AI Lies Can Trick Evaluators
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 LLMsSource: arXivAuthors: Alexander Panfilov et al.Published Date: 2025-09-23Visit www.paper2podcast.com to download the full paper and learn more. Thanks for listening!
You May Also Like
Semiconductor Insiders
SemiWiki
No Tiene Nombre
elbruno
Artificial Intelligence Masterclass
AI Masterclass
The Vergecast
The Verge
EasyApple
EasyPodcast
Radio Miraya
Radio Miraya
Eye On A.I.
Craig S. Smith
Nodesignal - Deine Bitcoin-Frequenz
Die Nodesignal Crew
Jack Hopkins
Jack Hopkins
Mark Tilbury
Mark Tilbury Fan
Semiconductor Insiders
SemiWiki
No Tiene Nombre
elbruno
Artificial Intelligence Masterclass
AI Masterclass
The Vergecast
The Verge
EasyApple
EasyPodcast
Radio Miraya
Radio Miraya
Eye On A.I.
Craig S. Smith
Nodesignal - Deine Bitcoin-Frequenz
Die Nodesignal Crew
Jack Hopkins
Jack Hopkins
Mark Tilbury
Mark Tilbury Fan
Community discussion