> Feedback helps, right. But if you've got a problem where a simple, contained feedback loop isn't that easy to build, the only source of feedback is yourself. And that's when you are exposed to the stupidity of current AI models.
That's exactly the point. Modern coding agents aren't smart software engineers per se; they're very very good goal-seekers whose unit of work is code. They need automatable feedback loops.
I'm working on an app to browse a codebase as a list of constructs — classes, methods, etc. It matches how I think about code: as a database of named entities, in which the implementation is often an afterthought — unlike text editors, in which constructs of various types, along with their implementation, all kind of look the same. It's still a very early project, but here's a short recording of some of what I've built so far[^0]. It's been a great way to learn SwiftUI, the Language Server Protocol, and FSEvents as well!
That's exactly the point. Modern coding agents aren't smart software engineers per se; they're very very good goal-seekers whose unit of work is code. They need automatable feedback loops.