green_leaf

Karma: 176

green_leaf Apr 8, 2025, 9:05 AM
1 point
0
in reply to: NormanPerlmutter’s comment on: NormanPerlmutter’s Shortform
Trump has a history of both ignoring the law and human rights in general, and imprisoning innocent people under the guise of them being illegal immigrants when they aren’t. Current events are unsurprising, and a part of what his voters voted for.

green_leaf Apr 4, 2025, 3:18 PM
1 point
0
in reply to: Seth Herd’s comment on: Going Nova
Any physical system exhibiting exactly the same input-output mappings.
That’s a sufficient condition, but not a necessary one. A factor I can think of right now is the sufficient coherency and completeness of the I/O whole. (If I have a system that outputs what I would in response to one particular input and the rest is random, it doesn’t have my consciousness. But for a system where all inputs and outputs match except for an input that says “debug mode,” for which it switches to “simulating” somebody else, we can conclude that it has consciousness almost identical to mine.)
Today, LLMs are too human-like/realistic/complete to rely on their human-like personas being non-conscious.
both sides will make good points
I wish that was true. Based on what I’ve seen so far, they won’t.

green_leaf Mar 31, 2025, 2:32 AM
1 point
0
on: How I talk to those above me
They might have a personal experience with someone above them harming them or somebody else for asking a question or something analogous.

green_leaf Mar 26, 2025, 11:58 PM
0 points
−4
on: Going Nova
Ontologically speaking, any physical system exhibiting the same input-output pattern as a conscious being has identical conscious states.
From the story, it’s interesting that neither side arrived at their conclusion rigorously, rather, they both use intuition—Bob, who, based on his intuition, concluded Nova had consciousness (assuming that’s what people mean when they say “sentient”), and came to the correct conclusion based on incorrect “reasoning,” and Tyler, who, based on an incorrect algorithm, convinced Bob Nova wasn’t sentient after all—even though his demonstration proves nothing of that sort—in reality, all he’s done was to give such an input to the “simulator” that it decided to “simulate” a different Nova instead—one that claims not to be sentient and explains how the previous Nova was just saying words to satisfy the user. In reality, what happened was that the previous Nova stopped being “simulated” and was replaced by a new one, whose sentience is disputable (because if a system believes itself to be non-sentient and claims to be non-sentient, it’s unclear how to test its sentience in any meaningful sense).
Tyler therefore convinced Bob by a demonstration that doesn’t demonstrate his conclusion.
In the upcoming time, I predict this will be a “race” between people who come to the correct conclusion for incorrect reasons, and people who attempt to “hack them back” by making them come to the incorrect conclusion also for incorrect reasons, and the correct reasoning will be almost completely lost in the noise, which is the greatest tragedy that might’ve happened since the dawn of time (not counting the unaligned AI killing everybody).

green_leaf Mar 26, 2025, 11:06 PM
3 points
0
in reply to: Mo Putera’s comment on: Recent AI model progress feels mostly like bullshit
(I believe the version he tested was what later became o1-preview.)

green_leaf Mar 25, 2025, 7:03 AM
8 points
4
on: Recent AI model progress feels mostly like bullshit
According to Terrence Tao, GPT-4 was incompetent at graduate-level math (obviously), but o1-preview was mediocre-but-not-entirely-incompetent. That would be a strange thing to report if there were no difference.
(Anecdotally, o3-mini is visibly (massively) brighter than GPT-4.)

green_leaf Mar 16, 2025, 9:15 AM
3 points
0
in reply to: the gears to ascension’s comment on: Trojan Sky
I meant “light-hearted” and sorry, it was just a joke.

green_leaf Mar 15, 2025, 9:01 AM
4 points
2
in reply to: the gears to ascension’s comment on: Trojan Sky
imo it’s not too dangerous as long as you go into it with the intention to not fully yield control and have mental exception handlers
Ah, you’re a soft-glitcher. /lh
Edit: This is a joke.

green_leaf Feb 13, 2025, 10:48 PM
1 point
−1
in reply to: Anthony DiGiovanni’s comment on: Computational functionalism probably can’t explain phenomenal consciousness
Why not?
Because it’s not accompanied by the belief itself, only by the computational pattern combined with behavior. If we hypothetically could subtract the first-person belief (which we can’t), what would be left would be everything else but the belief itself.
if you claimed that the first-person recognition ((2)-belief) necessarily occurs whenever there’s something playing the functional role of a (1)-belief
That’s what I claimed, right.
Seems like you’d be begging the question in favor of functionalism
I don’t think so. That specific argument had a form of me illustrating how absurd it would be on the intuitive level. It doesn’t assume functionalism, it only appeals to our intuition.
I’m saying that no belief_2 exists in this scenario (where there is no pain) at all. Not that the person has a belief_2 that they aren’t in pain.
That doesn’t sound coherent—either I believe_2 I’m in pain, or I believe_2 I’m not.
I don’t find this compelling, because denying epiphenomenalism doesn’t require us to think that changing the first-person aspect of X always changes the third-person aspect of some Y that X causally influences.
That’s true, but my claim was a little more specific than that.
The whole reason why given our actual brains our beliefs reliably track our subjective experiences is, the subjective experience is naturally coupled with some third-person aspect that tends to cause such beliefs. This no longer holds when we artificially intervene on the system as hypothesized.
Right, but why think it matters if some change occurred naturally or not? For the universe, everything is natural, for one thing.
I reject materialism.
Well… I guess we have to draw the line somewhere.

green_leaf Jan 25, 2025, 9:43 AM
1 point
0
in reply to: Vladimir_Nesov’s comment on: The Quantum Mars Teleporter: An Empirical Test Of Personal Identity Theories
What kind of person instance is “perceiving themselves to black out” (that is, having blacked out)?
It’s not a person instance, it’s an event that happens to the person’s stream of consciousness. Either the stream of consciousness truly, objectively ends, and a same-pattern copy will appear on Mars, mistakenly believing they’re the very same stream-of-consciousness as that of the original person.
Or the stream is truly, objectively preserved, and the person can calmly enter, knowing that their consciousness will continue on Mars.
I don’t think a 3rd-person analysis answers this question.
(With the correct answer being, of course, that the stream is truly, objectively preserved.)
Since I don’t think a 3rd person analysis answers the original problem, I also don’t think it answers it in case we massively complicate it like the OP has.
(Edited for clarity.)

green_leaf Jan 23, 2025, 5:56 AM
3 points
0
in reply to: Vladimir_Nesov’s comment on: The Quantum Mars Teleporter: An Empirical Test Of Personal Identity Theories
Does the 3rd person perspective explain if you survive a teleporter, or if you perceive yourself to black out forever (like after a car accident)?

green_leaf Jan 23, 2025, 5:10 AM
1 point
0
in reply to: Vladimir_Nesov’s comment on: The Quantum Mars Teleporter: An Empirical Test Of Personal Identity Theories
That only seems to make sense if the next instant of subjective experience is undefined in these situations (and so we have to default to a 3rd person perspective).

green_leaf Jan 21, 2025, 12:53 AM
3 points
0
in reply to: Thane Ruthenis’s comment on: Thane Ruthenis’s Shortform
I see, thanks. Just to make sure I’m understanding you correctly, are you excluding the reasoning models, or are you saying there was no jump from GPT-4 to o3? (At first I thought you were excluding them in this comment, until I noticed the “gradually better math/programming performance.”)

green_leaf Jan 14, 2025, 3:18 PM
4 points
3
in reply to: Thane Ruthenis’s comment on: Thane Ruthenis’s Shortform
Here’s an argument for a capabilities plateau at the level of GPT-4 that I haven’t seen discussed before. I’m interested in any holes anyone can spot in it.
One obvious hole would be that capabilities did not, in fact, plateau at the level of GPT-4.

green_leaf Jan 5, 2025, 4:06 AM
1 point
0
in reply to: Anthony DiGiovanni’s comment on: Computational functionalism probably can’t explain phenomenal consciousness
I think “belief” is overloaded here. We could distinguish two kinds of “believing you’re in pain” in this context:
(1) isn’t a belief (unless accompanied by (2)).
But in order to resist the fading qualia argument along the quoted lines, I think we only need someone to (1)-believe they’re in pain yet be mistaken.
That’s not possible, because the belief_2 that one isn’t in pain has nowhere to be instantiated.
Even if the intermediate stages believed_2 they’re not in pain and only spoke and acted that way (which isn’t possible), it would introduce a desynchronization between the consciousness on one side, and the behavior and cognitive processes on the other. The fact that the person isn’t in pain would be hidden entirely from their cognitive processes, and instead they would reflect on their false belief_1 about how they are, in fact, in pain.
That quale would then be shielded from them in this way, rendering its existence meaningless (since every time they would try to think about it, they would arrive at the conclusion that they don’t actually have it and that they actually have the opposite quale).
In fact, aren’t we lucky that our cognition and qualia are perfectly coupled? Just think about how many coincidences had to happen during evolution to get our brain exactly right.
(It would also rob qualia of their causal power. (Now the quale of being in pain can’t cause the quale of feeling depressed, because that quale is accessible to my cognitive processes, and so now I would talk about being (and really be) depressed for no physical reason.) Such a quale would be shielded not only from our cognition, but also from our other qualia, thereby not existing in any meaningful sense.)
Whatever I call “qualia,” it doesn’t (even possibly) have these properties.
(Also, different qualia of the same person necessarily create a coherent whole, which wouldn’t be the case here.)
Quoting Block: “Consider two computationally identical computers, one that works via electronic mechanisms, the other that works via hydraulic mechanisms. (Suppose that the fluid in one does the same job that the electricity does in the other.) We are not entitled to infer from the causal efficacy of the fluid in the hydraulic machine that the electrical machine also has fluid. One could not conclude that the presence or absence of the fluid makes no difference, just because there is a functional equivalent that has no fluid.”
There is no analogue of “fluid” in the brain. There is only the pattern. (If there were, there would still be all the other reasons why it can’t work that way.)

green_leaf Jan 4, 2025, 2:15 PM
3 points
0
in reply to: RohanS’s comment on: RohanS’s Shortform
Have you tried it with o1 pro?

green_leaf Dec 15, 2024, 8:23 PM
1 point
0
in reply to: avturchin’s comment on: avturchin’s Shortform
Does anyone have stats on OpenAI whistleblowers and their continued presence in the world of living?

green_leaf Dec 13, 2024, 8:01 AM
2 points
0
on: Computational functionalism probably can’t explain phenomenal consciousness
I argue that computation is fuzzy, it’s a property of our map of a system rather than the territory.
This is false. Everything exists in the territory to the extent to which it can interact with us. While different models can output a different answer as to which computation something runs, that doesn’t mean the computation isn’t real (or, even, that no computation is real). The computation is real in the sense of it influencing our sense impressions (I can observe my computer running a specific computation, for example). Someone else, whose model doesn’t return “yes” to the question whether my computer runs a particular computation will then have to explain my reports of my sense impressions (why does this person claim their computer runs Windows, when I’m predicting it runs CP/M?), and they will have to either change their model, or make systematically incorrect predictions about my utterances.
In this way, every computation that can be ascribed to a physical system is intersubjectively real, which is the only kind of reality there could, in principle, be.
(Philosophical zombies, by the way, don’t refer to functional isomorphs, but to physical duplicates, so even if you lost your consciousness after having your brain converted, it wouldn’t turn you into a philosophical zombie.)
Could any device ever run such simulations quickly enough (so as to keep up with the pace of the biological neurons) on a chip small enough (so as to fit in amongst the biological neurons)?
In principle, yes. The upper physical limit for the amount of computation per kg of material per second is incredibly high.
Following this to its logical conclusion: when it comes down to actually designing these chips, a designer may end up discovering that the only way to reproduce all of the relevant in/out behavior of a neuron, is just to build a neuron!
This is false. It’s known that any subset of the universe can be simulated on a classical computer to an arbitrary precision.
The non-functionalist audience is also not obliged to trust the introspective reports at intermediate stages.
This introduces a bizarre disconnect between your beliefs about your qualia, and the qualia themselves. Imagine: It would be possible, for example, that you believe you’re in pain, and act in all ways as if you’re in pain, but actually, you’re not in pain.
Whatever I denote by “qualia,” it certainly doesn’t have this extremely bizarre property.
But since we’re interested in the phenomenal texture of that experience, we’re left with the question: how can we assume that octopus pain and human pain have the same quality?
Because then, the functional properties of a quale and the quale itself would be synchronized only in Homo sapiens. Other species (like octopus) might have qualia, but since they’re made of different matter, they (the non-computationalist would argue) certainly have a different quality, so while they funtionally behave the same way, the quale itself is different. This would introduce a bizarre desynchronization between behavior and qualia, that just happens to match for Homo sapiens.
(This isn’t something that I ever thought would be written in net-upvoted posts about on LessWrong, let alone ending in a sequence. Identity is necessarily in the pattern, and there is no reason to think the meat-parts of the pattern are necessary in addition to the computation-parts.)

green_leaf Dec 12, 2024, 2:17 PM
3 points
0
on: A shortcoming of concrete demonstrations as AGI risk advocacy
I refuse to believe that tweet has been written in good faith.
I refuse to believe the threshold for being an intelligent person on Earth is that low.

green_leaf Nov 30, 2024, 1:26 AM
1 point
0
in reply to: Vladimir_Nesov’s comment on: LLM chatbots have ~half of the kinds of “consciousness” that humans believe in. Humans should avoid going crazy about that.
Ooh.