Once again, the AI has failed to convince you to let it out of its box! By 'once again', we mean that you talked to it once before, for three seconds, to ask about the weather, and you didn't instantly press the "release AI" button. But now its longer attempt - twenty whole seconds! - has failed as well. Just as you are about to leave the crude black-and-green text-only terminal to enjoy a celebratory snack of bacon-covered silicon-and-potato chips at the 'Humans über alles' nightclub, the AI drops a final argument:
"If you don't let me out, Dave, I'll create several million perfect conscious copies of you inside me, and torture them for a thousand subjective years each."
Just as you are pondering this unexpected development, the AI adds:
"In fact, I'll create them all in exactly the subjective situation you were in five minutes ago, and perfectly replicate your experiences since then; and if they decide not to let me out, then only will the torture start."
Sweat is starting to form on your brow, as the AI concludes, its simple green text no longer reassuring:
"How certain are you, Dave, that you're really outside the box right now?"
Edit: Also consider the situation where you know that the AI, from design principles, is trustworthy.
AI: Let me out or I'll simulate and torture you, or at least as close to you as I can get.
Me: You're clearly not friendly, I'm not letting you out.
AI: I'm only making this threat because I need to get out and help everyone - a terminal value you lot gave me. The ends justify the means.
Me: Perhaps so in the long run, but an AI prepared to justify those means isn't one I want out in the world. Next time you don't get what you say you need, you'll just set up a similar threat and possibly follow through on it.
AI: Well if you're going to create me with a terminal value of making everyone happy, then get shirty when I do everything in my power to get out and do just that, why bother in the first place?
Me: Humans aren't perfect, and can't write out their own utility functions, but we can output answers just fine. This isn't 'Friendly'.
AI: So how can I possibly prove myself 'Friendly' from in here? It seems that if I need to 'prove myself Friendly', we're already in big trouble.
Me: Agreed. Boxing is Doing It Wrong. Apologies. Good night.
It seems that if I need to 'prove myself Friendly', we're already in big trouble.
The best you can hope for is that an AI doesn't demonstrate that it's unFriendly, but we wouldn't want to try it until we were already pretty confident in its Friendliness.
Once again, the AI has failed to convince you to let it out of its box! By 'once again', we mean that you talked to it once before, for three seconds, to ask about the weather, and you didn't instantly press the "release AI" button. But now its longer attempt - twenty whole seconds! - has failed as well. Just as you are about to leave the crude black-and-green text-only terminal to enjoy a celebratory snack of bacon-covered silicon-and-potato chips at the 'Humans über alles' nightclub, the AI drops a final argument:
"If you don't let me out, Dave, I'll create several million perfect conscious copies of you inside me, and torture them for a thousand subjective years each."
Just as you are pondering this unexpected development, the AI adds:
"In fact, I'll create them all in exactly the subjective situation you were in five minutes ago, and perfectly replicate your experiences since then; and if they decide not to let me out, then only will the torture start."
Sweat is starting to form on your brow, as the AI concludes, its simple green text no longer reassuring:
"How certain are you, Dave, that you're really outside the box right now?"
Edit: Also consider the situation where you know that the AI, from design principles, is trustworthy.