HN 提问：你们在使用哪些工具进行 AI 辅助代码的人工审查？
3 分•作者: dafelst•大约 1 个月前
我们和我们的同事现在正以惊人的速度产出由助手辅助编写的代码，其中一些质量相当不错，但也有很多质量不佳。我个人发现，我们项目真正的质量门槛在于，生成代码经过人类评审的彻底程度，以确保它不仅正确，而且在架构上是合理的。
像 Coderabbit 和 Copilot 这样的 AI 代码审查工具，甚至将 Claude 代码指向 PR（Pull Request），通常在查找 bug 和风格问题方面表现不错，但在查找重复代码、模块间耦合、关注点分离不当等方面表现较差，即使被提示这样做。
我发现 GitHub 的 PR 界面对我来说并不太好用，即使在评审规模较小时它就已经有些卡顿，而现在随着规模的增大，它变得难以管理。再加上混合了助手评审的额外噪音，以及人们“肉身代理”（meat-proxying）复制粘贴助手输出的内容，这使得它变得非常嘈杂且难以导航。
大家有什么好的方法来精简对 AI 辅助代码的人工评审吗？工具和流程建议都欢迎。
查看原文
A good proportion of us and our colleagues are now churning out agent-assisted code at an incredible rate, with some of it that is actually good, and a lot that is not so good. I'm personally finding that the real quality gate for our projects is now how thoroughly the generated code was human reviewed to ensure that it is not just correct, but architecturally sensible.<p>AI code review tools like coderabbit and copilot, or even pointing claude code at a PR are all generally pretty good at finding bugs and style nits, but less good at finding duplicate code, module cross coupling, bad separation of concerns, and so on, even if prompted to do so.<p>I'm finding that github's PR interface is not really cutting it for me, it was janky even when the reviews were small, but now at the size they're at, it is becoming unmanageable. Add to that the extra noise of mixing in agent reviews, and people "meat-proxying" in copy-pasted agent output, and it's getting pretty noisy and difficult to navigate.<p>What have you all found that works well for streamlining human review of AI assisted code? Tools and process suggestions are welcome.