HackerNews中文版

您好！第一次发帖，潜水很久了。我是一家初创公司的专业软件工程师，公司大约有50名工程师。我的主要编程语言是 Ruby (Rails)、TypeScript (React) 和 Go。在我的同事中，我算是比较关注每一次新 AI 模型发布动态的。当出现新的前沿模型或开源模型时，我会将其作为主要工具试用几天，然后向同事们汇报我的使用体验。我在工作和个人项目中都使用 Cursor。我常用的模型是：用于规划的 GPT-5.6 Sol (高/超高精度设置)，用于实现的 GPT-5.6 Sol (中等精度设置) 或 Grok 4.6，以及偶尔用于处理复杂、难以理解和实现的任务的 Claude Fable 5。我的许多同事则专门使用 Claude，并且使用 Claude Code。我不是第一个注意到这一点的人，但我感觉每次使用 Fable、Opus 或 Sonnet 时，它们都非常啰嗦。它们会添加大量的额外代码注释，忽略指令，并且会为一些可以通过内置函数或预装库（如 Active Support 和 es-toolkit）解决的问题发明解决方案。我没有在其他模型上看到过同等程度的这种现象。我的问题是：为什么我们认为 Claude 模型出现这种情况的频率似乎更高？有没有人找到有效的方法来抑制这种行为？

查看原文

Hello! First time poster, longtime reader. I’m a professional software engineer at a startup with about 50 engineers. My primary languages are Ruby (Rails), TypeScript (React), and Go.<p>Of my colleagues, I’m one of the ones who tries to keep up with new AI models on every release. When there’s a new frontier or open-weight model, I’ll give it an honest try for a few days as my main driver and report back to my colleagues.<p>I’m a Cursor user at work and in my side projects. My go-to models are GPT-5.6 Sol on high/xhigh for planning, GPT-5.6 Sol on low/Grok 4.6 on medium for implementation, and the occasional Claude Fable 5 for complex, harder-to-understand and implement tasks. Many of my colleagues are exclusively Claude users and use Claude Code.<p>I’m not the first one to observe this but I feel like any time I use Fable, Opus, or Sonnet, they are extremely verbose. They make a ton of extra code comments, they ignore instructions, and they invent solutions for things solved by language built-ins or preinstalled libraries like Active Support and es-toolkit. I don’t see this happening with any other model at the same rate.<p>My question are: Why do we think the Claude models do this at a seemingly higher rate? And have people found any effective means to curb this behavior?

HN 提问：为什么 Claude 模型如此啰嗦？