I agree, and I think it's a continuum. I can say "make me an Instagram clone" and then come back after 100 agent loops and no looking at the code. Or I can outline the architecture, the components, service layer, data structures etc in a back and forth with the LLM and then have it do the minutia implementation.
You still get code hell after a while unless you review the code and refactor where needed, but I can absolutely imagine a future where the code is just a compile target for the architecture and design I specify. A little bit like a compiler spitting out assembly (caveats apply, LLMs being non-deterministic etc etc and at current state probably not reliable enough for full unsupervised coding)
You still get code hell after a while unless you review the code and refactor where needed, but I can absolutely imagine a future where the code is just a compile target for the architecture and design I specify. A little bit like a compiler spitting out assembly (caveats apply, LLMs being non-deterministic etc etc and at current state probably not reliable enough for full unsupervised coding)