![](https://www.think-tanks.fm/wp-content/uploads/2024/04/xTWP2R7JIKDNULNWTX4SEO2YKIY-306x200.jpg.pagespeed.ic.cravL0JXTc.jpg)
Catastrophic AI Risks
Dan Hendrycks joins the podcast again to discuss X.ai, how AI risk thinking has evolved, malicious use of AI, AI race dynamics between companies and between militaries, making AI organizations safer, and how representation engineering could help us understand AI traits like deception.