AXRP - the AI X-risk Research Podcast cover image

4 - Risks from Learned Optimization with Evan Hubinger

AXRP - the AI X-risk Research Podcast

00:00

The Most Dangerous Outcomes From Ai

The author of a paper on how to avoid dangerous outgones from artificial intelligence. He says that the majority of essential risks come from inner line, and mostly comes from deceptive line. But he is more worried about inter liner poes than outerline issues.

Transcript
Play full episode

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