Last Week in AI cover image

#223 - Haiku 4.5, OpenAI DevDay, Claude Skills, Scaling RL, SB 243

Last Week in AI

00:00

Cautious Weight Decay: A Simple Optimizer Tweak with Big Gains

Andrey outlines cautious weight decay which applies decay only when update and parameter signs align, improving training stability.

Play episode from 57:28
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