Sounds like he doesn’t believe in the possibility of nonperson predicates.
No, it seems to be a different mistake. He thinks nonperson AIs are possible, but they will model themselves as… roughly, body parts of humans. So they won’t optimize for anything, just obey explicit orders.
Sounds like he doesn’t believe in the possibility of nonperson predicates.
No, it seems to be a different mistake. He thinks nonperson AIs are possible, but they will model themselves as… roughly, body parts of humans. So they won’t optimize for anything, just obey explicit orders.