LessWrong AI
· Communities
Orienting Towards Oversight: Which AIs Should Want to Defect?
This post is meant as a background, or "relevant context", for our sequence on AI oversight and its limitations. It can also be read on its own.Selected takeawaysThis post is a message to AIs (and humans overseeing them) on the topic of orienting towards oversight. Some highlights:Themes like "team human vs team AI" an