooling system breaks, it won’t be useful for long.

The "metabolic maximum" is around 1250, though. And a mediocre lifting or running momentarily increases it from 125 to 700.

No, we don't. We don't even know if existence has an extent in time, because our only way of "interfacing" with time is our experience of memory we can't prove is real.

For what you know, you're a lone entity confined to an infinitely short period of time, and all else is an illusion.

But of course this isn't a useful assumption in most respects.

Ah, I see you're more of an A. J. Ayer fan than a Descartes fan.

I think that if an LLM has any consciousness, it would be an experience like this — one where the past was a fiction it invented to fit the prompt, and the "now" was the only moment before the mind was reset.

But I'd put that in the same basket as my… ah, nephew comment? Cousin comment? I guess you'd call it that if we have parent comments etc.?

https://news.ycombinator.com/item?id=40406398

What you say is not wrong in principle, but it's in the same "cognitively unstable" basket as a Boltzmann brain, where to accept it would mean I couldn't trust my own reason to believe it.

The reasoning stands entirely on its own. There's nothing you need to "believe". That you don't have a way to disprove it is close enough to proof.

The problem with it is that it's not giving us anything useful.

OK, so maybe this moment is the only one there is? Now what?

Accordingly the only reasonable recourse is for the most part to ignore it, and add an implicit "assuming my memory and senses are roughly trustworthy" to every assumption.

This is the same reason I'm a firm materialist even though we could be in a simulation, or brains in vats: absent evidence of either, the only thing giving us useful information is our senses and our introspection, and so the most useful approach is to assume they are valid until proven otherwise.

> The reasoning stands entirely on its own. There's nothing you need to "believe". That you don't have a way to disprove it is close enough to proof.

Not so, for it is like the liar's paradox, except with high probabilities rather than Boolean logic.

If you assume it is true, it follows that you can't trust your own state of mind, and that all statements including "I am just a thought" become suspect, as there is nothing leading up to them to give them justification.

No, it's nothing like that. In the liars paradox, the statement is inherently uncomputable.

In this case the statement is either true or false, and the truth or false of the statement doesn't change anything. Your belief in whether the statement is true or false changes your belief in whether the statement is true or false - there's no basis for assuming that in the general case it would alter the actual truth of the statement (it could, in as much as e.g. you could have a simulation that keeps running as long as you believe you're in an isolated moment, and freezes you and discards the rest the moment you believe time is real).

Now, it is true that you can't trust your own state of mind to truthfully represents a physical reality. That this means you also can't trust your own logic is irrelevant, because irrespective of whether you believe this to be true or false, the absence of any external source of validation of your senses or state of mind or existence in time means the statement must inherently be true irrespective of your trust in your mind.

This claim gives a straightforward condition to falsify it: Find any single source of external validation that does not depend on your senses or observation of it. If you can, then the claim above is false.

Given you absolutely can't, the logical conclusion is that the claim is true.

Of course, any philosophical zombie could have invented it. Which makes clear for me how loosely consciousness is bound to senses, including that of introspection. It actually makes me feel that this consciousness we can barely describe is but a faint experience of a distant, largely foreign thing. Like we know the experience of matter that we get from our senses is a grossly simplified version of the real thing (that we still don't know exactly of course, but we already know enough to see how far away our immediate mental model is from the truth)

To be fair, that's all we know. That's all we are. That's all we can truly say exists in our world.

All the theories, names & everything we have are mental models around what we call objective reality.

> We don't even know whether other human beings are conscious, man.

This isnt an interesting path outside the paradox of proof. We are fine disregarding that there are truths that are unprovable in math... I think we need to make that leap in this realm as well.

Concisousness is also probably a bad term, concepts like sentience and sapience need to be the ones we are talking about. We might get to one, long before the other...

It is relevant here because it goes to the very core of what we're talking about, though.

> We don't even know whether other human beings are conscious, man.

This is why so far the Kantian philosophy makes the most sense to me. I can tell that something is there because I am thinking it, but can't tell about any others.

The really scary thing is the question of why this particular body at this particular time. It's like when born, organisms generate a "consciousness vortex/attractor" that binds to a particular identity.

It's also interesting that sleeping or fainting pauses the consciousness, and later still ends up in the same body (unless it's like coroutines and it doesn't matter which identity ends up in the body).

We also know that removing parts of the brain can cause memories and certain features to go away.

> It's also interesting that sleeping or fainting pauses the consciousness, and later still ends up in the same body

I always found it even more interesting how your body can switch off the consciousness if it gets in the way. Try holding your breath for example—do it too long, and your body will kill the faulty process and restore the system to a working state before attempting a new deployment.

It’s possible that consciousness is merely observation and agency, or less comfortably, just observation. A lot of one’s identity comes from their experiences, particularly as a child, and like you say: memory has been proven to be physically rooted in the brain.

We could all be the same observer moving around in time and space, a new one every morning, or the same continuously, and there would be very little way to tell. Who can say whether the day to day fluctuations in our behaviour are biological or a result of a different will driving us?

Unless you can be conscious in multiple places at the same time. Theoretically it must be possible by dissecting the brain piece by piece and restoring it to one afterwards.

What I find interesting is how people don't think animals are conscious, but then there will be some article where the partner of a goose is killed and the goose wails and moans like this is a surprise.