But you didn't upgrade the shed into a skyscraper. The iterative process you describe involves a human respecifying from scratch using the knowledge developed building the previous instance and seeing it's limitations first hand. That part can't be automated, no LLM is going to challenge your design assumptions by itself. Hence people pushing agent-built projects way past what their inherent architecture should support, delivering an unmaintainable code spaghetti.
People have been in love with machines for a long time. It's just that the machines didn't talk back so we didn't grant them the "partner" status. Wait for car+LLM and you'll have a killer combo.
France has Ariane, which was good enough to send Jame Web Telescope to some Lagrange point with extra precision. It's all fun and and games until the French finish their cigarette, arms French Guyana and fire ze missiles.
The ribbon thing was a taste of things to come in the degradation of UI standards. Take something that works great and looks ok, replace it with something flashy that gives marketing people something to say. Break the workflow of existing users. Repeat every 10 years.
IIRC the Ribbon had real UX testing behind it. All the most common features were truly easier to access, but it was harder to find a certain feature when you needed it. In other words they optimized for the wrong thing.
My favorite was that Paste was a giant button while Cut and Copy were small because the UX research found that people paste more than they cut or copy...
Also, outside of the zone of influence of an imperialist authoritarian power which would prevent them from handling the exploitation of their resources for the benefit of their nation instead of the profit of foreign oligarchs. See Petro-Canada privatization.
reply