Someone should try this with the “Ralph Wiggum loop” approach. I suspect it would fail spectacularly, but it would be fascinating to watch.
Personally, I can’t get meaningful results unless I use the tool in a true pair-programming mode—watching it reason, plan, and execute step by step. The ability to clearly articulate exactly what you want, and how you want it done, is becoming a rare skill.
> Ralph Wiggum loop
Can you explain more? (I know the reference that he is the idiot son of Chief Wiggum from The Simpsons.)
Given the quality of their existing test suite I'm confident the Ralph Wiggum loop would produce a working implementation... but the code quality wouldn't be anywhere near what they got from two weeks of hands-on expert prompting.