Have to call out that comment about grok code being sub par. I used it exclusively when it was free in Cursor and have nothing bad to say about it. And that was months ago. I imagine it’s a lot better now.

I have a lot bad to say about it. It was ass compared to OAI/Anthropic models.

It was incredibly fast though, but that just meant it was writing buggy code at breakneck speed

Its ass, just like every LLM (and their users)