Comment by tinodb

I dove into the scoring a bit and must say that there are quite some overly subjective rules in the Verbosity set. Also some that go against pep8. This sounds like trying to make the llm pass an exam without telling it it will fail if it uses a blue pen…

I’m rerunning some now without those rules.

And also, couldn’t we greatly improve the outcome if we give the llm those quality gates? That is more interesting to me.