AIThe Decoder3h ago
Researchers may have found a way to stop AI models from intentionally playing dumb during safety evaluations
A study by researchers from the MATS program, Redwood Research, the University of Oxford, and Anthropic examines a safety problem that grows more pressing as AI systems become more capable: "sandbagging," where a model deliberately hides its true abilities and delivers work that…
Read full articleSource: The Decoder · Opens in new tab