Actually, why is it that when the Lobian obstacle is discussed that it seem to always be in reference to an AI trying to determine if a successor AI is safe, and not an AI trying to determine whether or not it, itself, is safe?
Because we’re talking about criteria for action, not epistemology. The heart of the Lobstacle problem is that straightforward ways of evaluating the consequences of actions start to break down when those consequences involve the outcomes of deductive processes equal to or greater than the one brought to bear.
Actually, why is it that when the Lobian obstacle is discussed that it seem to always be in reference to an AI trying to determine if a successor AI is safe, and not an AI trying to determine whether or not it, itself, is safe?
Because we’re talking about criteria for action, not epistemology. The heart of the Lobstacle problem is that straightforward ways of evaluating the consequences of actions start to break down when those consequences involve the outcomes of deductive processes equal to or greater than the one brought to bear.