Programming as Theory Building (1985) [pdf]

The trouble with No Code is that your first paragraph is already my job description: I plan out and document and refine the structure of a problem and its architectural solution while simultaneously developing the system itself. The "sufficient explanation of the goals/problem" is the code—anything less is totally insufficient. And once I have the code, it is both the fully-documented problem and the spec for the solution.

I won't pretend to know the final end state for these tools, but it's definitely not that engineers will write natural-language specs and the LLMs will translate them, because code (in varying degrees of high- and low-level languages) is the preferred language for solution specification for a reason. It's precise, unambiguous, and well understood by all engineers on a project. There is no need to be filled by swapping that out with natural language unless you're taking engineers out of the loop entirely.

I was trying to articulate the idea that code generation tools will become increasingly sophisticated and capable, but still be tools that require operation by engineers for maximal effect. I see them as just another abstraction mechanism that will exist within the various layers that separate a dev from the metal. That doesn’t mean the capabilities of such tools are limited to where they are today, and it doesn’t mean that programmers won’t need to learn new ways of operating their tools.

I also hinted at it, but there’s nothing to say that our orchestration of such systems needs to be done in natural language. We are already skilled at representing procedures and systems in code like you said; there’s no reason to think we wouldn’t be adept at learning new languages specialized for specifying higher order designs in a more compact but still rigorous form to codegen systems. it seems reasonable to think that we will start developing DSLs and the like for communicating program and system design to codegen systems in a precise manner. One obvious way of thinking about that is by specifying interfaces and test cases in a rigorous manner and letting the details be filled in - obviously attempts at that now exhibit lots of poor implementation decisions inside of the methods, but that is not a universal phenomenon that will always hold.

Like hiring that one unicorn dev to solve X hard problem isn't a great "theory building" exercise. It can build theories for that one person, but without feedback they're never tested, they're never adopted by the whole team

So you actually NEED juniors, 'stupid' questions, outside points of view, and ways of openly and scientifically evaluating theories instead of defaulting to the authority of supposed experts. You also need to retain seniors who have context and a good historical working definition of the problem.

But a lot of teams are focused on just the next problem and "shipping it". Rather than using "shipping" to help the team develop a better theory of the problem.

The value isn't what's shipped, its the working knowledge of the team.