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.
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. You can learn more about Dan's work at https://www.safe.ai Timestamps: 00:00 X.ai - Elon Musk's new AI venture 02:41 How AI risk thinking has evolved 12:58 AI bioengeneering 19:16 AI agents 24:55 Preventing autocracy 34:11 AI race - corporations and militaries 48:04 Bulletproofing AI organizations 1:07:51 Open-source models 1:15:35 Dan's textbook on AI safety 1:22:58 Rogue AI 1:28:09 LLMs and value specification 1:33:14 AI goal drift 1:41:10 Power-seeking AI 1:52:07 AI deception 1:57:53 Representation engineering
Emilia Javorsky explores how AI can realistically aid cancer research, where current hype exceeds evidence, and what changes researchers, policymakers, and funders must make to turn AI advances into real clinical impact.
Researcher Zak Stein discusses how anthropomorphic AI can exploit human attachment systems, its psychological risks for children and adults, and ways to redesign education and cognitive security tools to protect relationships and human agency.
Andrea Miotti, founder of Control AI, discusses the extreme risks from superintelligent AI and his case for a global ban on systems that could outsmart humans, touching on industry lobbying, regulation strategies, public awareness, and citizen actions.
