I guess that under the plausible (?) assumption that at least one enhancement strategy in a not too huge search space reliably produces friendly superintelligences, the problem reduces from creating to recognizing friendliness? Even so I’m not sure that helps.
Interesting.
I guess that under the plausible (?) assumption that at least one enhancement strategy in a not too huge search space reliably produces friendly superintelligences, the problem reduces from creating to recognizing friendliness? Even so I’m not sure that helps.