It writes more informative commits than I could ever make so I’m just reading what it says and mostly copy/pasting completely most of the time, I write all of the changes I’ve made into an LLM with a large context window and it write a very detailed commit not just with a title but with bullet points describing each of the changes precisely
Precision > concision && accuracy > concision. Just use your own wording as the commit message. I’d rather see an account of a code change from the viewpoint of the change’s author than a shorter reformulation, even if that reformulation did come from a human who knew the problem space and wasn’t prone to making shit up on the fly.
The problem is people are lazy and most places I’ve been, peoeple make bad commit messages and often very non informative.
I’d rather see no commit message than an AI-generated one.
Also if I wasn’t misinterpreting OP, it sounded from the post I was responding to like OP provided a summary to the LLM along with code. If OP’s writing a summary anyway, why not just proofread that and use that as the commit message rather than involving an LLM in the middle of the process?
Even in a hypothetical where the company hired human tech writers to write commit messages for developers, I’d rather have in the commit message what the developer had to say rather than the possible misinterpretation of the tech writer.