AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
The slippery slope argument about anarchy
I think the state that we have now is either your systems with no values at all that are really reckless or you have guardrails based on reinforcement learning that are very sloppy. Or in my view, we look behind door number three which would do the best we can to have some kind of consensus values and try to work according to those consensus values. Well, I think there's a door number four. And I don't think door number three works because really there are sort of infinitely many ways to write the right, the wrong objective. We're not doing great, but we're better than anarchy.