nafyi.
话题 / AI产品

观点转述 · 非原话引用

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·已发布

观点背后的信息

译文仅辅助阅读；核查观点请以原始摘录为准。

Building Codex with Tibo Sottiaux

原始摘录

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.

此片段未附更多上下文，请阅读原始访谈。

打开原始内容 · 47:53 （在新标签页中打开）查看这场访谈

打开该集并跳转至47:53。

时间点来自所提供的转录稿，尚待媒体回放核对。