Judging code quality by use of LLM in a documentation and commit messages is weird.

While I write all of my code myself and I'm against vibe coding etc., there is one place where I let a LLM write for me: readmes, commit messages and Javadoc comments.

I know how to write code but at the same time I'm shit at both my native language and even more so at English. So I let Language Models write natural language texts for me and just fix them when necessary. My documentation is more clear, grammatically correct and more detailed than in any of my previous projects, and I can focus on writing code.

And I wouldn't say "No one does that in a project they're building for themselves". I do that for projects that only I will ever see, and OP shared his project with others, so it's great that he included a clear documentation

I'm not OP, but my wife unfortunately has a similar problem with editing PDFs.

She works as a special education teacher, and one of her regular tasks is to modify tests to adapt them to a specific child’s disability (e.g., simplifying the content of questions or using less distracting images so that the test actually assesses the child’s knowledge, rather than their ability to analyze complex sentences or their ability to concentrate)

The problem is that most subject teachers do not prepare tests themselves, but rather send her PDFs that they downloaded from the internet or received from the textbook publisher.

If my wife needs to change the wording of two sentences, remove one image, and perhaps switch the order of two questions, editing the PDF will take her 10 minutes compared to the several hours of work it would take to rewrite the entire test from scratch.

This is probably a very unusual use case, but I’m sure there are a thousand other unusual use cases that legitimately can’t be handled any other way, so holding off on a recommendation for the OP until they explain themselves is a bit wierd

Fuck russia