AXRP - the AI X-risk Research Podcast cover image

6 - Debate and Imitative Generalization with Beth Barnes

AXRP - the AI X-risk Research Podcast

00:00

Cansev Generalise From the Human Labels?

Cansev generalises from the human labels that were generated from learning on the previous thing? Yes, ye. So imagine that, am i right? That one example of where you might want to use this is, like, it's going o be like easier and better to use a breakdown of,. like, the energies in this problem to like solve this physics. Another debater says, ah, it's actually going  better to do the breakdown of the forces. Cansev: Is the idea that, like, using imitative generalization, like, the reason that's going to be good is that we'regang to have a good prior over, like, a good

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