Can we give Alice good reasons to self-modify to become a friendly AI?
A clip-tiler is friendly by its own standards, so the real question is “Can we prevent AI-ice from appearing friendly to herself and humanity without actually being one, once she is smarter than a human?”, and now we are back to the AI-in-a-box problem.
A clip-tiler is friendly by its own standards, so the real question is “Can we prevent AI-ice from appearing friendly to herself and humanity without actually being one, once she is smarter than a human?”, and now we are back to the AI-in-a-box problem.