AXRP - the AI X-risk Research Podcast cover image

2 - Learning Human Biases with Rohin Shah

AXRP - the AI X-risk Research Podcast

00:00

Ia, A, Is This a Domain Independent Corp?

It's still making some simplifying assumptions that are like, not actually true. But it really does seem to incentivise quite a lot of things that i would characterize as helpfulness skills or something like it incentivises preference learning. It centivizes, you know, asking questions when being insure in the first place. So, i don't know, it feels like this is a thing that we can get agents to do in a relatively domain independent way and if we succeeded at it, then there would not be existential risk any more.

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