For Humanity: An AI Risk Podcast cover image

AI Safety on the Frontlines | For Humanity #73

For Humanity: An AI Risk Podcast

00:00

The important moment: stopping the twitching Frankenstein

Esben frames intervention at initial AGI takeover as actionable safety work distinct from pre-deployment alignment research.

Play episode from 36:09
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