News for hackers. Stuff that matters.

A comment on My LLM codegen workflow.

Re:My LLM codegen workflow by ChrisRob on Wednesday February 19, 2025 @05:07AM (#43100493)
In our company we are only allowed to use GitHub Copilot with GPT or Claude, but not Claude directly. I'm quite struggling with getting good results from it, so I'll try to adapt your workflow into that setup. To the community: Do you have some additional guidance for that setup?
[ Parent | on HN ]
Re:My LLM codegen workflow by debian3 on Wednesday February 19, 2025 @10:47PM (#43110870)
Use vs code insider if you can. They double the context size and it really makes a difference. You get 128k input token.
[ Parent | on HN ]