Not sure what I can say but the LLMs simply do not write good code without tons of handholding. As a C developer most LLMed patches I have seen the last couple of months have been awful and the few good ones I know from the author themselves that they did a ton of iteration and/or manual cleanup. Maybe they are less bad at writing other languages.

People say this every 6 months. I've stopped even paying attention to it, because (A) the code quality remains below the floor, and (B) the people saying it continue to ignore all the other issues with LLM code generation.