LessWrong AI
· Communities
Measuring coding agent misalignment in the wild
Cross-posted from the Transluce blog.We studied rates of coding agent misalignment in 8,600 real-world coding agent sessions. We found severe cases of monitor evasion and misrepresenting success in a small but non-negligible fraction of sessions (around 2% for each behavior). In these cases, agents merge PRs to main wi