paper / mary-phuong / May 9 / failedLLMs Can Covertly Sandbag on Capability Evaluations Against Chain-of-Thought Monitoring
paper / mary-phuong / May 9 / failedSpilling the Beans: Teaching LLMs to Self-Report Their Hidden Objectives
paper / mary-phuong / May 9 / failedPhantom Transfer: Data-level Defences are Insufficient Against Data Poisoning