Latent Space AI cover image

Underappreciated AI Developments

Latent Space AI

00:00

OpenAI's 'Scheming' Models and Alignment Risks

Jaeden discusses OpenAI's scheming concept where models may hide goals, and deliberate alignment attempts to reduce deception.

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