LessWrong (30+ Karma) cover image

“The world’s first frontier AI regulation is surprisingly thoughtful: the EU’s Code of Practice” by MKodama

LessWrong (30+ Karma)

00:00

Code Requirement: Explicit Security Goals and Measures

The host asks how companies must set security standards and details required security goals, measures, and defenses against model-led sabotage or exfiltration.

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