Ask HN: 你们在开源项目中如何处理 PR 密度（和冗余）？
1 分•作者: ofermend•5 个月前
鉴于像 Claude Code 或 Codex 这样的编码代理现在已经相当出色，向开源项目提交的 PR 数量当然也大幅增加。但并非所有 PR 都质量上乘，其中一些是真正的 AI 垃圾代码。
例如，可以参考 Daniel Stenberg 针对 cURL 提出的相关观点：
https://daniel.haxx.se/blog/2026/01/26/the-end-of-the-curl-bug-bounty/ 和 https://daniel.haxx.se/blog/2025/07/14/death-by-a-thousand-slops/
我很好奇这个问题对其他开源项目的影响有多大。
提交者们，你们看到了多少这种困扰？你们是否正在使用任何 AI 工具来缓解或解决这个问题？
查看原文
Given that coding agents like Claude Code or Codex are now quite good, there's of course a massive increase in PRs submitted to open source projects. Not all of them are great, some are true AI slop.<p>See for example Daniel Stenberg on the topic as it relates to cURL:
https://daniel.haxx.se/blog/2026/01/26/the-end-of-the-curl-bug-bounty/ and https://daniel.haxx.se/blog/2025/07/14/death-by-a-thousand-slops/<p>I'm curious how much of a problem this is to other open source projects<p>Committers, how much of this pain are you seeing, and are you using any AI tools to mitigate or address this issue?