Deep copilot integration feels so intrusive. It pops up with your recent files. What if they were my bank accounts or api keys? Whoever thought that would be a good use experience should be fired.

gguf or mlx? edit, just tried a community mlx and lm studio said it didn't support loading it yet.

Number 2 makes me chuckle honestly. Too many people going down the 10x rabbit holes on youtube. Next up, a framework that 100xs your workflow. You know its good because it comes with 300 agents and 20 mcp servers and 1200 skills

Short answer no. Less short answer, the science is catching up to big ones quickly.

forget the warning, just compact like someone suggested in the ticket. Who would opt for a massive cache miss?

I will say I have noticed none of these things in my enterprise account. Is this is a known targeting of non-enterprise clients only?

The cost of building your own tool here is practically 0 these days. Why even bother trusting another party at all.

I would do this but cant stand the MacBook keyboards anyway. Even a cheap $50 amazon mechanical is a much more ergonomic experience

As a cynical modern eng look for landing page skills

If you review the code then committing as yourself makes perfect sense to me

Linux has used "Reviewed-by" trailers for many years. If you've only done minor editing, or none at all, it's something to consider.

If you review a juniors code, do you commit it under your name?

A junior is a person. A tool is a tool. Do you credit your text editor with authorship?

False equivalence. A text editor does not type characters that you didn't explicitly type or select.

If it contributed significantly to the design and execution, and was a major contributing factor yes. Would you say a reserve parachute saved your life or would you say you saved your own life? What about the maker of the parachute?

I'd be thanking the reserve and the people who made it, and credit myself with the small action of slightly moving my hand as much as its worth.

Also, text editors would be a better analogy if the commit message referenced whether it was created in the web ui, tui, or desktop app.

I suppose that for me the tool rarely contributes to the design and execution. At work and for any project I care about, I prompt once I know what I want, in terms of both function and the shape of the program to do it. If the model gen matches the shape closely enough, I accept, otherwise iterate from there. To me this is authorship.

When I vibe code - which for me, means using very high level prompts and largely not reading the output - then I could see attributing authorship to a model; but then I wonder what the purpose of authorship attribution is to begin with. Is it to tell you who to talk to about the code? Is it personal attestation to quality, or to responsibility? Is it credit? Some combination of these certainly, but AI can hold none except the last, and the last is, to me, rather pointless. Objects don't have feelings and therefore are unaffected by whether credit is given or not; that's purely a human concern.

I suppose the dividing line is fuzzy and perhaps best judged on the basis of the obscenity rule, that is, I know it when I see it.

That’s reviewing code vs contributing code.