I've had a handful of software projects in my career land essentially on the day I predicted, sometimes several months out, and the commonality across all of those projects was that the specification was crystal clear. Two of them were actual ports of an existing piece of software over to a new system. And so any time we had a question about the implementation, we could look at the existing version and immediately have our questions answered about what "correct" was.

I think projects where correct is very clearly defined can benefit from LLM acceleration, as you're describing here.

But so much of modern software development is figuring out what the right thing to build is. And in those situations, I don't think LLMs provide nearly as much benefit.

I think the role of llm’s is once you have a rich enough understanding of what you want - you can speed run to build it. And then perhaps re-build to cover the issues created by the llm.

Problem for model producers is - the revenues they get from this mode of work is tiny relative to what they need.

And there's a few domains where the spec is clear and the solution kinda easy to implement. But it breaks the contract with your users or downstream projects and you now have to coordinate communication. Code rarely exists in isolation.