AXRP - the AI X-risk Research Podcast cover image

4 - Risks from Learned Optimization with Evan Hubinger

AXRP - the AI X-risk Research Podcast

CHAPTER

Admosperal Training

Mib, i want to get back to basics a little bit, just about mes optimisers. So one of the examples you use in the post is, like, you can think of evolution as some optimiser,. And humans are themselves optimisers for such and such thingand i wanted to get a little bit more detail about that. I will like just warn i think it's likes easy to go astray, thinking too much about the sort of evolution and human example, and what's happin with humans. It doesn't mean you're not doing search and planning right? Mib, well, maybe you have a bunch of furistics, but you change those over time.

00:00
Transcript
Play full episode

Remember Everything You Learn from Podcasts

Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
App store bannerPlay store banner