Fred Brooks told us to "plan to throw one version away, because you will."
What he missed is that the one version that is not thrown away will have to be maintained pretty much for ever.
(Can we blame him for not seeing SaaS coming ?)
What if the real value of AI was at the two sides of this:
* to very quickly built the throwaway version that is just used during demos, to gather feedback from potential customers, and see where things break ?
That can probably be a speed-up of 10x, or 100x, and an incredible ROI if you avoid building a "full" version that's useless
* then you create the "proper" system the "old" way, using AI as an autocomplete on steroid (and maybe get 1.5x, 2x, speedup, etc...)
* then you use LLMs to do the things you would not do anyway for lack of time (testing, docs, etc...) Here the speedup is infinite if you did not do it, and it had some value.
But the power that be will want you to start working on the next feature, by this time...
* I don't know about how LLMs would help to fix bugs
So basically, two codebase "lanes", evolving in parallel, one where the AI / human ratio is 90/10, one where it's maybe 30/70 ?
Maybe but anytime someone keeps doing mental gymnastics and theorizing that there are new forces at play, something comes out and says no, it was something very straightforward. Hammock Driven Development describes a zen internalized way an expert does exactly as you describe but it is nicer you don't have to pay per token. To be clear, I think this all falls again under the rubber duck umbrella which is fine, but seemingly impossible to design a controlled study for?
I agree that the study is biased (it compared people unused to a tool with people not using the tool. Duh. The only person who was more efficient was the person... who knew how to use the tool. Duh indeed.)
However I don't see how hammock driven dev allows you to validate an idea with a prototype built in an hour as opposed to a month.
What he missed is that the one version that is not thrown away will have to be maintained pretty much for ever.
(Can we blame him for not seeing SaaS coming ?)
What if the real value of AI was at the two sides of this:
* to very quickly built the throwaway version that is just used during demos, to gather feedback from potential customers, and see where things break ?
That can probably be a speed-up of 10x, or 100x, and an incredible ROI if you avoid building a "full" version that's useless
* then you create the "proper" system the "old" way, using AI as an autocomplete on steroid (and maybe get 1.5x, 2x, speedup, etc...)
* then you use LLMs to do the things you would not do anyway for lack of time (testing, docs, etc...) Here the speedup is infinite if you did not do it, and it had some value.
But the power that be will want you to start working on the next feature, by this time...
* I don't know about how LLMs would help to fix bugs
So basically, two codebase "lanes", evolving in parallel, one where the AI / human ratio is 90/10, one where it's maybe 30/70 ?
AI for fast accretion, human for weathering ?