Hacker News new | ask | show | jobs
by beyang 544 days ago
FYI, you can do that with Cody + Ollama. A good portion of our user community does exactly that: https://sourcegraph.com/blog/local-code-completion-with-olla...
1 comments

I don't want a local LLM, it is slower, less capable, and slows the computer down generally

What I would like is a deep integration with VS Code using my preferred foundational model

I see Cursor has their own model and support for 2 foundational models, but not my preferred model and they charge a monthly fee.

Supposedly: https://cloud.google.com/blog/products/ai-machine-learning/g...

but do I still have to pay microsoft $20+ per month? what I really want is pay-per-usage, not pay-for-access+usage