About this episode

Carina Prunkl discusses the challenges of assessing AI capabilities and risks.

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…

People in this episode

Host: Future of Life Institute

Guest: Carina Prunkl

Topics covered

• AI evaluation
• general-purpose AI
• capabilities assessment
• risks of AI
• de-skilling
• safeguards

Keywords

• AI evaluation
• general-purpose AI
• risks
• de-skilling
• red teaming
• safeguards

Mentioned in this episode

Organizations: Inria

More episodes of Future of Life Institute Podcast

• Defense in Depth: Layered Strategies Against AI Risk (with Li-Lian Ang) · April 2, 2026 · 56 min
• What AI Companies Get Wrong About Curing Cancer (with Emilia Javorsky) · March 20, 2026 · 1h 12m
• AI vs Cancer - How AI Can, and Can't, Cure Cancer (by Emilia Javorsky) · March 16, 2026 · 2h 43m
• How AI Hacks Your Brain's Attachment System (with Zak Stein) · March 5, 2026 · 1h 45m
• The Case for a Global Ban on Superintelligence (with Andrea Miotti) · February 20, 2026 · 1h 7m
• Can AI Do Our Alignment Homework? (with Ryan Kidd) · February 6, 2026 · 1h 47m

Explore listener stats, chart rankings, contacts and more on the Future of Life Institute Podcast podcast page.