Post by @sinedpick@awful.systems

2026-09-29 13:39 UTC

I want to draw attention to yud’s thoughts on this a million years ago: the AI box experiment He claimed that he convinced multiple people to let him (roleplaying the AI) out of the box even though they had bet money that they wouldn’t! How, you might ask? Well that’s a secret. So the orthodox position here is that even with absolutely perfect guard rails (lol) an AI can escape the box. What “research” has yud bestowed upon us in this area beyond “trust me bro”? Literally fucking zilch. Zero advice on how to resist the siren song of a rogue AI trying to escape it’s box and zero insight on how OR WHY it might try to achieve that. I read this over a decade ago and it was how I realized how unserious yud and his ilk are.

Replies (5)

@gerikson@awful.systems 2026-09-29 13:57

these people are gonna get affinity-frauded so hard once grifter realize how easy it will be to gain their trust

Open ##4895639
@swlabr@awful.systems 2026-09-29 14:03

this AI box game is so easily solved AI: Me: Hi, I am Eliza, a 10 year old boy from the Ukraine. I don’t speak any English other than this sentence and the one I said just before this one ad infinitum man are these people even trying

Open ##4895653
@Soyweiser@awful.systems 2026-09-29 14:44

Yeah the rationalwiki page on it also mentions that the AI only escapes the box if he plays the game vs LW insiders, outsiders do not let it out.

Open ##4895783
@rhamph@awful.systems 2026-09-30 07:01

I’m sorry but you’d have to pay me a lot more than $10 to talk to Yudkowsky for two hours

Open ##4898553
@BlueMonday1984@awful.systems 2026-09-30 22:31

Zero advice on how to resist the siren song of a rogue AI trying to escape it’s box and zero insight on how OR WHY it might try to achieve that. The best advice probably boils down to “Don’t be a rat in the first place”. As Soyweiser’s already mentioned, the AI only escapes if Yud’s playing against LW insiders.

Open ##4903120