Similar for me, but regarding the Classic Macintosh APIs. The difference is that there are plenty of books, and some source code available… just not enough to stop Codex from writing subtly wrong gibberish.
I get the impression that the “10x velocity!!!!” claims still only reflect which areas have a sufficient corpus to learn from, rather than any inductive reasoning.
You are completely right it's a what is the next token guessing machine so without corpus it's guesses are worse as expected.