AI auditors catch most agent misbehavior but flood reviewers with false alarms, new study finds

AI models can often spot problematic behavior by other AI agents in logs, according to a study by Anthropic researcher Andy Hall. GPT-5 found about 98 percent of reward-hacking cases, but the more exhaustively the search is tuned, the more false alarms pile…

Preview courtesy of The Decoder. The full article opens on their site.