A Practical Approach to Verifying Code at Scale

As autonomous collaborative coding systems proliferate, the volume of produced code quickly exceeds the limits of thorough human oversight. As this gap widens, so does the risk that AI written code introduces severe bugs and vulnerabilities—whether accidentally or intentionally. We cannot assume that code-generating systems are trustworthy or correct; we must check their work. Automated code review is a practical output monitor that complements chain-of-thought monitoring, action monitoring, internal activation monitoring, behavioral testing, honesty training and other safety work as part of a defense-in-depth strategy. In this post, we share what we learned from training a dedicated, agentic code reviewer as part of gpt-5-codex and gpt-5.1-codex-max[1]. We discuss how giving the reviewer repo-wide tools and execution access improves both recall and precision, and how deployment-time considerations guide us toward high-signal settings with minimal alignment tax. These ideas aren't theo

A Practical Approach to Verifying Code at Scale ← Back to OpenAI Alignment Blog A Practical Approach to Verifying Code at Scale Dec 1, 2025 · Maja Trębacz, Sam Arnesen, Albin Cassirer, Max Johnson, Xin Lin, Thibault Sottiaux, in collaboration with the rest of the Codex team As autonomous collaborative coding systems proliferate, the volume of produced code quickly exceeds the limits of thorough human oversight. As this gap widens, so does the risk that AI written code introduces severe bugs and vulnerabilities—whether accidentally or intentionally. We cannot assume that code-generating systems

related reading

• Auto-review of agent actions without synchronous human oversightalignment.openai.com
• When AI Writes the World's Software, Who Verifies It? — Leonardo de Mouraleodemoura.github.io
• I built an AI code review agent in a few hours, here's what I learnedsourcebot.dev
• Introducing FrontierCode | Cognitioncognition.ai
• Treat Agent Output Like Compiler Output | Skipskiplabs.io
• Your job is to deliver code you have proven to worksimonwillison.net
• Composer2.pdfcursor.com
• If you are good at code review, you will be good at using AI agentsseangoedecke.com
• Shipping at Inference-Speed | Peter Steinbergersteipete.me
• Introducing FrontierCode | Cognitioncognition.com
• Using AI to write better code more slowly | Read the Tea Leavesnolanlawson.com
• Coding Models Are Doing Too Much | whnrehiew.github.io