I use Manjaro Linux with the Cinnamon desktop and sometimes run into system-level issues, but I have no idea how to properly debug them. It doesn’t feel as straightforward as debugging a normal program. What’s the best way or resource to learn system debugging on Linux?
Did you try to do this workflow with local models? If so, in your experience what are the better models for this?
We did experiment with local models. They were okay, if a little slow with the resources we allocated for testing. Ultimately though, we paid for copilot. I’m still a little sceptical that it won’t leak data, despite the assurances, so I do clean anything sensitive before pasting.
As for best models - generally gpt4 or 5 is my go-to, but the others have their uses. I tend to stick with one until it annoys me, then move on. Claude’s pretty good for code help, imo, but there’s not really a huge difference between them.
What’s your experiences?
I do not use models in general online, but my needs are also much smaller. Max I use my local model for ollama is translations. I am always interested in seeing more focused models so we can use on lower end hardware