[rbanffy]

> It’s completely the opposite. LLMs write awful python. Horrendous.

I've been using Claude Opus and it's pretty competent. I rarely have to make steering corrections. Once I had to deal with confusion, but, overall, the code is neat and the approaches sensible. It all depends on how much context you give it to work from, for instance. If it's building on top of a well organized codebase with a good best-practices document, it performs just fine.