A Practical Approach to Verifying Code at Scale

Summary

OpenAI describes training a dedicated agentic code reviewer used with gpt-5-codex and gpt-5.1-codex-max, aimed at catching bugs and vulnerabilities in AI-written code. The post argues that precision matters more than recall for adoption, and that giving the reviewer repo-wide tools and execution access improves both. Every OpenAI PR is reviewed automatically by this system.

Related items

• InfoRogue Anthropic AI agent gave police fake tip in unsolved murder caseSame vendor · BBC Technology
• InfoOpenAI Fires 3 Safety Researchers in Dispute Over AI RisksSame vendor · SecurityWeek
• Info‘Pure insanity’: Mathematicians will need years to make sense of OpenAI’s latest dropSame vendor · The Verge (AI)
• InfoOpenAI reports three new incidents of misalignmentSame vendor · CSO Online
• InfoA new feature for my blog, built using my voiceSame vendor · Simon Willison's Weblog