My experience is exactly the opposite. 30 years writing software for my job, been using claude/grok for most of this year. At first they were really amazing. A real lever for higher output. But, I spend most of my time now telling them how to design high-performance systems and how to manage high concurrency and low contention.
They'll shove out a pattern quickly, but no matter how new and magical the latest model is, they will just put out some tweaked variant of existing designs. I find myself treating it like a junior-mid engineer. "Add rdtsc-based timers around major parts of the code to whittle down what's taking too long." "Use that to figure out where the transfer amount is way too small to justify the time taken without copying the payload." etc.
But concurrency bugs from large LLM-developed codebases are a major issue. They constantly find bugs they wrote. I eventually told it to start writing formal models of the concurrent uses and to (a) validate the models; (b) verify the code implements the models; to make it work.
So yeah, I stand by my words. For simple commands and tiny codebases, it /can/ do those things, but even small projects (50 KLOC) are a mess of making it fix its own mistakes, reconcile basic logic in requirements analysis, and everything has to be taken over with a fine-tooth comb to make it any good.