Media Summary: This is a clip from our recent podcast release with Past analyses of reinforcement learning from human feedback (RLHF) assume that the human fully observes the environment.
Why Ais Deceive You Marc - Detailed Analysis & Overview
This is a clip from our recent podcast release with Past analyses of reinforcement learning from human feedback (RLHF) assume that the human fully observes the environment.
![Scott Emmons — When Your AIs Deceive You [TAIS 2024]](https://i.ytimg.com/vi/LP2d4EAGCdc/mqdefault.jpg)
