Ask HN: 你在使用 Claude 代码方面有哪些高效的实践?

2作者: nocobot7 个月前
我对基于 LLM 的编码工具持怀疑态度,但很多人似乎都在吹捧其带来的巨大生产力提升,这我也很乐意看到。<p>然而,当我尝试使用 cc 时,我非常失望。为了说明情况,我正在参与一个相对全新的 Rust 项目,并给它分配了一些我认为适合初级同事的任务,例如:<p>- 更改一个 trait 的返回类型及其所有实现<p>- 将重复代码重构到一个辅助函数中<p>- 用一个外部 crate 替换我们的一些代码<p>它一个都没正确完成,而且花费了很长时间。是我使用这个工具的方式不对吗?<p>你们是如何使用 cc 或其他基于 agent 的工具的?
查看原文
I tend to be sceptical when it comes to LLM based coding tools but many people seem to be raving about huge productivity gains which I wouldn’t mind as well.<p>However when trying cc it left me vey disappointed. For context I’m working on a relatively greenfield rust project and gave it tasks that I would consider appropriate for a junior level colleague like:<p>- change the return type of a trait and all it’s impls<p>- refactor duplicate code into a helper function<p>- replace some of our code with an external crate<p>it didn’t get any of them correct and took a very long time. Am I using the tool wrong?<p>How are you using cc or other agentic tools?