> I think that the prompt is the thing that should be PR'd at this point, because ultimately the spec is what's important.

The fundamental problem there is the code generation step is non-deterministic. You might make a two sentence change to the prompt to fix a bug and the generation introduces two more. Generate again and everything is fine. Way too much uncertainty to have confidence in that approach.

> At some point I think it makes more sense to fine tune the prompts to get increasingly more specific and just regenerate the the code based on that spec, and store that in Git.

Generating code using a non-deterministic code generator is a bold strategy. Just gotta hope that your next pull of the code slot machine doesn’t introduce a bug or ten.

> I suspect if people saw the handwritten code of many, many, many products that they used every day they would be shocked.

Absolutely. The difference is that the amount of bad code that could be generated had an upper limit on it — how fast a human can type it out. With LLMs bad code can be shat out at warp speed.

> I guess I'm ignorant but why do we continue overspending worldwide?

Social programs are popular with voters (well, the ones who benefit from them without paying sticker price), no one ever wants to take a step backwards in lifestyle (especially government employees), and there’s an unwavering belief that any amount of spending is “fine”, all we need are those damned rich people to pay their fair share.