Original Summary

Does any prompt or system exist which addresses this issue?<p>I tend to write my code comments in a very idiosyncratic way, and LLMs either don&#x27;t understand that (nor do I expect them to), or it isn&#x27;t much worth explaining. I&#x27;m fine with normal LLM comments, but publishing to production means I often have to do a lot of manual clean up with comments when committing code, and that&#x27;s tedious.<p>It would even be fine if LLMs all commented the same, but they don&#x27;t. I actually like the way some LLMs comment, but others are horrendous. The inconsistency is what makes this a mess, and simply saying &quot;no comments whatsoever&quot; (though it works) is hardly an alternative. What I want is a clean, consistent format with strict guidelines on what, and importantly what <i>not</i>, to comment, that works for all LLMs.<p>The idea here being that I can go on my merry way coding with agents, and that going forward they&#x27;ll always output perfectly understandable code which I&#x27;ll never have to check again.<p>Is there any progress here?

  • 情报分类：技术学习与提效
  • 分类依据：内容涉及技术、AI、软件工具或工程实践
  • 信息来源：Hacker News 新项目
  • 发布时间：2026/9/22 01:27:36