Intelligent Machines (Audio) cover image

IM 844: Poob Has It For You - Spiky Superintelligence vs. Generality

Intelligent Machines (Audio)

00:00

Why scaling post-training matters more than pre-training

Jeremy favors scaling post-training (RL and on-policy learning) to induce reasoning, though size increases still help if trained right.

Play episode from 37:20
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