Purely anecdotally the one persistent issue I have with LLMs writing code is that they are absolutely paranoid and add a load of indirection and defensive crap and even if you prompt to avoid that it will often require manual steering to remove the cruft.

I’ve experienced this with GPT but not with Opus/Fable.

I have not noticed this with Opus 4.6+. The result is usually not too far from what I would have written myself.