The Information Bottleneck cover image

EP9: AI in Natural Sciences with Tal Kachman

The Information Bottleneck

00:00

How to Train Your Advisor paper

Ravid summarizes Berkeley's advisor model idea: small steerers that prompt large black-box LLMs and RL fine-tuning.

Play episode from 12:02
Transcript

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