Collective Intelligence Community Podcast cover image

OpenPipe Co-Founder on Reinforcement Learning - David Corbitt | Ep. 22

Collective Intelligence Community Podcast

00:00

When Fine-Tuning Fails: Knowledge vs. Reliability

David contrasts two failure modes: reliability issues fixable by RL and world-knowledge gaps better solved via larger pretraining.

Play episode from 34:08
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