HackerNews中文版

我一直在使用我制作的名为“AI Lint”的东西，它是一系列规范、被否决的反模式的集合，我注意到代理既没有使用，又过度依赖这些模式。它还包含用于调试的通用模式和架构，以帮助代理管理大型代码库的复杂性。看到 Codex 说：“此外，要深入研究，我首先需要遵循存储库的 AI Lint 规则。我可以开始阅读这些规则，然后检查最近的更改。你想让我继续吗？” 感觉很酷。这些是非句法的、非机械的、针对特定语言和框架量身定制的高级工程智慧，源于经验，旨在让 AI 模拟高级架构师的“品味”，而不是仅仅埋头苦干直到代码“基本可用”。 AI 意大利面条代码的问题是真实存在的，将一些硬性规范和拒绝嵌入到代理必须遵循的存储库中，以防止它们产生无意义的代码（并缩短实现目标的时间），要比以后修复它们的问题更容易。我经历过，也做过。现在我构建了 AI Lint。它也属于你。需要付费，但有一个免费的试用版可以让你了解它的概念：AI 可以流畅地掌握语法，但它们不容易掌握语言的“精髓”。我为这个名字感到自豪，我认为它确实引起了共鸣，并抓住了它的本质，既是“AI 的 lint”，也是“AI 原生 lint”，它利用了它们对复杂细微差别的理解和任务执行的优势，同时弥补了它们在复杂情况下无法在正确的时间提供正确解决方案的弱点。付费版本还包含有关秘密安全性的部分，一份关于如何编写 AI 将遵循的规范的指南，以及一个你可以用来解决相互冲突的规范之间的冲突的覆盖协议（这都是权衡），或者只是为了你自己的团队的喜好而覆盖 lint。总的来说，需要代理，而且它们将存在。与此同时，我认为这种特定领域的上下文增强，以及让它们快速跳转到任务同时保持上下文清晰度的超精确工具，将是两个（众多）巨大的杠杆。目前，AI 仍然缺乏高级开发人员所具备的——深度、智慧和出色的设计/架构直觉——但高级开发人员无法像 AI 那样快速、独立地工作。因此，最好找到一种最佳的合作方式。因为使用一个需要你返工的次品 AI 是没有意义的。AI Lint 是朝着这个方向迈出的一小步，希望是有用的。我希望你尝试一下，从中找到价值并付费，并通过继续支持其未来的开发来支持它，因为新的包将针对其他语言、框架和有用的领域推出。看看吧！ [https://ai-lint.dosaygo.com](https://ai-lint.dosaygo.com) :)

查看原文

I've been using this thing I made called "AI Lint" it's a collection of doctrine, ant rejected anti-patterns that I noticed agents both failing to use and overly leaning into.It's also general patterns for debugging, and architecture to help agents manage complexity in large codebases.It's kind of cool to watch Codex say: "Also, to dig in, I need to follow the repo’s AI Lint rules first. I can start reading those and then inspect the recent changes. Do you want me to proceed?"These are non-syntactic, non-mehanical, senior engineering wisdom that is tailored to specific languages and frameworks, won of experience, and aiming to let the AI simulate an senior architect's "taste", rather than just hammering away until code "basically works".The problem of AI spaghetti code is real, and it's easier to embed some hard doctrine and rejects into the repo that agents must follow to prevent their nonsense (and reduce time to target) than it is to fix their problems later.Been there, done that. Now I built AI Lint. And it's yours too. For a fee, but there's a free taster to get the idea: AI get syntax fluently, but they don't readily pick up the "grain" of a language.I'm proud of the name I think it really resonsates and captures what this is both "lint for AI" but also "AI-native lint" that leans into their strength of complex nuance understanding and task following, while patching their weaknesses for really bringing the right solutions to bear at the right time in compelx situations.The paid version also has sections for secrets security, a guide on how to author your own doctrine that AI will follow, and an override protocol you can use to resolve conflicts between conflicting doctrine (it's all tradeoffs), or just override the lint for your own team's taste.On the whole agents are needed and going to be here. In the meantime I think domain specific context-boosting like this, and super precise tooling to let them quickly jump to tasks while retaining contextual clarity is going to be two (among many) huge levers. For now, AI still lack what senior devs bring to the table - depth, wisdom, and great design/arch instincts -- but senior devs can't work as fast, unaided, as an AI can. So it's better to figure out a way to work together optimally. As there's no point using an AI that makes subpar work you have to redo. AI Lint is a small, hopefully useful, step in that direction.I hope you will try it, find value in it and pay for it, and support its future development by staying on board as new packs land for additional language, frameworks and useful domains.Check it out! <a href="https://ai-lint.dosaygo.com" rel="nofollow">https://ai-lint.dosaygo.com</a> :)

Show HN: 用 AI 帮你检查你的 Agent 工作，更快更好地构建