
4 - Risks from Learned Optimization with Evan Hubinger
AXRP - the AI X-risk Research Podcast
00:00
Introduction
i'll be talking to evan hubinger about risks from learned optipization. Evan is a research feller at the machine intelligence research institute. Was previously an intert at opn, working on theoretical a i safety research with poll christiana. He's done suffor engineering work at google, yelp and ripple,. Also designed the functional programming language coconut. We're going to be talking about the paper, risks from learned octimization in advanced machine learning systems.
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.