The difference between compilers and LLMs is that compilers actually work. LLMs do not produce a usable result, no matter how much AI bros try to convince everyone else otherwise.

> LLMs do not produce a usable result

At this point, this is categorically false. Your mental model is very out of date.

The results may not be ideal but I can't say I've had a single output so far this year that wasn't usable.