"The Cognitive Revolution" | AI Builders, Researchers, and Live Player Analysis cover image

Can We Stop AI Deception? Apollo Research Tests OpenAI's Deliberative Alignment, w/ Marius Hobbhahn

"The Cognitive Revolution" | AI Builders, Researchers, and Live Player Analysis

00:00

Deliberative Alignment: Method and Test Design

Marius explains OpenAI's deliberative alignment: writing a spec, SFT rollouts, RL fine-tuning, and the narrow anti-scheming training set used to evaluate broad generalization.

Transcript
Play full episode

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