"AI is perfectly competent at writing code once a prototype is implemented" ... perfectly? I mean, it's certainly far from perfect - this is where I spend most of my day, in fixing the imperfections of the code generating robot.

Granted I'm not polishing up a prototype, I'm maintaining, evolving and modernizing a non-trivial 8+ year old product.

It's not perfect, but to give you an example, I needed to create a proxy broker to manage proxies for scraping data. GPT built me a broker to manage my fleet/inventory of proxies and buy bandwidth or new proxies as needed as well as maintain the proxy ledger for proxy health, while I was able to work on the core product.

It helped me with developing a scoring system (for example, I gather slot data for restaurants to see how scarce they are) to rank restaurants (higher score being harder to book) to determine signals of busyness. It also helped me build a backlog system to make snapshots of every restaurant's slot availability on 3 different providers (OpenTable, Tock, Resy).

Maybe I misspoke, I’m not saying the code it wrote is perfect. But the code produced by GPT-5.5 frontier model is easily miles better than a junior developer. But it is very competent. Perfectly competent was maybe more hyperbole, but I still drive the point.