Last Week in AI cover image

#231 - Claude Cowork, Anthropic $10B, Deep Delta Learning

Last Week in AI

00:00

Constitutional Classifiers++ defenses

Hosts review Anthropic's staged classifier cascade and linear-probe checks to cost-effectively defend against universal jailbreaks.

Play episode from 01:26:11
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