[MrScruff]

This is true, but what is also true is that with each new generation of models (and not just for code generation) it becomes less and less true.

[svelle]

IMO LLM writing hasn't significantly improved since maybe GPT4. It still does the exact same "It's not x, it's actually y" tropes and many of the other common LLM smells. Most LLM generated text is immediately discernible as such.

[MrScruff]

You can avoid the smells with a prompt. I have a benchmark involving short story writing within specific styles and the level of sophistication achievable is increasing over time, in my opinion.