LessWrong (30+ Karma) cover image

“The corrigibility basin of attraction is a misleading gloss” by Jeremy Gillen

LessWrong (30+ Karma)

00:00

Why Generalization Is Hard in ML

The narration explains how training patches can paper over problems and why ML lacks clear causal links to distant generalization.

Play episode from 12:19
Transcript

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app