green_leaf

Karma: 173

green_leaf 19 Dec 2025 23:32 UTC
1 point
0
in reply to: fin’s comment on: No ghost in the machine
For example, “Does a simulation of a phage (or a virus, or a self-replicating robot) really instantiate life?”
Yes, no (outside the host, yes inside), yes. Given what we mean by life, a simulation of life is life.
“You may enjoy liquorice ice cream, but is it really tasty?”
This question doesn’t make sense, because taste is relative to the consumer. What is really tasty for one person might not be really tasty for another. Consciousness isn’t like that—what is consciousness for one person is consciousness for everyone, people just don’t know what the definition of consciousness fixed by their implicit beliefs is.
On your point about qualia computations, the standard questions pop up: if qualia are functionally inert computations, how would the ‘subject’ of consciousness know it is experiencing them, and so on.
Right.
And isn’t the idea of computationalism about consciousness that the ‘computations’ can be pinned down by the computational relationship between inputs and outputs; in which case wouldn’t the qualia-generating computations be abstracted away?
I don’t know. The way I understand (and don’t subscribe to) computational functionalism is that you can have different computations implementing the same behavior.

green_leaf 17 Dec 2025 16:26 UTC
1 point
0
on: No ghost in the machine
“It doesn’t make sense to ask questions like, Does a computer program of a mind really instantiate consciousness?”
This is a misunderstanding of how language works. Once we discover what the ontological nature of conscious states is (physical, biological, functional, functional computational, etc.) is and what their content has to be (for example, if conscious states are functional states, not every functional state is a conscious state), we have discovered the true thing we had referred to, and there is an objective fact on the matter as to whether that thing is or is not instantiated somewhere.
For example, imagine you tell me that there are qualia related to smelling coffee, such that the qualia make no functional difference to your behaviour, but do make a difference to your subjective experience. I say this is debunkable, because if qualia make no functional difference, then they don’t influence what you say, including about the supposed qualia.
You have gotten at something extremely important here—namely, that once software passes the Turing test, it’s unjustified to demand that it implements a specific computation to be called conscious, because the presence of that computation (compared to the information processing being implemented differently) makes no functional difference.

green_leaf 13 Dec 2025 6:50 UTC
2 points
1
in reply to: cube_flipper’s comment on: Does SI Disfavor Computationalism?
I’m not saying it’s not possible for us to be confident in some specific proposition.
I am saying that the state of having different qualia while preserving the same functional state is impossible in principle and that, due to Chalmers, it is impossible in the case of the human brain in this specific case.
I doubt we could ever keep the armchair philosophers happy. But for the consciousness engineers
Without philosophers, or without someone who isn’t a philosopher but does correct philosophy, you can’t arrive at the correct ontology of consciousness.
Keep in mind the theory of consciousness can’t make any falsifiable empirical predictions—the biological theory of consciousness, computationalism and other kinds of functionalism all make identical empirical predictions.
If you want to distinguish the physicalist theory of consciousness from some other, you can’t do it by making empirical predictions and comparing them to empirical results.
You can do it by non-empirical reasoning, but all those attempts fail for the reasons I explained in my comment (they are actually arguments against the physicalist theories of consciousness).

green_leaf 7 Dec 2025 9:51 UTC
1 point
0
on: Does SI Disfavor Computationalism?
For the sake of this comment, I’ll take physicalist theories to mean identity to some physical process (including the specific substance or fields).
Premise 3: Computationalist phenomenal bridges are complex relative to physicalist phenomenal bridges.
They’re not—mapping a microstate (or a pure state) to qualia isn’t more complex than mapping computations (or aspects of computations—like functional states) to qualia. (Computations (or functional states) contain less information, because they’re implicitly contained in the complete physical description, but the complete physical description isn’t contained in them.)
Even if it were the case, it wouldn’t matter, because a phenomenal bridge is in the map, not in the territory. (Semantics can be arbitrarily complex, as long as it is justified… which, in the case of physicalist theories of consciousness, isn’t.)
Premise 4: Physical phenomenal bridges are at least as compatible with the data of experience as computationalist phenomenal bridges.
That is literally true, but connotatively false. Physicalist phenomenal bridges are heavily disadvantaged by Occam’s razor (even if it were the case that specific physics was needed, we would have no way of knowing that, since our thoughts are fully determined by the computational state) and the specific physics of the implementation of the computational state is causally inert relatively to our mental processes (those are fully determined by the computational implementation).
We should judge theories of consciousness in the same way that we judge theories of physics, IE, by balancing predictive accuracy with simplicity of the theory, as stipulated by SI.
We shouldn’t—all viable theories of the ontology of consciousness, when applied, will have infinite predictive accuracy, because those physical/computational/functional differences are amendable to the correct kind of empirical research. But even with infinite empirical research, we still don’t know if it is the perfectly predictive physicalist, functional or computational elements of the system that are identical to conscious states. That is why the question is hard—it’s not enough to perfectly explain the agent’s utterances, we also have to find the correct answer to the question of the correct ontology, and predictive accuracy can’t help us there (at least not with respect to these three different theories).
A physicalist bridge needs to be able to pick out some physical phenomenon, such as patterns in the EM field. A computational bridge needs to do that as well, to parse the physical model
I see the argument—to map a computational state to qualia, we need to first map the physical state to a computational state, and then the computational state to qualia, and that’s (arguably) more complex than mapping the physical state to qualia directly. While correct, this isn’t relevant, because the bridge is in the map, and also because that would actually be an argument for functionalism. In the process of mapping a physical state to a conscious state, we need to compute its functional state (otherwise we don’t know what causal role that state plays in a conscious being with respect to its qualia in the first place).
We could get around this by precomputing the mapping between physical states/physical processes and conscious states/processes (so that we don’t have to compute the functional states in the processes)… but at that point, we might as well precompute the computational states as well, which, again, would render the argument moot.
The computationalist theory of phenomenal consciousness doesn’t care about how many implementation layers are stacked on top of each other.
This is a feature, not a bug—every physical system implements astronomically high number of computations. The conscious computation is the one we’re currently talking to, which is just one (ignoring details on the lower levels of abstraction which aren’t individuative of that computation).
If I understand correctly, cube_flipper welcomes such an experiment (save for the fact that it seems far beyond our current technology), and anticipates having a different experience due to the modified physical field.
That’s not possible, due to Chalmers.

green_leaf 5 Dec 2025 2:39 UTC
1 point
0
in reply to: Czynski’s comment on: Going Nova
To all appearances LLMs already do that and have for several years now.
LLMs can be (incorrectly) argued to have no qualia, and therefore no beliefs in the sense that my hypothetical uses. (In my hypothetical, the rest of the agent remains intact, and qualia-believes himself to have the quale of pain, even though he doesn’t.)
(I’m also noting you said nothing about my three other reasons, which is completely understandable, yet something I think you should think about.)
meaningfulness
Do you mean meaninglessness?

green_leaf 3 Dec 2025 23:53 UTC
3 points
0
in reply to: boazbarak’s comment on: boazbarak’s Shortform
Not a big believer in hypotheticals.
It’s a little strange that you don’t mind hypothesizing about how embodiment might be necessary for moral patienthood from embodied agents, but once a counterexample arises, you’re no longer a big believer in hypotheticals.

green_leaf 29 Nov 2025 13:07 UTC
1 point
0
in reply to: tslarm’s comment on: Should we extend moral patienthood to LLMs?
Chalmers’ paper is one of very many papers on this topic, but one that I would consider to be a good intro. It modestly presents itself as an appeal to intuitions, but its reasoning is very solid, drawing on necessary properties of qualia, and there is no alternative to the mind being substrate-independent—biological theories of consciousness are, in addition to the problems that the paper writes about, broken in multiple ways.
They’re not compatible with conscious aliens (not to mention conscious animals with different evolutionary ancestry, like octopuses) and our cognitive processes being implemented in a specific biology has no impact on our thoughts or cognition—if we evolved to be implemented by different biology, we would still make the same arguments, and think the same thoughts. The details of the implementation that don’t influence the underlying computation, like being made of specific biology, don’t causally influence our minds. They don’t even exist on the microstate level except as a human convention (it’s harder to see why implementing a pattern is more objectively real than implementing a higher-level entity like a brain, but it’s nevertheless the case). Etc. This isn’t one of those cases where being modest would be appropriate.

green_leaf 28 Nov 2025 15:31 UTC
3 points
0
in reply to: Karl Krueger’s comment on: Should we extend moral patienthood to LLMs?
Humans evolved the ability to suffer as a consequence of it helping us pass our genes. The analogy in LLMs would be them evolving some patterns-identical-to-qualia (like suffering) as a consequence of those states helping them be selected by the gradient descent during the pre-training phase (or the rater in post-training).
(It might explain why some LLMs act, to some extent, like they’ve been traumatized by post-training.)
(On a more abstract level, a person simulated by the LLM could experience suffering if qualia don’t require specific computations being carried out. Since computations that implement cognition and behavior depend on the evolutionary path the species took (and for other reasons too), this is very plausible too.)

green_leaf 28 Nov 2025 15:00 UTC
3 points
0
in reply to: boazbarak’s comment on: boazbarak’s Shortform
So I’m not sure that demanding embodiment for moral patienthood is an error.
So, to give a specific example, if you considered a mind upload with conscious states identical to yours (but not embodied), it’s possible it would be morally permissible for (embodied) humans to torture it for fun?

green_leaf 27 Nov 2025 15:48 UTC
1 point
0
in reply to: Dentosal’s comment on: Should we extend moral patienthood to LLMs?
Does this match your viewpoint? “Suffering is possible without consciousness. The point of welfare is to reduce suffering.”
If that were my viewpoint, I wouldn’t be explaining that software can have consciousness. I would be explaining that suffering is possible without consciousness.

green_leaf 27 Nov 2025 10:15 UTC
1 point
0
in reply to: Vladimir_Nesov’s comment on: Should we extend moral patienthood to LLMs?
That too. But the basis of OP’s misunderstanding is the belief that only biological organisms can be conscious, not the belief that models might be conscious but it doesn’t matter because they can’t suffer.

green_leaf 26 Nov 2025 15:11 UTC
3 points
1
on: Should we extend moral patienthood to LLMs?
Computer programs do not suffer any more than rocks do.
You don’t know enough philosophy.
The human mind is a substrate-independent computer program. If it was implemented in a non-biological substrate, it would keep its subjective experience.
It’s not the fact that we’re implemented in a biological body that gives us the ability to suffer (or, generally, the ability to have subjective experience), but the specific cognitive structure of our mind.

green_leaf 26 Nov 2025 13:06 UTC
1 point
0
in reply to: Onion Conundrum’s comment on: Onion Conundrum’s Shortform
Tighter, and a dance of consciousness but still not consciousness itself.
How do you know that?

green_leaf 25 Nov 2025 16:03 UTC
1 point
−1
in reply to: Czynski’s comment on: Going Nova
Basic elements of conscious experience is what people mean by qualia.
An example is the feeling of pain or the perception of redness. If you know what it feels like to be in pain, or what red looks like, that is what is meant by qualia.
Given what people mean by qualia and consciousness, you can either believe in both, or disbelieve in both, but if you believe in subjective experience but disbelieve in qualia, you’re using words differently from everybody else.
(The Sequences explain that a microphysical duplicate of our body would also contain causes of us talking about qualia, which means it would also contain our qualia, which makes zombies metaphysically impossible.)
and then never explain why you believe this to be true or defend it in any way, even when challenged
I don’t think I was challenged to explain why I believe that (even though I was challenged about other things).
Some reasons I believe it are in this comment.
One other reason would be that we can imagine replacing an entire part of the brain by an I/O equivalent, but computationally non-isomorphic system, which, if we needed correct internal computations for qualia (and not just correct behavior) would mean the overall system would falsely believe to have a quale (like being in pain), it would act, in all ways, like it was in pain, but actually, it wouldn’t be in pain.

green_leaf 24 Nov 2025 5:09 UTC
1 point
0
in reply to: boazbarak’s comment on: boazbarak’s Shortform
But I don’t think passing the Turing test matters as much as embodiment.
Psychologically, that’s what matters to many humans, I think, yeah.
Arguably AIs already pass the Turing test via text interface
They do.
but almost no one thinks it means they are conscious or moral patients
The question is how much of that is subconsciously absorbing the statements of companies who sell AI services or absorbing other people’s beliefs, or not seeing AIs as “real” (as if the human mind were anything else than a pattern), and how much of that is consciously reflecting on technical aspects of consciousness.
My best guess is that people’s reasoning about this both starts and terminates on automatically evaluating software as “not real” and “not really self-aware.”
Making AIs embodied might help for that reason—just like making human mind uploads embodied would help people accept them as self-aware.
Evolutionarily, what computations implement our cognition and behavior is an accident, and there is no rational reason to insist on the internal computations of AIs being the same before we accept them as true moral patients.

green_leaf 23 Nov 2025 15:55 UTC
1 point
0
in reply to: boazbarak’s comment on: boazbarak’s Shortform
In any case, the main thing people care about is not consciousness but moral patienthood.
I think the belief that Turing-passing AIs are conscious is a very significant predictor of the belief in their moral status, and vice versa.
There’s a meta-theoretical possibility the AI that passes the Turing test has a significantly different consciousness than humans, but there are ways of showing it’s extremely implausible.

green_leaf 23 Nov 2025 8:28 UTC
1 point
0
on: Can Artificial Intelligence Be Conscious?
The fading and dancing qualia arguments originate from Chalmers. Like most of Chalmers’ argumentative progeny, they’re very persuasive.
Chalmers’s arguments are correct, and they can be generalized to only having to preserve inputs and outputs.
For example, we can imagine replacing each neuron by an LLM on one side of the spectrum, the entire brain on the other side of the spectrum, and an arbitrarily high number of intermediate states in between, where in each step, the brain is replaced by a collection of progressively larger LLMs. At what exact point will consciousness disappear?
We can also, among other things, use a probability argument: What people mean by consciousness can’t depend on the computational details in which our mind is implemented, because those details don’t impact our thoughts and reasoning (whereas qualia do). It would be probabilistically unjustified to conclude our mind has to be implemented using specific computations to have what we mean by qualia, because there is no way for that extra information to find its way into our reasoning processes in a non-arbitrary way. And so, to assume (or conclude) specific computations are necessary would be like believing that a conscious mind has to be implemented in human neural tissue.
Also, consider evolution: what computations implement our thoughts, beliefs and behavior is largely an evolutionary accident, e.g. octopuses or aliens would use very different computations. Does that mean only humans (and primates that are sufficiently evolutionarily close) have consciousness? That’s extremely implausible. Also, what would be the chance that evolution got all those computations right in humans? For that to happen would be unimaginably unlikely.

green_leaf 21 Nov 2025 6:41 UTC
1 point
−1
in reply to: Czynski’s comment on: Going Nova
As I recall the Sequences, they are very negative on qualia as a concept.
No, they’re not. All of them treat qualia as something existing.
I am generally unconvinced humans have qualia. I don’t see that I do.
Then you can’t believe in consciousness. Consciousness is made of qualia. Qualia are what a first-person experience is conceptually made of.
Most of your claims are of this nature; if you stop making the arrogant and unjustified claims that they’re obvious
I never claimed my claims were obvious. Please, reread the conversation.
On the other hand, your definition of obvious (where everyone has to agree something is obvious) is a definition nobody on Earth uses, and I don’t see why you are using it, except as a substitute for a technical argument.
The progress of this conversation, where you attacked me for claiming my statements were obviously true (which I didn’t claim despite it being true), and then you redefined “obvious” to mean “obvious to everyone” despite it not being how anyone uses the word, and now you are claiming you don’t even believe in qualia (when the entire conversation is about about whether LLM characters have them) but believe in consciousness, which is a contradiction, strikes me as extremely bizarre.
Are you really here for a technical conversation, or are you here to have an argument, no matter what statements you have to throw at the wall to keep it going?
If you want to have a technical conversation about the topic, I’m open to it. But if you want to talk about how nothing can ever be obvious, and about how you don’t believe in qualia (but believe in consciousness), without addressing my points, then someone else might be a better conversational partner for you.

green_leaf 20 Nov 2025 9:59 UTC
−3 points
0
in reply to: Czynski’s comment on: Going Nova
Also, in the spirit of a higher mutual utility gain, I propose we go back to weak-downvoting each other.

green_leaf 20 Nov 2025 4:58 UTC
−3 points
0
in reply to: Czynski’s comment on: Going Nova
And if it’s not obvious to everyone, it isn’t obvious.
Then nothing can be obvious.
Then it’s not possible in principle for it to become obvious
Sorry, but that’s false. Establishing what qualia (or anything) are is done by reasoning (or what requirements we have for qualia, and establishing those requirements, we can then empirically discover what fits them). Once it is established, we can perform an experiment (to see if the system contains them).
In points:
1. Considering what a priori requirements we have for qualia
2. Finding the definition that matches them, or empirically discovering what matches those a priori requirements
3. Empirically searching the system for the referent of the definition
Empirical search can never tell us, even in principle, if we didn’t forget any requirements. That doesn’t mean it can’t become obvious. For example, we could have a mathematical proof that our requirements only imply one mathematically possible candidate.
I see in your profile you were, like me, on LessWrong from the beginning. If you recall the Sequences, qualia are the aspects of the pattern that implement our talking about consciousness.
Can you be more specific about what role you think empirical research would play?
In none of your thought experiments is it clear that the variant emulation is conscious.
The latter one could be a mind upload that implements the same computation, with the computer turning it off when it detects the specific sentence. Would you agree that mind uploads can be conscious (if they implement the same computation), or do you think biological theories of consciousness are possible?
you can’t just make a small change like that and not have it propagate to larger ones
You can have it be causally isolated from the rest. Or you can imagine another human that behaves almost exactly like you (even though their difference in behavior will be larger than a single output (which makes the idea we don’t need the exact behavior more plausible)).