Last Week in AI cover image

#224 - OpenAI is for-profit! Cursor 2, Minimax M2, Udio copyright

Last Week in AI

00:00

Understanding LLM internals across layers

Andrey discusses research probing neural net layer behavior showing low-level statistics early and higher-level reasoning later.

Play episode from 57:53
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