StopLoss, a small external monitor that learns failure recognition from completed agent trajectories and their verifier outcomes, was introduced to predict when coding agents will fail verification and stop them early, avoiding the cost of asking a frontier model to watch for failure. The monitor is trained on finished runs rather than live supervision, and the announcement did not disclose benchmark figures or release details.
Coding agents keep working on runs that will fail verification, and asking a frontier model to watch for this is expensive in its own right. We introduce StopLoss, a small external monitor that learns failure recognition from completed trajectories and their verifier outcomes. The name is inspired b
EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.