I've lately been making my git commit messages with AI
reddthat.com
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
You are viewing a single comment
If a glorified autocomplete algorithm can write more informative and concise commit messages than you, the actual author behind the code, I think you need to sit down and think long and hard what that actually implies.
And what does it imply?
That an AI might be better at writing documentation than the average dev, who is largely inept at writing good documentation?
Understandably, as technical writing isn't exactly a focus point or career growing thing for most devs. If it was, we would be writing much better code as well.
I've seen my peers work, they could use something like this. I'd welcome it.
it implies that the author of the code has no idea what they were doing.
I disagree. I am capable of writing a good commit message, I just don't really want to. Depending on the change, formulating a concise text that includes all relevant information can be quite time consuming.
I can travel to Italy on foot. Will I do that? Of course not. What does it imply? That I'm incapable of moving my body? Of course not! It just means I'm too lazy to do it and that there are faster ways to get to the same goal.
how do you write Pull-Requests? Just half-assing it? Writing good commit messages help you write a good PR as well (as it can be just a summary of the things you commited) But yeah, you do you.
There is a saying, which I don't generally agree with. Those who can, do. Those who can't, teach. That said, writing good code and describing code effectively are two different skills, and there is no guarantee any given individual will have both.
Don't ever call me a glorified autocomolete algorithm again