Article · The Decoder ·
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. That's not yet enough for reliable safety checks.
Read at the-decoder.com The opening of the article at the-decoder.com.
In this story
A tool or model opens in the Heidelberg AI Curriculum: what it does, what it costs, how to start. A repo opens on GitHub.
