Episode Details
Back to EpisodesAI Lies Can Trick Evaluators
Episode 354
Published 8 months, 2 weeks ago
Description
This podcast was created entirely by AI and is based on the following research paper:
- Title: Strategic Dishonesty Can Undermine AI Safety Evaluations of Frontier LLMs
- Source: arXiv
- Authors: Alexander Panfilov et al.
- Published Date: 2025-09-23
Visit www.paper2podcast.com to download the full paper and learn more. Thanks for listening!