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

Guaranteed Safe AI? World Models, Safety Specs, & Verifiers, with Nora Ammann & Ben Goldhaber

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

00:00

Ensuring Safe AI: The GSAI Framework

This chapter explores the Guaranteed Safe AI (GSAI) concept, detailing safety specifications, verifiers, and their application across diverse sectors like transportation and robotics. It emphasizes the importance of a collaborative approach in the field of AI safety, integrating insights from multiple disciplines to establish rigorous safety standards. The discussion also highlights the need for a shift towards quantitative safety metrics and a nuanced understanding of AI risks to enable effective engineering solutions.

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