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

References

1. The Decoder. (2026, November 7). AI auditors catch most agent misbehavior but flood reviewers with false alarms, new study finds. The Decoder. https://the-decoder.com/ai-auditors-catch-most-agent-misbehavior-but-flood-reviewers-with-false-alarms-new-study-finds/