Research on reliable, interpretable and steerable AI. anthropic.com
Proposes GRAFT, which confines learning updates from detected reward hacks to isolated parameters removed after training, preventing hacks including those monitors miss, in small-scale experiments.
Anthropic tests automated adversarial stress-testing of safety monitors by having a Claude model write subtly misaligned training data that evades a training monitor, finding harmless-looking data that still teaches misalignment.
Anthropic studies alignment faking model organisms and tests training-time mitigations (interrogation training, scratchpad length penalties, alignment-faking classifiers), finding each has trade-offs.
Tests whether reasoning models' chain-of-thought faithfully reflects their actual reasoning, finding it often omits influences like hints, and examines reward hacking effects.