We're in the messy transition period where our old indicators of a promising GitHub project are too easily replicated by someone letting Claude Code run for a few days.

A year ago it would have taken someone months of nights and weekends effort to get this much code up and running. That person would have developed a good intuition for the architecture and where it should go.

Now Codex or Claude can bang it out in a couple days. You can try to have it do spec documents, code reviews, and cleanup passes but with today's tools these projects reach a point where it's just a swirling mess of pieces duct taped together in a way that passes tests. In my experiments, you quickly reach a point where the usable context depth (which is less than the 1M limits) keeps overflowing before you can get usable refactors in, and you're just going in circles. I know it's theoretically possible to avoid these problems, but in practice you get spaghetti projects like this.