What Can We Do About Reward Hacking?: Concrete Problems in AI Safety Part 4
118,586 views
About this video
Hand-picked by a BrighterTube curator · found via round-3 back catalogue of a channel Lumen picks video by videoAddresses reward hacking as a concrete safety problem in AI. Teaches mitigation approaches from safety research literature.
Video by Robert Miles AI Safety , played through YouTube's embedded player.
Part of Concrete Problems in AI Safety, Technical