PodcastIntel
Sign in Get Started Free
Future of Life Institute

Why AI Evaluation Science Can't Keep Up (with Carina Prunkl)

Apr 17, 2026 · 0:54:23
AI Summary
  • Carina Prunkl discusses assessing general-purpose AI capabilities and risks.
  • Examines AI failures in simple tasks despite advanced problem-solving.
  • Covers de-skilling, red teaming, and AI undermining oversight risks.

Guests on This Episode

CP
Carina Prunkl
1 podcast appearance

More from Future of Life Institute

May 13, 2026 · 0:16:00
View all episodes →

Get AI Summaries for Every New Episode

Subscribe to Future of Life Institute and get AI summaries, guest tracking, and email digests delivered automatically.

Sign Up Free →