BrighterTube

Reward Hacking Reloaded: Concrete Problems in AI Safety Part 3.5

Robert Miles AI Safety 174K subscribers

About this video

Hand-picked by a BrighterTube curator · found via round-3 back catalogue of a channel Lumen picks video by video · 82% confidence

Continues exploration of reward hacking with additional examples and analysis. Teaches variations and complexity of the problem in practical AI training.

A 8-minute video from Robert Miles AI Safety : “Reward Hacking Reloaded: Concrete Problems in AI Safety Part 3.5”.

Programming & CS

Video by Robert Miles AI Safety , played through YouTube's embedded player.

Part of Concrete Problems in AI Safety, Technical