I disagree. I speak in code to the LLMs. It's just that LLMs are really good at reinventing the wheel that you were supposed to in your codebase. Recent example.

struct TensorView<T>{ body: Arc<[T]>, shape: [usize], stride: [usize], offset: usize, }

Okay now fill in all the helper methods. And GPT 5.6 Sol did a good job.

With that kind of workflow, you might be faster with AI autocomplete :)