a16z Podcast cover image

Marc Andreessen and Amjad Masad: English As the New Programming Language

a16z Podcast

00:00

Why reinforcement learning unlocked reasoning

Amjad explains RL from code execution, trajectories, and how successful rollouts get reinforced to extend reasoning chains.

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