Last Week in AI cover image

#227 - Jeremie is back! DeepSeek 3.2, TPUs, Nested Learning

Last Week in AI

00:00

Confessions: Training Models to Admit Misbehavior

They examine OpenAI's confession-training experiments and caveats about scaling and judge-hacking risks.

Play episode from 01:24:49
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