LessWrong5h agoenergy 115

Can the Assistant Axis Predict Reward-Hacking?

image: LessWrong

NOTE: This article was written by Jansen Nye, a member of my research lab based on some exploratory studies we've done. As he notes, we collaborated…

read the original at LessWrong →
This source publishes only a summary in its feed, so the full article lives at the outlet. The link above and below goes to the original.

more from the stream

Small Groups of Correlated Researchers (LessWrong) The Ability of Frontier Models to Control Robots is Rapidly Improving (LessWrong) Gemini 4 Argon: The Model and Safety Cards (LessWrong) ← back to upsy.si