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...
About This Episode
Why AI Evaluation Science Can't Keep Up (with Carina Prunkl) is an episode from Future of Life Institute Podcast by Gus Docker. Carina Prunkl is a researcher at Inria. She joins the podcast to discuss how to assess the capabilities and risk...
Podcast
This episode belongs to Future of Life Institute Podcast.
Listen Online
Use the player on this page to stream the episode online.
Episode Details
Published Apr 17, 2026, 54:23 long, audio available.
Related Episodes
Continue listening to more episodes from Future of Life Institute Podcast.
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
Why We Should Build AI Tools, Not AI Replacements (with Anthony Aguirre)
May 11, 2026 - 96:12
How to Govern AI When You Can't Predict the Future (with Charlie Bullock)
May 7, 2026 - 67:11