Artificial intelligence5 min read
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 up.
By Manuel UthThe Decoder

Read the full story
Originally published by The Decoder on Nov 7, 2026.
Comments
Sign in to join the discussion.