WARNING: Reading this article may commit you to an eternity of suffering and torment.
Slender Man. Smile Dog. Goatse. These are some of the urban legends spawned by the Internet. Yet none is as all-powerful and threatening as Roko’s Basilisk. For Roko’s Basilisk is an evil, godlike form of artificial intelligence, so dangerous that if you see it, or even think about it too hard, you will spend the rest of eternity screaming in its torture chamber. It's like the videotape in The Ring. Even death is no escape, for if you die, Roko’s Basilisk will resurrect you and begin the torture again.
Are you sure you want to keep reading? Because the worst part is that Roko’s Basilisk already exists. Or at least, it already will have existed—which is just as bad.
Roko’s Basilisk exists at the horizon where philosophical thought experiment blurs into urban legend. The Basilisk made its first appearance on the discussion board LessWrong, a gathering point for highly analytical sorts interested in optimizing their thinking, their lives, and the world through mathematics and rationality. LessWrong’s founder, Eliezer Yudkowsky, is a significant figure in techno-futurism; his research institute, the Machine Intelligence Research Institute, which funds and promotes research around the advancement of artificial intelligence, has been boosted and funded by high-profile techies like Peter Thiel and Ray Kurzweil, and Yudkowsky is a prominent contributor to academic discussions of technological ethics and decision theory. What you are about to read may sound strange and even crazy, but some very influential and wealthy scientists and techies believe it.
One day, LessWrong user Roko postulated a thought experiment: What if, in the future, a somewhat malevolent AI were to come about and punish those who did not do its bidding? What if there were a way (and I will explain how) for this AI to punish people today who are not helping it come into existence later? In that case, weren’t the readers of LessWrong right then being given the choice of either helping that evil AI come into existence or being condemned to suffer?
You may be a bit confused, but the founder of LessWrong, Eliezer Yudkowsky, was not. He reacted with horror:
Listen to me very closely, you idiot.
YOU DO NOT THINK IN SUFFICIENT DETAIL ABOUT SUPERINTELLIGENCES CONSIDERING WHETHER OR NOT TO BLACKMAIL YOU. THAT IS THE ONLY POSSIBLE THING WHICH GIVES THEM A MOTIVE TO FOLLOW THROUGH ON THE BLACKMAIL.
You have to be really clever to come up with a genuinely dangerous thought. I am disheartened that people can be clever enough to do that and not clever enough to do the obvious thing and KEEP THEIR IDIOT MOUTHS SHUT about it, because it is much more important to sound intelligent when talking to your friends.
This post was STUPID.
Yudkowsky said that Roko had already given nightmares to several LessWrong users and had brought them to the point of breakdown. Yudkowsky ended up deleting the thread completely, thus assuring that Roko’s Basilisk would become the stuff of legend. It was a thought experiment so dangerous that merely thinking about it was hazardous not only to your mental health, but to your very fate.
Some background is in order. The LessWrong community is concerned with the future of humanity, and in particular with the singularity—the hypothesized future point at which computing power becomes so great that superhuman artificial intelligence becomes possible, as does the capability to simulate human minds, upload minds to computers, and more or less allow a computer to simulate life itself. The term was coined in 1958 in a conversation between mathematical geniuses Stanislaw Ulam and John von Neumann, where von Neumann said, “The ever accelerating progress of technology ... gives the appearance of approaching some essential singularity in the history of the race beyond which human affairs, as we know them, could not continue.” Futurists like science-fiction writer Vernor Vinge and engineer/author Kurzweil popularized the term, and as with many interested in the singularity, they believe that exponential increases in computing power will cause the singularity to happen very soon—within the next 50 years or so. Kurzweil is chugging 150 vitamins a day to stay alive until the singularity, while Yudkowsky and Peter Thiel have enthused about cryonics, the perennial favorite of rich dudes who want to live forever. “If you don't sign up your kids for cryonics then you are a lousy parent,” Yudkowsky writes.
If you believe the singularity is coming and that very powerful AIs are in our future, one obvious question is whether those AIs will be benevolent or malicious. Yudkowsky’s foundation, the Machine Intelligence Research Institute, has the explicit goal of steering the future toward “friendly AI.” For him, and for many LessWrong posters, this issue is of paramount importance, easily trumping the environment and politics. To them, the singularity brings about the machine equivalent of God itself.
Yet this doesn’t explain why Roko’s Basilisk is so horrifying. That requires looking at a critical article of faith in the LessWrong ethos: timeless decision theory. TDT is a guideline for rational action based on game theory, Bayesian probability, and decision theory, with a smattering of parallel universes and quantum mechanics on the side. TDT has its roots in the classic thought experiment of decision theory called Newcomb’s paradox, in which a superintelligent alien presents two boxes to you:
The alien gives you the choice of either taking both boxes, or only taking Box B. If you take both boxes, you’re guaranteed at least $1,000. If you just take Box B, you aren’t guaranteed anything. But the alien has another twist: Its supercomputer, which knows just about everything, made a prediction a week ago as to whether you would take both boxes or just Box B. If the supercomputer predicted you’d take both boxes, then the alien left the second box empty. If the supercomputer predicted you’d just take Box B, then the alien put the $1 million in Box B.