How do you avoid the spaghetti code that (in my experience) most AI models spit out? Sure you can steer it, ask it to make it better, etc... but it's easier to me to be in the driver's seat. Doesn't mean AI isn't useful, but whenever AI designs a feature end-to-end, everything is tightly-coupled, the wrong abstractions are picked, and fundamentally the code is not optimized for human understanding. I don't really understand how people can tolerate this kind of code (assuming they read it, which I think they do not). Just take the Claude Code CLI as an example - is there anyone in the world that knows how that spaghetti machine works?

I agree that AI is very useful in reviewing PRs and searching for bugs. It's definitely a game-changer there. But a human still needs to understand the code and take responsibility for it.