But if you had instead spent the "weeks to learn your way around the codebase", that would have given dividends forever. I'm a bit afraid that by oneshoting features like these, many will never get to the required level to do bigger changes that relies on a bigger understanding.

Of course, LLMs might get there eventually. But until then I think it will create a bigger divide between seniors and juniors than it traditionally has been.

I've never been able to one-shot a feature with an agent. It's much easier to "learn my way around the codebase" by watching the AI search the codebase and seeing its motivation/mental model.

Going AFK is a terrible idea anyways because I have to intervene when it's making bad architectural decisions. Otherwise it starts randomly deleting stuff or changing the expected results of test cases so they'll pass.