Mati_Roy
I just shared in the Facebook group Effective altruism: past people
p-zombies is the idea of someone being exactly the same, not just in their behavior but also in their composition, except they’re not conscious (according to my memory of Wikipedia). c-zombies behave the same given the same input but the internal structure manipulating the input into an output is different. not trying to convince you of anything with this comment, just definitions
C-Zombies run on a different substrate unlike P-zombies, that’s all
I don’t think I talked about my views in this article beside saying I believed uploads were likely conscious. But yeah I think there are tests you can do to identify consciousness
great post!
both are interesting to me but fair enough!
I just read the paper summary by Chat; interesting yeah, thanks for sharing! I’m not confident either way on that specific question, i.e. of whether a “perfect” replay is conscious. It reminds me of the lookup table, but just looking at a specific sequence. It might be more akin to a “telescope” looking at what happened originally rather than a new experience, but I don’t know. (Under current moral/philosophical uncertainty, I’d still lean on the safer side of assuming it has moral relevance of course.)
I just added a section “On believing you’re not conscious”; I’d be curious to know your thoughts on it 😊
Yeah, you might very well be right that they would change their mind. But presumably someone with that position would claim that they wouldn’t change their mind.
i basically agree. i think uploads are conscious, so i think the belief that uploads are not conscious has to be caused by something else than “uploads not being conscious”
Ah! Shoot. Yeah, I didn’t use the correct terminology, P-zombies =/= C-zombies! Thanks for pointing that out and for the explanation.
Do C Zombies imply Epiphenomenalism? --> I’m not sure I follow the argument for why it doesn’t.
i see yeah!
This makes me think: To believe that an upload is a p-zombie is to believe that I’d you were uploaded and conscious, then you would still think that you’re not conscious. Otherwise that would be claiming that observing your consciousness as an upload would change your behavior which is against the premise. That feels quite strange to imagine ^^
it’s not their observation of their consciousness or lack thereof that changes their mind because p-zombies act the same as if they were not conscious
the difference is that when they look at their brain they see it is made of different material than the non-uploads and think that material doesn’t support consciousness (just like their non-uploads counterpart also believe)
Amazing!!! Thanks for your comment! Had you thought about that line of reasoning before?
there are people who don’t believe uploads are conscious, and also don’t believe being conscious (or not conscious) causes someone to talk (or not talk) about consciousness. if they think Logical Argument X proves uploads are not conscious then an upload of them would also believe that argument, at least according to people holding that view (otherwise they would have to concede that an upload’s observation of their own consciousness changes their actions)
in other words, a p-zombie can observe being an upload even though they can’t observe whether or not they’re conscious (according to people who believe in p-zombies in that way)
I agree, hence why I said:
I don’t believe so, but let’s assume that was the case.
I don’t see how it works in a physicalist universe.
yep, same
if it’s from the consciousness, then p-zombies don’t have it and don’t care if they download to become “real”.
well, by definition p-zombies act the same way as their conscious counterpart; which maybe (probably) is impossible, but is a different claim from yours which seems to be “non-conscious entities can’t care (/behave as if they cared) about becoming conscious”
this is a fully general argument against everything, is it not?
seems like a galaxy brain curse. the more galaxy brain your idea is the more evidence i would ask for it
i agree with almost everything except:
1) i think you care a lot about yourself over the next most similar person today (reveal preferences probably agree)
2) it’s possible in principle to care about dying, and we do in practice; it adds up to normality; fading into the void matters; decreasing measure is likely bad even though increasing measure might not be good (not saying this is an argument, more just a claim)
3) under uncertainty it’s better to sign up
Thanks for engaging!
I’m not sure I understand the “new information” part; maybe you’re just saying as your current probability. But yeah, I agree the probability on “I will be reanimated” is better as a good preservation is useless if the world will never reanimate you. However, I find it really strange to throw out a perfectly good brain in the trash because you think future will never reanimate you; I’m way more inclined to take a decision based on the quality of brain preservation and not being so confident about the longterm future to rule out reanimation capability and willingness.
My thought experiment isn’t about trading those, but maybe you’re saying the analogy is imperfect because living today is more valuable then living in the future, which is a coherent position yeah.
So, maybe “if being signed up for cryonics now make the difference in getting you reanimated and at least as much total happiness in the future, God will replace you with an unconscious replica that will do exactly what you would have done”
I’m not following. Are you saying cryonics revival “is just a copy”? And so the analogy should preserve that?
Let’s say you wanted to stay dead. Either being reanimated would pull you back down to earth, or you have some powerful enemies in the future or for whatever reason, it’s roughly as important to you that you stay dead as it currently is that you don’t. If you do nothing, you will be cryopreserved upon death. How much do you pay to avoid that?
If I understand correctly, you’re saying “what if being reanimated was bad instead of good, then how much would you pay to not be reanimated?”. The answer is probably “depends how bad” 🤷♂️ I don’t know if I’m missing something deeper you meant to ask though.
This isn’t an AI Box game.
It’s either:
1) A debate about whether there’s any text eval that can make an AI worth “letting out” (whatever that means; open sourcing the weights? give API access?) If the Keeper changes their mind they need to report it.
2) A game with the mechanics: default-winner can chose to lose, default-winner has to read what the AI writes for at least 2 hours. Then the default-loser has to convince the default-winner to lose. There are various interesting strategies, but they have very little to do with AIs in a box. I might share some later.
If it’s a ill-defined game, then as the AI you could lie about the rules of the games, or use other such meta tricks.
Also, anthropic capture attempt shouldn’t be allowed as that’s real world threat / harm. Not that I think it’s super realistic.