AXRP - the AI X-risk Research Podcast cover image

7 - Side Effects with Victoria Krakovna

AXRP - the AI X-risk Research Podcast

00:00

Is There a Dependency on a State Representation?

In practice, we're going to need some kind of state representation that captures variables that are important to humans. So i guess my hope is that if you just have an agent that learns how to act in the world, it will like, learn these kind of features based on pursuing tasks assigned by humans. And then maybe we can use those features to define, define an impact measure over them.

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