That might actually be a benefit as most public code say in C++ is not good code.

If the pool is smaller but from say experienced programmers then the number of errors might be less. I can see that for Ada however most Haskell is probably written by undergraduates just learning it so not a quality code base.

I think Apple researchers published a recent papaer where they had a LLM giving good Swidt code but the original corpus only included one Swift program but the AI model was tuned by experienced Swift programmers to get into a good stae for general use.