我之前对绿地项目中的氛围编码有些误解。
我曾经认为“氛围编码”适合于全新项目，但我错了。
如果你不在乎代码，只想测试你的想法，那么这仅仅是一个一次性的概念验证，而不是一个真正的项目。没错，氛围编码在这种情况下是很有效的。
然而，随着工具和模型的不断改进，智能体在现有代码库上的表现也越来越好。智能体常常会发现代码库中已有的方法或代码风格，并据此进行编码。
我意识到，在一个全新项目中，重要的是在将代码盲目交给人工智能之前，先设定好数据模型、数据流和代码库的整体结构。否则，代码将变得难以维护，你也不想再去看那段代码。
查看原文
I used to think that vibe coding was good for greenfield projects. I was wrong.<p>If you don't care about the code and all you want to do is just to test your idea, then it is merely a throw-away PoC not a project. And yes, vibe coding is great for that.<p>However, as harnesses and models got better over the time, agents started working better on existing codebases. Often times, agents discover existing approaches/code style in the codebase and they start coding accordingly.<p>I realized that in a greenfield project it is important to set the data models and data flow and general structure of the codebase before handing it off to AI blindly. Otherwise it becomes an unmaintainable mess, and you never want to look at that code again.