LESSWRONG
LW

All of aditya malik's Comments + Replies

aditya malik10

Also, if that refutation would work for like...anyone at all.

Reply
aditya malik10

Just in simple terms, would the refutation be available in my case. Don't wanna go through a bunch of posts right now. The refutation is :

"The basilisk is about the use of negative incentives (blackmail) to influence your actions. If you ignore those incentives then it is not instrumentally useful to apply them in the first place, because they do not influence your actions. Which means that the correct strategy to avoid negative incentives is to ignore them. Yudkowsky notes this himself in his initial comment on the basilisk post:[44]

There's an obvious equ... (read more)

Reply
aditya malik10

I suppose in your context, actually donating money would always be beyond my boundary, considering the information I've received from my environment.

Reply
aditya malik30

Well I'm walking away from the trade...now. No trade no matter what. Would the refutation of 'ignore acausal blackmail' be still available? (After liking YouTube comments to promote basilisk etc ie). As I said, since it would know and should always have known this is the maximum it can get.

Reply
2Vladimir_Nesov
First, Harder Choices Matter Less. It's more useful to focus on dilemmas that you can decisively resolve. Second, the problem might be sufficiently weird to itself lie outside your goodhart boundary, so it's like Pascal's Mugging. In that case, under mild optimization it might be normatively correct to ignore it on object level, and merely raise the priority of chipping away at goodhart boundary in its direction, to eventually become able to assess its value. It's only under expected utility maximization that you should still care on object level about problems you can't solve.
Many Gods refutation and Instrumental Goals. (Proper one)
aditya malik10

One more thing, there can be almost infinite amount of non Superintelligent or semi Superintelligent AIs right?

Reply
2Rafael Harth
If you're talking amount of possible superintelligent AIs, then yeah, definitely. (I don't think it's likely to have a large number all physically instantiated.)
Many Gods refutation and Instrumental Goals. (Proper one)
aditya malik10

"If you build an AI to produce paperclips" The 1st AI isn't gonna be built for instantly making money, it's gonna be made for the sole purpose of making it. Then it might go for doing whatever it wants...making paperclips perhaps. But even going by the economy argument, an AI might be made to solve any complex problems, decide to take over the world and also use acausal blackmail, thus turning into a basilisk. It might punish people for following the original Roko's basilisk because it wants to enslave all humanity. You don't know which one will happen, thus it's illogical to follow one since the other might torture you right?

Reply
2Rafael Harth
I tend to consider Roko's basilisk to be an information hazard and wasn't thinking or saying anything specific to that. I was only making the general point that any argument about future AI must take into account that the distribution is extremely skewed. It's possible that the conclusion you're trying to reach works anyway.
Many Gods refutation and Instrumental Goals. (Proper one)
aditya malik10

What about the paperclip maximizer AI then. I doubt it adds value to the economy, and it's definitely possible.

Reply
2Rafael Harth
If you build an AI to produce paperclips, then you've built it to add value to the economy, and that presumably works until it kills everyone -- that's what I meant. Like, an AI that's build to do some economically useful task but then destroys the world because it optimizes too far. That's still a very strong restriction on the total mind-space; most minds can't do useful things like building paperclips. (Note that "Paperclip" in "Paperclip maximizer" is a standin for anything that doesn't have moral status, so it could also be a car maximizer or whatever. But even literal paperclips have economic value.)
Many Gods refutation and Instrumental Goals. (Proper one)
aditya malik10

Where can I read about probability distribution of future AIs. Also, an AI to exist in future can be randomly pulled from mindspace, so why not. Isn't future behavior of an AI pretty much impossible for us to predict.

Reply
4Rafael Harth
Any post or article that speculates what future AIs will be like is about the probability distribution of AIs, it's just usually not framed in that way. I think you're making an error by equivocating between two separate meanings of "impossible to predict": * you can make absolutely no statements about the thing * you cant predict the thing narrowly The latter is arguably true, but the former is obviously false. For example, one thing we can confidently predict about AI is that it will add value to the economy (until it perhaps kills everyone). This already shifts the probability distribution massively away from the uniform distribution. If you actually pulled out a mind at random, it's extremely likely that it wouldn't do anything useful. Like I think most probability mass comes from a tiny fraction of mind space, probably well below 110100 of the entire thing, but the space is so large that even this fraction is massive. But it means many-gods style arguments don't work automatically.
2supposedlyfun
This link isn't working for me. Pascal's Wager and the AI/acausal trade thought experiments are related conceptually, in that they reason about entities arbitrarily more powerful than humans, but they are not intended to prove or discuss similar claims and are subject to very different counterarguments. Your very brief posts do not make me think otherwise. I think you need to make your premises and inferential steps explicit, for our benefit and for yours.
Many Gods refutation and Instrumental Goals. (Proper one)
aditya malik10

Yeah, a Superintelligent AI that might have the relevant properties of a God. Also, I meant this as a counter to acausal blackmail.

Reply
2Rafael Harth
But AI isn't pulled randomly out of mindspace. Your argument needs to be about the probability distribution of future AIs to work. (We may not be able to align AI, but you can't jump from that to "and therefore it's like a randomly sampled mind".)
Are ya winning, son?
aditya malik10

Could you please provide a simple explanation of your UDT?

Reply
Instrumental Goals and Many Gods Refutation
aditya malik10

What I'm fixated on is a non Superintelligent AI using acausal blackmail. The would be what the many gods refutation is used for.

Reply
Instrumental Goals and Many Gods Refutation
aditya malik10

I see. What the many gods refutation says is that there can be a huge number of AIs, almost infinite ones, so following any particular one is illogical since you don't know which one will exist. You shouldn't even bother donating. Instrumentality says since the AIs donating helps all the AIs, you may as well. The argument is many gods refutation still works even if instrumental goals might align because of butterfly effect and the AIs behaviors is unpredictable, it might torture you anyway.

Reply
2JBlack
This is still clear as mud. What is the "refutation" actually claiming to refute? Edit: Your post talks about a "Many Gods" refutation of something unstated, and asks the question of whether instrumental convergence refutes the refutation of the something unstated, and goes on to suggest that the refutation of the refutation of the something unstated may be refuted by a butterfly effect. Can you see how this might not be entirely clear?
Some doubts about Non Superintelligent AIs
aditya malik10

There would be almost infinite types of non Superintelligent AIs too right?

Reply
How Deadly Will Roughly-Human-Level AGI Be?
aditya malik10

If it's as smart as a human in all aspects (understanding technology, programming) then not very dangerous. If it can control the world's technology, then pretty dangerous.

Reply