It's more like better-than-senior 99% of the time. Makes mistakes 1% of the time. Most of the 'bad results' I've seen people struggle with ended up being the fault of the human, in the form of horrible context given to the AI or else ambiguous or otherwise flawed prompts.

Any skilled developer with a decade of experience can write prompts that return back precisely what we wanted almost every single time. I do it all day long. "Claude 4" rarely messes up.

Same!