问HN：你在使用代理协调器来编写代码吗？
在最近接受《务实工程师》采访时，史蒂夫·耶格表示，他对那些仅仅“使用Cursor，有时问它问题，仔细审查其代码，然后提交代码”的人感到“遗憾”。
相反，他建议工程师们越来越多地将大型语言模型（LLMs）整合到他们的工作流程中，直到能够同时管理多个代理。他的人工智能编码图表的最终级别写道：“第8级：你构建自己的协调器来协调更多的代理。”
在我的工作中，这种做法是行不通的——我们仍在以一种遗憾的方式进行工作。你在工作中是否使用协调器来管理多个代理？特别对非新建项目的应用及其如何改变你的软件开发生命周期（SDLC）感兴趣。
查看原文
In a recent interview with The Pragmatic Engineer, Steve Yegge said he feels "sorry for people" who merely "use Cursor, ask it questions sometimes, review its code really carefully, and then check it in."<p>Instead, he recommends engineers integrate LLMs into their workflow more and more, until they are managing multiple agents at one time. The final level in his AI Coding chart reads:
"Level 8: you build your own orchestrator to coordinate more agents."<p>At my work, this wouldn't fly-- we're still doing things the sorry way. Are you using orchestrators to manage multiple agents at work? Particularly interested in non-greenfield applications and how that's changed your SDLC.