This is amazing

The way frontier models work, that loop will get compressed to a one-shot within a version or two

Most ai output is meant for other ai's to read, in my experience. The humans job is to compress it for humans

I prefer to have the LLM ask me the questions

many of us work with swarms of cheap off-shore contractors and have to rewrite or finish their code already as it is. The llm is much lower friction

IME, the LLM when used well also gets closer to correct.