I don't think this was only about implementation being the bottleneck. It was also because implementation forces you to think about the thing you're building at a very grannular level of detail, at which point you might discover flaws or opportunities that weren't obvious at the higher level.
And I find that, when it reasons through and encounters some of those, it just makes assumptions rather than asking the user.
In my experience I can heavily influence this based on the prompt.
Follow the sound of my voice. Come back toward the light.