AXRP - the AI X-risk Research Podcast cover image

10 - AI's Future and Impacts with Katja Grace

AXRP - the AI X-risk Research Podcast

00:00

Agents Are Like, Really Good for Achieving Goals

The current way we build systems is implicitly getting the best thing in a large class of models, like achieving some task. Do you think there is a particular reason to think that agents are like the best things for achieving certain goals? Yes. So, yes, t it eams to be the one inside. You. The broader class being something like, i'm just sort of confused about, like, he agency and how it works,. What these kind of partial agency things are like, and how easy it is to do these different things.

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