As a follow-up, how would this workflow feel if the LLM generation were instantenous or cost nothing? What would the new bottleneck be? Running the tests? Network speed? The human reviewer?
I have videos showing Cerebras: https://simonwillison.net/2024/Oct/31/cerebras-coder/ and Gemini Diffusion: https://simonwillison.net/2025/May/21/gemini-diffusion/