nafyi.
Topics / AI products

Attributed viewpoint · Not a direct quote

Security flags can block pull-request merges

Tibo Sottiaux says OpenAI benchmarks code-review models for correctness and security. He describes mandatory checks that block pull-request merges when a security issue is flagged.

Tibo Sottiaux·Published

Behind the viewpoint

Translations are for reading; original excerpts remain the evidence.

Building Codex with Tibo Sottiaux

Original excerpt

When we benchmark them, it's like they're superhuman in code review. And this is not just true for correctness. This is also true for security, for example, where they're capable of reasoning across Very, very complex things. And then coming up with, hey, you have a critical security vulnerability here, which is now mandatory across all of OpenAI pull requests. We block pull requests from merging if we flag them with a security issue.

Additional context is not included in this excerpt. Read the original conversation.

Open original · 47:53 (opens in a new tab)View source page

Open the episode and seek to 47:53.

Start time comes from the supplied transcript. Playback alignment is awaiting review.