Stress-Testing Alignment Audits With Prompt-Level Strategic Deception

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Daniels, Oliver, Moodley, Perusha, Marlin, Benjamin M., Lindner, David
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!