Hacker News Reader

If you have a decent GPU or a modern Mac, you can run something like LM Studio (https://lmstudio.ai/) or Ollama (https://ollama.com/), configure the tool such as Cursor to use those models you've downloaded (personally I use Zed.dev), and then everything happens straight on your computer. Responses will be somewhat slower and not as good as state-of-the-art models, but they still can be helpful.

Git host doesn't really make a difference.

What model do you use? I’ve been trying devstral with Zed, and found it rather disappointing.

All of these agents work on local files... do you mean local LLMs?

No, he basically means thay companies will not allow LLMs on their own code, I think.

I work in a multinational conglomerate, and we got AI allowed ... 2-3 weeks ago. Before that it was basically banned unless you had gotten permission. We did have another gpt4 based AI in the browser available for a few months before that as well.

Correct. I don't want to circumvent rules but sometimes it feels like falling behind, like for reviewing MRs.

Claude Code runs in your terminal and works with your local files.