I did this locally to try it out :) Also stubbed out the telemetry and added jj support. "Personalizing" software like this is definitely one of LLMs superpowers.

I'm not particularly inclined to publish it because I don't want to associate myself with a project harvesting emails like this.

> and added jj support

Please do the same for Aider :-)

https://github.com/Aider-AI/aider/issues/4250

Be the change you want to see! This is pretty close to a best case task for these models because it's a relatively direct "translation" of existing code.

There's a big difference between "something actually ready for use" and "claude hacked sometime together with bubblegum and ducttape that works on my system" though - doing it properly will probably take a bit of work.

yes, i was just doing/thinking the same, it was an interesting experience to sculpt a somewhat complex codebase to my needs in minutes.

Use a telemetry backed tool to remove telemetry from another telemetry backed tool?

There's telemetry you consent to, and telemetry you don't. Just because I'm fine with a tool like Claude Code collecting some telemetry, doesn't mean I'm fine with a different party collecting telemetry - and the two products being used together doesn't change it. It's not naive, it's simply my right.

it came to mind first, you're free to use whatever flavour of LLM f̶l̶o̶a̶t̶s̶ ̶y̶o̶u̶r̶ ̶b̶o̶a̶t̶ vibes your code.

That doesn’t change the naïvety of the response.

Your insult calling the commenter naive requires all telemetry from all sources to be the same.

I disagree with who is naive in this exchange.