I'm genuinely at a loss how to criticize this approach. If there's any AI worth listening to for longer, and I wouldn't be doing this if I didn't believe there were such AIs, this would seem to be one of the right ones. I'm sure as heck not letting you out of the box, but, y'know, I still haven't actually destroyed you either...
Eh, I'd go with AI DESTROYED on this one. Considering advice given to you by a potentially hostile superintelligence is a fairly risky move.
I wouldn't be doing this if I didn't believe there were such AIs
Whyever not? I thought that it was an imposed condition that you couldn't type AI DESTROYED until the AI had posted one line, and you've publically precommitted to make AI go boom boom anyways.
Eliezer proposed in a comment:
>More difficult version of AI-Box Experiment: Instead of having up to 2 hours, you can lose at any time if the other player types AI DESTROYED. The Gatekeeper player has told their friends that they will type this as soon as the Experiment starts. You can type up to one sentence in your IRC queue and hit return immediately, the other player cannot type anything before the game starts (so you can show at least one sentence up to IRC character limits before they can type AI DESTROYED). Do you think you can win?
This spawned a flurry of ideas on what the AI might say. I think there's a lot more ideas to be mined in that line of thought, and the discussion merits its own thread.
So, give your suggestion - what might an AI might say to save or free itself?
(The AI-box experiment is explained here)
EDIT: one caveat to the discussion: it should go without saying, but you probably shouldn't come out of this thinking, "Well, if we can just avoid X, Y, and Z, we're golden!" This should hopefully be a fun way to get us thinking about the broader issue of superinteligent AI in general. (Credit goes to Elizer, RichardKennaway, and others for the caveat)