I would also bet that 90% of Swift training data is UI code.
And UI code quality tends to be technically pretty crummy/low-discipline. Your UI code doesn't need much consideration around data races, for example.
You wouldn't know that, if you looked at the UI code the LLM gives me. It loves threads; often mixing GCD and async/await, in one function.
A lot of the code I need to tear out, looks like that.
Most of the code I write is UI. It's actually fairly intense work, but relies on the underlying SDK, rather than language tricks.
I find the UIKit code I get, is a lot more robust and performant, than the SwiftUI code.
You wouldn't know that, if you looked at the UI code the LLM gives me. It loves threads; often mixing GCD and async/await, in one function.
A lot of the code I need to tear out, looks like that.
Most of the code I write is UI. It's actually fairly intense work, but relies on the underlying SDK, rather than language tricks.
I find the UIKit code I get, is a lot more robust and performant, than the SwiftUI code.