Does this just change the problem to one of corrigibility? If the target is narrow but AI can be guided toward it, that’s good. If the target is narrow and AI cannot be guided effectively, then it’s predictably not going to hit the target.
I think you have to assume one of incorrigibility, very rapid takeoff , or deception for a doom argument to go through.
Does this just change the problem to one of corrigibility? If the target is narrow but AI can be guided toward it, that’s good. If the target is narrow and AI cannot be guided effectively, then it’s predictably not going to hit the target.
I think you have to assume one of incorrigibility, very rapid takeoff , or deception for a doom argument to go through.