AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
The Relationship Between Corrigeibility and Utility Preservation
i want to talk about the relationship between attainable utility preservation and cordiability. Andayf people are more interested in this a inner alignment issue, i encourage them to listen to the episode with even hubing er. I think some variance of it and some settings will help a lot with off switch corrigeability. There's an idea that you have n system that like, is amenable to being corrected by you, and like, doesn't stop you from trying to correct it. It seems like a less serious thing to not be able to do at this appointed time, do not know how to do.