[AmbroseBierce]

I would be more interested in an hybrid approach, an AI that when has low confidence in a generated commit message asks the user for their input: "Was this change meant to fix a bug? y/n" and about splitting commits "you changed 6 html files and 1 SQL file, they seem unrelated" should I split that into 2 separated commits? y/n"

[austinshea]

I love it. A bit guided of assistance can really make all the difference.

[selfhoster11]

That actually sounds like a good match for LLMs' ability to do fuzzy intuition and pattern-matching.

[fka]

this is a really good idea.