The "Defeating Dr. Evil with self-locating belief" paper hinges on some fairly difficult to believe assumptions.
It would take a lot more than just a not telling me the brains in the vats are actually seeing what the note says they are seeing, to degree that is indistinguishable from reality.
In other words, it would take a lot for the AI to convince me that it has successfully created copies of me which it will torture, much more than just a propensity for telling the truth.
it would take a lot for the AI to convince me that it has successfully created copies of me which it will torture, much more than just a propensity for telling the truth. Is the fact that it is fully capable (based on, say, readings of it's processing capabilities, it's ability to know the state of your current mind, etc), and the fact that it has no reason NOT to do what it says (no skin of it's back to torture the subjective "you"s, even if you DON'T let it out, it will do so just on principal).
While it's understandable to say that, today, y...
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.