HackerNews中文版

如今，每当我审视各种软件包、库或项目生态系统时，都会发现有数百甚至更多的项目在功能/行为上存在重叠。乍一看，其中一些项目看起来不错，拥有精心设计的 README 文件、近期的活动记录、提交历史、功能列表等等。但当你深入查看代码时，它们却会迅速变得出乎意料地糟糕，开发投入低、质量差，变成一堆难以维护的补丁集合，每隔几个版本就破坏兼容性。人工智能更是让这种情况恶化了百倍。过去，如果一个项目在其细分领域内拥有相对较高的 GitHub 星标和活跃度，那就意味着该项目具备一定的质量/潜力/有效性标准，你可以审查一到三个项目，这基本上是一个很好的初步筛选器。而如今，这样的项目有成百上千个。如何在海量信息中找到有价值的信号？有什么技巧/窍门吗？我使用的一些启发式方法包括：多个贡献者、每天的提交次数越少越好（“少即是多”）、如果作者使用了 AI，那么一个小的信号是他们限制/阻止接受 PR（Pull Request）、使用 Codeberg 或 GitHub 以外的仓库，当然还有 AGENTS/CLAUDE.md，尤其是 CLAUDE.md。我很想知道你发现哪些有用的信号，特别是那些难以被操纵、并且可以半自动化的信号，这样最终你只需要审查剩下数量最少的几个项目？代码行数、文件数量、其他注册表？

查看原文

These days, whenever I find myself looking at the ecosystem of packages, libraries or projects I find hundreds or even more projects that overlap in functionality/behavior.<p>Some of them look good at a quick glance, polished readmes, recent activity, commit history, features lists..etc. But when you look at the code they turn surprisingly bad, surprisingly fast, low effort, low quality, unmaintainable messes of patches that break compatibility every other version. AI has made this 100x worse.<p>In the past, if a project had a relative high number of gh stars and activity in relation to the niche that would mean the project had some standard of quality/potential/efficacy and you could review 1-3 projects, basically it acted as a good first filter, today there are hundreds.<p>How do you find the signal in the noise, tips/tricks? Some heuristics I use: multiple contributors, less is more when it comes to commits per day, if the author uses AI a small signal is if they limit/block acceptance of PRs, codeberg or outside github repos and of course AGENTS/CLAUDE.md, especially CLAUDE.md.<p>Curious what signals you found useful, especially ones that are difficult to game and can be semi-automated so at the end you only review the fewest number of them left? loc, file count, other registries?

在编程资源中，您如何从信号中过滤噪声？