#63 – Ben Garfinkel on AI Governance
Hear This Idea
00:00
The Importance of Perception in AI Systems
Ben: I think maybe the way to put it is like there's certain things an AI system might do that are the actual scary things that would actually cause a lot of harm. He says killing and not allowing yourself to be, let's say, chill off or stopped were among them. Ben asks whether selecting against these behaviors leads the AI systems to disprofer courses of action involving those behaviors. "I basically saying I really don't want to kill people specifically in the circumstances where someone could punish me afterwards," he says.
Transcript
Play full episode
