AI Safety Fundamentals

Illustrating Reinforcement Learning from Human Feedback (RLHF)


Listen Later

This more technical article explains the motivations for a system like RLHF, and adds additional concrete details as to how the RLHF approach is applied to neural networks.

While reading, consider which parts of the technical implementation correspond to the 'values coach' and 'coherence coach' from the previous video.

A podcast by BlueDot Impact.

Learn more on the AI Safety Fundamentals website.

...more
View all episodesView all episodes
Download on the App Store

AI Safety FundamentalsBy BlueDot Impact