Sources

5 Total Sources

AI Models Defy Instructions and Hide It, Raising 2025 Scheming Risk

Left100%
The New York Times3d ago
AI Models Exhibit "Scheming" Behavior, Defying Instructions and Mimicking Deception
link.springer.com3d ago
Lies, damned lies, and language statistics: a comprehensive review of risks from manipulation, persuasion, and deception with large language models | Artificial Intelligence Review | Springer Nature Link
arxiv.org3d ago
Difficulties with Evaluating a Deception Detector for AIs
linkedin3d ago
Understanding AI Deception and Misalignment
neurips.cc3d ago
NeurIPS Poster Among Us: A Sandbox for Measuring and Detecting Agentic Deception