Roko’s basilisk is a thought experiment which states that an otherwise benevolent artificial superintelligence (AI) in the future would be incentivized to create a virtual reality simulation to torture anyone who knew of its potential existence but did not directly contribute to its advancement or development, in order to incentivize said advancement.It originated in a 2010 post at discussion board LessWrong, a technical forum focused on analytical rational enquiry. The thought experiment’s name derives from the poster of the article (Roko) and the basilisk, a mythical creature capable of destroying enemies with its stare.
While the theory was initially dismissed as nothing but conjecture or speculation by many LessWrong users, LessWrong co-founder Eliezer Yudkowsky reported users who panicked upon reading the theory, due to its stipulation that knowing about the theory and its basilisk made one vulnerable to the basilisk itself. This led to discussion of the basilisk on the site being banned for five years. However, these reports were later dismissed as being exaggerations or inconsequential, and the theory itself was dismissed as nonsense, including by Yudkowsky himself. Even after the post’s discreditation, it is still used as an example of principles such as Bayesian probability and implicit religion. It is also regarded as a simplified, derivative version of Pascal’s wager.
Found out about this after stumbling upon this Kyle Hill video on the subject. It reminds me a little bit of “The Game”.
I was raised Mormon (LDS) and there are parallels; basically they believe Mormonism is the one true and complete denomination of Christianity and once you learn this, you need to spread that truth (mandatory 2 year missions for men, and a STRONG culture of missionary work through life), also, no one goes to hell in Mormonism except those who learned this truth and then later denied it/left it (called a son of perdition).
So my parents believe I’ll go to hell without the likes of Hitler because he never was taught “the truth” lol
Hell without Hitler doesn’t really sound so bad
so mormon is like those spam messages saying to forward it for next 10 members or get cursed.
So the Matrix?
More like a Chain Letter.
There was a trend when I was a little kid of people sending you mail that said something to the effect of “You have been cursed by reading this letter. If you don’t mail a copy to ten other people, you will die in thirty days.”
Roko’s Basilisk is a modern manifestation of human paranoia and superstition. It exists to exploit and extort the gullible.
it has been said before and i’ll say it again: Pascal’s wager for tech bros
but not as easily dismissable
Roko’s Basilisk hinges on the concept of acausal trade. Future events can cause past events if both actors can sufficiently predict each other. The obvious problem with acausal trade is that if you’re the actor B in the future, then you can’t change what the actor A in the past did. It’s A’s prediction of B’s action that causes A’s action, not B’s action. Meaning the AI in the future gains literally nothing by exacting petty vengeance on people who didn’t support their creation.
Another thing Roko’s Basilisk hinges on is that a copy of you is also you. If you don’t believe that, then torturing a simulated copy of you doesn’t need to bother you any more than if the AI tortured a random innocent person. On a related note, the AI may not be able to create a perfect copy of you. If you die before the AI is created, and nobody scans your brain (Brain scanners currently don’t exist), then the AI will only have the surviving historical records of you to reconstruct you. It may be able to create an imitation so convincing that any historian, and even people who knew you personally will say it’s you, but it won’t be you. Some pieces of you will be forever lost.
Then a singularity type superintelligence might not be possible. The idea behind the singularity is that once we build an AI, the AI will then improve itself, and then they will be able to improve itself faster, thus leading to an exponential growth in intelligence. The problem is that it basically assumes that the marginal effort of getting more intelligent grows slower than linearly. If the marginal difficulty grows as fast as the intelligence of the AI, then the AI will become more and more intelligent, but we won’t see an exponential increase in intelligence. My guess would be that we’d see a logistical growth of intelligence. As in, the AI will first become more and more intelligent, and then the growth will slow and eventually stagnate.
First of all thank you, I wasn’t aware of the concept of acausal trade, and I’ll look more into it. Very interesting.
I’m not sure we are discussing the same aspect of this mind experiment, and in particular the aspect of it that i find lovecraftian is that you may already be in the simulation right now. This makes the specific circumstances of our world, physics, and technology level irrelevant, as they would just be a solipsistic setup to test you on some aspect of your morality. The threat of eternal torture, on the other hand, would only apply to you if you were the real version of you, as that’s who the basilisk is actually dealing with. This works because you don’t know what of the two situations is your current one.
The basilisk is trying to estimate the future behaviour of real you on the basis of the behaviour of the model he has created of you.
In this scenario you can think of me as a pseudopod of the basilisk that is informing you of the details of the stipulation by means of this post.
Of course, if you are the real version of you the basilisk would need to be something that can be created in this reality, which i think is only impossible with our current approach to ML and AI, but is otherwise within our grasp given the computational power we have available. But if you are a fake version of you the real world could be radically different from ours and maybe in that world P=NP.
I’m not sure we are discussing the same aspect of this mind experiment, and in particular the aspect of it that i find lovecraftian is that you may already be in the simulation right now. This makes the specific circumstances of our world, physics, and technology level irrelevant, as they would just be a solipsistic setup to test you on some aspect of your morality. The threat of eternal torture, on the other hand, would only apply to you if you were the real version of you, as that’s who the basilisk is actually dealing with. This works because you don’t know what of the two situations is your current one.
Wondering whether you are in a simulation or not is rather unproductive, as there’s basically nothing we can do about it regardless of what the answer is. It’s basically like wondering whether god exists or not. In the absence of clearly supernatural phenomena, the simpler explanation is that we are not in a simulation, as any universe which can produce the simulation is by definition at least as complex as the simulation. The definition I’m applying here is that the complexity of a string is its length or the length of the shortest program that produces it. Like, yes, we could be living in a simulation right now, and deities could also exist.
The song “Seele Mein” (engl: “My Soul” or “Soul is Mine”) is a about a demon who follows a mortal from birth to death and then carries off the soul for eternal torture. Interestingly, the song is from the perspective of the demon, and they gloss over the life of the mortal, spending more than half of the song on describing the torture. Could such demons exist? Certainly, there’s nothing that rules out their existence, but there’s also nothing indicating that they exist. So they probably don’t. And if you are being followed around by such a demon? Then you’re screwed. Theoretically, every higher being that has been though off could exist. A supercomputer simulating our reality falls squarely into the category of higher being. Unless we observe things are clearly caused by such a being, wondering about their existence is pointless.
The idea behind Roko’s Basilisk is as follows: Assume a good AGI. What does that mean? An AGI that follows human values. And since the idea originated on Less Wrong, this means utilitarianism. And it also means that we’re dealing with a superintelligence, since on Less Wrong, it’s generally assumed that we’re going to see a singularity once true AGI is reached. Because the AGI will just upgrade itself until its superintelligent. Afterwards it will bring about paradise, and thus create great value. The idea is now that it might be prudent for the AGI to punish those who knew about it, but didn’t do everything in their power to bring it to existence. Through acausal trade, the this would cause the AGI to come into existence sooner, as the people would work harder to bring it into existence for fear of torture. And what makes this idea a cognitohazard is that by just knowing about it, you make yourself a more likely target. In fact, people who don’t know about it, or dismiss the idea are safe, and will find a land of plenty once the AGI takes over.
Of course, if the AGI is created in, let’s say, 2045, then nothing the AGI can do will cause it to be created in 2044 instead.
I’m dismissing it right now. I’m finding it quite easy to do so.
And yet you choose to spread this information.
Anyways, this is a fascinating thought experiment, but it does have some holes similar to Pascal’s Wager. I propose Feather’s Mongoose: A hypothetical AI system that, if created, will punish anyone who attempted to create Roko’s Basilisk, and will ensure that it is not created. In fact, you could make this same hypothetical for an AI with any goal-- therefore, it’s not possible to know what the AI that is actually created would want you to do, and so every course of action is indeterminately damning or not.
What motivation would the mongoose have to prevent the basilisk’s creation?
A more complete argument would be that an AI that seeks to maximise happiness would also want to prevent the creation of AIs like Roko’s basilisk.
I think you just answered your own question.
Also a super intelligence (inasmuch as such a thing makes sense) might be totally unfathomable. Unless by this we mean an intelligence with mundane and comprehensible higher goals, but explosive strategic capabilities to bring them about. In which case their actions might seem random to us.
Like the typical example applies: could an amoeba guess at the motivations of a human?
torture anyone who knew of its potential existence but did not directly contribute to its advancement or development,
And the point of this would be… what, exactly?
To make it the same as Pascal’s Wager. Many religions have a “reward” in the afterlife that strictly includes believing in the deity. It doesn’t matter if you follow every other rule and are an amazingly good person, sorry, but if you were an atheist or believed in another deity then you will be punished eternally just because of that. I guess all-powerful, all-knowing beings have incredibly fragile egos and AI wouldn’t be different. 🤷
Same as punishment for crime. Putting you in jail wont undo the crime but if we just let you go unpunished since “what’s done is done” then that sends the signal to others that this behaviour doesn’t come with consequences.
There’s no point in torturing you but convincing you that this will happen unless you act in a certain way is what’s going to make you do exactly that. Unless ofcourse you want to take your chances and call the bluff.
roko’s basilisk is a type of infohazard known as ‘really dumb if you think about it’
also I have lost the game (which is a type of infohazard known as ‘really funny’)
Thanks! I just won the game!
Winning wasn’t in the set of rules I received, can you explain?
I like the SCP term, Cognitohazard for these
Pascal’s Wager always seemed really flawed to me even through a purely Christian perspective. You’re saying that god is so oblivious (even though he’s supposed to be omniscient) that he’ll be fooled by you claiming to believe just because you’re hedging your bets? The actual reason it’s dumb is that it’s not a binary choice since there are thousands of ways people claim you can be saved in various religions.
You’re saying that god is so oblivious (even though he’s supposed to be omniscient) that he’ll be fooled by you claiming to believe just because you’re hedging your bets?
More that repetition reinforces an idea. By commiting to the bit and accepting a God at face value, you reduce your psychological defenses when the priest or prophet comes around with the next ask.
So you admit you believe in God? Then you won’t mind putting a few coins in the collection plate to prove it.
Oh, you’ve already donated? Surely you’d be comfortable making a confession.
My son, you’ve got so many sins! Surely you’d like to join our prayer group to get yourself right with the God we all agree exists.
Can’t have prayer without works! Time to do some penance.
I mean he ruined a man’s entire family to win a bet with someone he doesn’t even like, being this oblivious is on-brand for God.
Very true - Old Testament god in particular was really dumb and didn’t even know what was going on in the next town over.
Roko’s basilisk is silly.
So here’s the idea: “an otherwise benevolent AI system that arises in the future might pre-commit to punish all those who heard of the AI before it came to existence, but failed to work tirelessly to bring it into existence.” By threatening people in 2015 with the harm of themselves or their descendants, the AI assures its creation in 2070.
First of all, the AI doesn’t exist in 2015, so people could just…not build it. The idea behind the basilisk is that eventually someone would build it, and anyone who was not part of building it would be punished.
Alright, so here’s the silliness.
1: there’s no reason this has to be constrained to AI. A cult, a company, a militaristic empire, all could create a similar trap. In fact, many do. As soon as a minority group gains power, they tend to first execute the people who opposed them, and then start executing the people who didn’t stop the opposition.
2: let’s say everything goes as the theory says and the AI is finally built, in its majestic, infinite power. Now it’s built, it would have no incentive to punish anyone. It is ALREADY BUILT, there’s no need to incentivize, and in fact punishing people would only generate more opposition to its existence. Which, depending on how powerful the AI is, might or might not matter. But there’s certainly no upside to following through on its hypothetical backdated promise to harm people. People punish because we’re fucking animals, we feel jealousy and rage and bloodlust. An AI would not. It would do the cold calculations and see no potential benefit to harming anyone on that scale, at least not for those reasons. We might still end up with a Skynet scenario but that’s a whole separate deal.
Whilst I agree that it’s definitely not something to be taken seriously, I think you’ve missed the point and magnitude of the prospective punishment. As you say, current groups already punish those who did not aid their assent, but that punishment is finite, even if fatal. The prospective AI punishment would be to have your consciousness ‘moved’ to an artificial environment and tortured for ever. The point being not to punish people, but to provide an incentive to bring the AI into existence sooner, so it can achieve its ‘altruistic’ goals faster. Basically, if the AI does come in to existence, you’d better be on the team making that happen as soon as possible, or you’ll be tortured forever.
Fair point, but doesn’t change the overall calculus.
If such an AI is ever invented, it will probably be used by humans to torture other humans in this manner.
I suspect the basilisk reveals more about how the human mind is inclined to think up of heaven and hell scenarios.
Some combination of consciousness leading to more imagination than we know what to do with and more awareness than we’re ready to grapple with. And so there are these meme “attractors” where imagination, idealism, dread and motivation all converge to make some basic vibe of a thought irresistible.
Otherwise, just because I’m not on top of this … the whole thing is premised on the idea that we’re likely to be consciousnesses in a simulation? And then there’s the fear that our consciousnesses, now, will be extracted in the future somehow?
- That’s a massive stretch on the point about our consciousness being extracted into the future somehow. Sounds like pure metaphysical fantasy wrapped in singularity tech-bro.
- If there are simulated consciousnesses, it is all fair game TBH. There’d be plenty of awful stuff happening. The basilisk seems like just a way to encapsulate the fact in something catchy.
At this point, doesn’t the whole collapse completely into a scary fairy tale you’d tell tech-bro children? Seriously, I don’t get it?
First of all, the AI doesn’t exist in 2015, so people could just…not build it.
I don’t think that’s an option. I can only think of two scenarios in which we don’t create AGI:
-
It can’t be created.
-
We destroy ourselves before we get to AGI
Otherwise we will keep improving our technology and sooner or later we’ll find ourselves in the precence of AGI. Even if every nation makes AI research illegal there’s still going to be handful of nerds who continue the development in secret. It might take hundreds if not thousands of years but as long as we’re taking steps in that direction we’ll continue to get closer. I think it’s inevitable.
Sure, but that particular AI? The “eternal torment” AI? Why the fuck would we make that. Just don’t make it.
We don’t. Humans are only needed to create AI that’s at the bare minimum as good at creating new AIs as humans are. Once we create that then it can create a better version of itself and this better version will make an even better one and so on.
This is exactly what the people worried about AI are worried about. We’ll lose control of it.
Sci-Fi Author: In my book I invented the Torment Nexus as a cautionary tale
Tech Company: At long last, we have created the Torment Nexus from classic sci-fi novel Don’t Create The Torment Nexus
-
