原始对话
The Pragmatic Engineer · · 1:13:22
Tibo Sottiaux discusses research and product co-design, avoiding elaborate workarounds for model limitations, and automated code-review security checks.
简短、标注来源的段落，并附有可验证上下文。完整对话保留在其发布者处。
原始摘录
I wanted to join a group where all the parameters were considered together, where research and product were really co-designing.
此片段未附更多上下文，请阅读原始访谈。
原始摘录
care about the user, care about the coherence of the product, care about the models and where they're going. If you're doing something and you're building this 10,000 lines of code crutch to work around the model flaws, you're probably doing the wrong thing. So we have a set of principles, but it's just really So like a team culture and ethos at this point.
此片段未附更多上下文，请阅读原始访谈。
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。
这些观点均关联原始来源。转述已明确标注，不作为逐字原话展示。
打开转录或来源材料 （在新标签页中打开）报告问题
nafyi.