Gresham College Lectures cover image

Taming AI - Matt Jones

Gresham College Lectures

00:00

Shaping Behaviour: Reinforcement and Human Preferences

Matt Jones explains reinforcement learning, preference shaping, sycophancy, and risks from how humans train models.

Play episode from 35:26
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