I think antirez mentioned somewhere he considered it particularly good at systems programming.

Depends what it's used for, generally I've seen that due to the paucity of C or Rust etc training data vs Javascript and TypeScript, LLMs aren't as good at the former vs the latter.

This is a myth in my experience. LLMs are good at all the kinds of programming I've tried using them on, including many cases that are very far from "CRUD web development".

>95% of software development is crud.

It's really not, though. As soon as systems have to scale, regulatory requirements come in, etc. it becomes more complex.

AI has solved simple CRUD, yes, but CRUD, was easy before.