/ideas cover image

The state of AI in 2025: Reasoning, regulation, and rethinking scale

/ideas

00:00

How reinforcement learning improves reasoning

Fergal describes RL harnesses that select successful chains of thought to iteratively improve model performance.

Play episode from 06:12
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