The thing I find least compelling about these “AI is a compiler” arguments is that they require dissonance or magical thinking where somehow the AI is good enough to write and review all the code to the point where you don’t even need to look at it, but at the same time the LLM needs an experienced software engineer to feed it the prompts.

Because apparently this agent isn't capable of reading the business rules that exist today that determine things like that. Seems like the prediction is a regression over the next 5 years.