Warning Shots cover image

The Book That Could Wake Up the World to AI Risk | Warning Shots #9

Warning Shots

00:00

Inscrutability of models and control limits

Michael explains why neural architectures and weight matrices resist mechanistic interpretability, limiting controllability.

Play episode from 17:41
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