{"podcast":{"title":"Future of Life Institute Podcast","slug":"future-of-life-institute-podcast-1112471","podcast_index_feed_id":1112471,"rss_url":"https://feeds.transistor.fm/future-of-life-institute-podcast-4e4d1fa5-a878-4cb2-91be-91c3ce266dfd","website_url":"http://podcast.futureoflife.org","image_url":"https://img.transistorcdn.com/J_n37RCZqjxGWjRTeSwa1kYSzes1V2OR3ShI3uGkwh8/rs:fill:0:0:1/w:1400/h:1400/q:60/mb:500000/aHR0cHM6Ly9pbWct/dXBsb2FkLXByb2R1/Y3Rpb24udHJhbnNp/c3Rvci5mbS81MmU5/MDZjZGQ5OTI0MDc5/YTk2ZTAxYTgwYTNk/M2VlOC5qcGc.jpg","author":"Future of Life Institute","episode_count":271,"summary":"The Future of Life Institute (FLI) is a nonprofit working to reduce global catastrophic and existential risk from powerful technologies. In particular, FLI focuses on risks from artificial intelligence (AI), biotechnology, nuclear weapons and climate change. The Institute's work is made up of three main strands: grantmaking for risk reduction, educational outreach, and advocacy within the United Nations, US government and European Union institutions. FLI has become one of the world's leading voices on the governance of AI having created one of the earliest and most influential sets of governance principles: the Asilomar AI Principles.","last_synced_at":"2026-07-01T06:20:26.948551+00:00","page_url":"https://stenobird.com/podcast/future-of-life-institute-podcast-1112471"},"episode":{"title":"Why AI Evaluation Science Can't Keep Up (with Carina Prunkl)","slug":"why-ai-evaluation-science-can-t-keep-up-with-carina-prunkl","published_at":"2026-04-17T15:54:27+00:00","page_url":"https://stenobird.com/podcast/future-of-life-institute-podcast-1112471/why-ai-evaluation-science-can-t-keep-up-with-carina-prunkl","show_page_url":"https://stenobird.com/podcast/future-of-life-institute-podcast-1112471","url":"https://share.transistor.fm/s/14615be3","audio_url":"https://media.transistor.fm/14615be3/4192276c.mp3","summary":"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 simple tasks, why pre-deployment tests often miss real-world behavior, and how faster capability gains can increase misuse risks. The conversation also covers de-skilling, red teaming, layered safeguards, and warning signs that AIs might undermine oversight. LINKS: Carina Prunkl personal website CHAPTERS: (00:00) Episode Preview (01:04) Introducing the report (02:10) Jagged frontier capabilities (05:29) Formal reasoning progress (12:36) Risks and evaluation science (19:00) Funding evaluation capacity (24:03) Autonomy and de-skilling (31:32) Authenticity and AI companions (41:00) Defense in depth methods (48:34) Loss of control risks (53:16) Where to read report PRODUCED BY: https://aipodcast.ing SOCIAL LINKS: Website: https://podcast.futureoflife.org Twitter (FLI): https://x.com/FLI_org Twitter (Gus): https://x.com/gusdocker LinkedIn: https://www.linkedin.com/company/future-of-life-institute/ YouTube: https://www.youtube.com/channel/UC-rCCy3FQ-GItDimSR9lhzw/ Apple: https://geo.itunes.apple.com/us/podcast/id1170991978 Spotify: https://open.spotify.com/show/2Op1WO3gwVwCrYHg4eoGyP","meta_description":"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 sy…","key_points":[],"chapters":[],"topics":[],"duration_seconds":3263,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/future-of-life-institute-podcast-1112471/episodes/why-ai-evaluation-science-can-t-keep-up-with-carina-prunkl/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/future-of-life-institute-podcast-1112471/why-ai-evaluation-science-can-t-keep-up-with-carina-prunkl.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]}}