TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Ask HN: How are you using LLMs in your command-line?

4 点作者 shaburn超过 1 年前
Ideally with system/file access/awareness and recording success.

3 条评论

eigenhombre超过 1 年前
ShellGPT <a href="https:&#x2F;&#x2F;github.com&#x2F;TheR1D&#x2F;shell_gpt">https:&#x2F;&#x2F;github.com&#x2F;TheR1D&#x2F;shell_gpt</a> does pretty well for a lot of use cases. I mostly use it in REPL mode, switching topics as needed. I have wrappers around the `sgpt` command to, say, start a REPL with a particular topic, say, Python, which loads my previous history on that topic as part of the prompt.<p>I also have an alias to save existing chats as text files so I can go back and review history.<p>Finally, there is an alias to load a question up in an editor if I need to enter multiline text, e.g. to discuss code fragments, etc.<p>I expect command-line workflows to be pretty individualized and I&#x27;m curious what others do. For me (old programmer), using a command line REPL feels much more natural (and blissfully noise-free) than going to a Web page to talk to, say, ChatGPT.
throwaway798214超过 1 年前
Nope, not using, I&#x27;m not even using command history or bash completion. The only way to actually learn what you are doing is by doing it yourself - but that&#x27;s just me, I don&#x27;t judge others for doing differently.
评论 #37330118 未加载
coding123超过 1 年前
I&#x27;m not but I am curious if you have some ideas?
评论 #37316568 未加载