Well, that’s the tricky part. But suppose, for the sake of argument, that we have good reason to think that it will. Then we’ll help it. So it’s good for the AI if we have good reason to think this. And it can’t be good reason unless the AI actually does it. So it will.
Well, that’s the tricky part. But suppose, for the sake of argument, that we have good reason to think that it will. Then we’ll help it. So it’s good for the AI if we have good reason to think this. And it can’t be good reason unless the AI actually does it. So it will.