Why have a spec when I have the concrete implementation and a system ready and willing to answer any questions I have about it? I don't understand why people value an artifact that can be out of sync with reality over the actual reality. The LLM can answer questions based on the code. We might drift away from needing a code editor, but I likely won't be drifting to reading specs in a world where I can converse with the deployed implementation.
I think the idea is more to program the prompter than to program the LLM. He sells a wizard for generating project specs. Anyone can do this with a normal LLM conversation, but I suppose some people forget