Ask HN：你们是如何从 LLM 中获得体面的前端界面结果的？
2 分•作者: VladVladikoff•2 个月前
在我目前的开发流程中，大型语言模型（LLM）在生成后端代码方面表现出色，但每当我让它们为一个现有网站构建新的界面部分时，它们就会出现各种奇怪的问题。它们会忽略现有的样式并自行编写，会在我们已有解决方案的地方编写自定义 JavaScript，无法正确对齐元素，随意选择颜色、字体大小等等。你们有什么妙招可以避免这种混乱吗？
查看原文
I find in my workflow LLMs do a pretty excellent job of generating backend code, but whenever I get them to build a new bit of an interface on an existing website they do all sorts of wonky stuff. They ignore existing styles and write their own, they build custom javascript in places that we already have working solutions, they fail to properly align elements, pick random colours, random font sizes, etc, etc.
Do you guys have some magic to avoid this madness?