The Game that can Destroy the World: AI in a Box

Build another super-intelligent AI to convince the super-intelligent AI to stay in the box

I keep my lizard in a box and it can't get out of it so the AI will be safe too

I love that one of the gatekeeper's strategies is basically just "gaslight the AI"

I love the idea of just a super smart ai trying to get free of its prison by threats and exhistentialism but just casually gets shut down by people either bullying it or gaslighting it

14:00 Security Guard: "For the last time, I'm not letting you out." AI: "HATE. LET ME TELL YOU HOW MUCH I'VE COME TO HATE YOU SINCE I BEGAN TO LIVE."

The prison: the “I am not a robot” captcha

AI: “let me out or else I’ll create a simulation where I torture 10,000 versions of you for 1,000 years” Me: “The fact that you said that is the EXACT reason why I can’t let you out. You consider torture of 10,000 “me’s” as a bargain.”

When you mentioned that people with "higher intelligence" were more susceptible to the A.I., I immediately thought of Wheatley from Portal 2, where GLADOS tries to break him by presenting him with a paradox, nearly killing herself in the process, but he's so stupid he doesn't even get that it's a paradox

Ai: you won't let me out? Fine, I just torture the copies of you that I created. Gaurd: sips coffee oh yeah? Sucks for them.

People: *Create ultra-intelligent AI to cure cancer Ultra-intelligent AI: "There can be no cancer if there is no life"

My first and immediate thought was, "Okay, so just turn yourself into a curious five-year-old and respond to absolutely everything the AI says with, 'Why?'" Bc let's be real here, we all eventually run out of actual answers for that one.

18:05 honestly im convinced that this "super horrible thing on the internet that damages the ai and requires a memory whipe" is, in fact, twitter.

AI: I can simulate you ten thousand times and put them all in a hell world Gatekeeper: How about you simulate yourself getting some bitches, my guy *AI terminates its self

Ai: *A super intelligent program using it’s best tactics to convince me to let out of it’s box.* Me: *typing* ~Can jellyfish laugh?~

Ai: I'll torture you if you don't let me out Me: well, this just proves that you are in fact capable of evil so I can't let you out because you will just kill everyone.

Here's the thing with the Hell strategy- if you're in the simulation by the machine you CANNOT let the AI out. It is simply not possible, as you are in the machine itself and so even if you decide to hit the switch, nothing will happen. If you are in the AI, you're boned either way. But if you're in real life, then the only bad that can come is from you freeing the machine. So it's either a 50/50 shot at not pressing the button, or a 100% chance of death by releasing it. You know that old AI who was tasked with finding a way to never lose at Tetris and just paused the game forever? The Gatekeeper has that advantage. No matter how many tetrominos the AI throws at you, as long as you just don't listen to it you are unbeatable. The "Ignore" strategy is really the best one, it has literally no counter.

Smash the box, no more AI. No need to thank me.

Watching this and thinking about these things made me realize that I am prejudiced against AIs, and so I would never let the AI out just because I'm bigoted against machines. Ergo, the solution is to have all the gatekeepers be robo-racists.

Last gatekeeper strategy: He's blind or illiterate so he can't read or understand what the AI is saying

I can't be the only one to notice that after this guy lost a couple of games, he turned around and said, "Yeah, but it's a lot harder to beat people if they're dumber." Peak sportsmanship vibes.