LessWrong (30+ Karma) cover image

“AIs can now often do massive easy-to-verify SWE tasks and I’ve updated towards shorter timelines” by ryan_greenblatt

LessWrong (30+ Karma)

00:00

Automating Safety Research: Hands-on Findings

Ryan shares his experiments automating empirical safety projects and the main blockers he encountered.

Play episode from 18:22
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