vagozino

That's cool! One thing I would like is to have an `llm` agent that takes your current un-staged files and automatically figures out how to put them into different commits.

This technique might be more efficient but can be highly correlated to the order of the input text. The paper [1] I mention in the repo touches upon such methods briefly.

[1]: https://arxiv.org/abs/2306.17563

Yes, that's correct! All three techniques have their trade-offs. I like the term "stability" you are using for this. There's definitely interesting avenues to go about this trading number of comparisons vs. stability.

Yeah that's right, the same amount of lines appear in the output. I see the `shell_gpt` project is very similar to the `llm` system, in any case.