I see, so it’s basically assuming that problems factor.
Yeah, in the context of a larger alignment scheme, it’s assuming that in particular the problem of answering the question “How good is the AI’s proposed action?” will factor down into sub-questions of manageable size.
I see, so it’s basically assuming that problems factor.
Yeah, in the context of a larger alignment scheme, it’s assuming that in particular the problem of answering the question “How good is the AI’s proposed action?” will factor down into sub-questions of manageable size.