Hi, I'm Dylan Young. I build software & write about where AI is taking it.

Every level of AI maturity, from human-only development to autonomous agents, shares the same blind spot: the only thing that improves over time is the humans. They get better at prompting, better at reviewing. The model stays frozen, same quality on day 100 as day 1. Every bad output a developer rejects, every subtle fix they make, that signal just vanishes. So what would it look like if it didn't? That's the Flywheel Architecture.