OpenAI DevDay 2026: Codex Security goes from vulnerability to verified fix
OpenAI · youtube · 2026-11-11
At DevDay 2026, OpenAI Cyber product leads Kylie Brown and Ian Webster demoed finding and fixing vulnerabilities with OpenAI's cyber models and open-source CLI/SDK — scanning large codebases, catching issues in pull requests, and verifying fixes, drawing on OpenAI's internal security work.
More from coding & agent
- Dev: Agents With Ambient Listening Make @-Mentioning Feel Like the Stone Age — cramforce · 2026-11-11
- Designing for Verification: How Claude Artifacts Redefines Software UI in the Agent Era — dotey · 2026-11-11
- rea-video: open-source tool reverse-engineers any video shot by shot, 6.5k GitHub stars — songguoxiansen · 2026-11-11
- Dev builds force-based artificial life sim with hunting and gene inheritance using Fable 5.2 — CatAstro_Piyush · 2026-11-11
- Spotify's viral Claude Code token trick tested: the real ~90% savings, numbers and prompt inside — aakashgupta · 2026-11-11
- One Opus run cost $1.99 — 94% went to reading files, not writing code — aakashgupta · 2026-11-11