Joseph Miller

Existing circuits in the mechanistic interpretability literature may not be as faithful as reported. Current circuit faithfulness scores reflect both the methodological choices of researchers and the actual components of the circuit.

We describe an attack on the state-of-the-art Go-playing AI system, KataGo. The adversaries do not win by learning to play Go better than KataGo but instead by tricking KataGo into making serious blunders, demonstrating that even superhuman AI systems may harbor surprising failure modes.