Why AI Hacking Is Becoming Hard to Control (with Benjamin Weinstein-Raun)
Aug 28, 2026 - 59:06
Radio and PodcastLive Radio & Podcasts
Technology
Why AI Evaluation Science Can't Keep Up (with Carina Prunkl)
Carina Prunkl is a researcher at Inria. She joins the podcast to discuss how to assess the capabilities and risks of general-purpose AI. We examine why systems can solve hard coding and math problems yet still fail at si...
Related Episodes
Continue listening to more episodes from Future of Life Institute Podcast.
First 24 Hours of a Bioweapon Attack - Annie Jacobsen
Aug 21, 2026 - 88:01
Why AI Evaluations Are Broken and How to Fix Them (with David Manheim)
Jul 17, 2026 - 79:21
How AI Is Replacing Children's Ability to Think (with Randi Weingarten)
Jun 30, 2026 - 43:59
How AI Companions Trap Users Through Addictive Design (with Claire Boine)
Jun 12, 2026 - 68:29
Why AI Chatbots Are a Rival to the Family (with Michael Toscano)
May 26, 2026 - 73:43