When I read commit messages and comments Claude makes a large fraction of the time they don't seem terribly related to the code, nor necessarily relevant to the problem at hand. The commits don't generally make a great deal of logical, linear sense either. Reviewing Claude PRs commit-by-commit is kind of nauseating. I only have 12yrs of experience though so I must be wrong. I'll defer to you guys. Sure would be nice to know wtf everyone's so excited about though I just don't get it.
News flash: you can tell LLMs how to do shit and they're generally pretty good at following instructions.
Those things are good enough to solve novel math problems I've never even heard about, surely it can figure out how you like your commit messages and apply it a million times over in the time it'd take you to make yourself a cup of coffee.
