Is AI Safety a Pascal's Mugging?

388,382 views

About this video

Hand-picked by a BrighterTube curator · found via HackerTube (Karpathy's dataset of videos Hacker News recommends · 84% confidence

Is AI safety a Pascal's mugging? Robert Miles explains expected-value reasoning and argues the case for safety work does not rest on tiny probabilities of huge payoffs; a careful lesson in decision theory as much as AI safety.

Robert Miles explains Pascal's mugging and why AI safety is not that kind of argument, with the probabilities spelled out.

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

Part of Best Of