Uncanny Valley | WIRED cover image

BIG INTV: Open AI’s Former Safety Lead Calls Out Erotica Claims

Uncanny Valley | WIRED

00:00

Mechanistic Interpretability and Its Limits

Katie asks about interpretability; Adler outlines the promise and limits of mechanistic work and game‑theory enforcement challenges.

Play episode from 28:18
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