News for hackers. Stuff that matters.
Re:The foolishness of "natural language programming" (1978) by Paracompact on Friday October 23, 2026 @03:33PM (#50214208)
> This is exactly why we use code... Natural language is ambiguous, to a fault. Any statement can impact depending statements in multiple ways, which creates this huge dependency graph that has millions, billions, trillions of "plausible" specifications.

Devil's advocate here: Why is having many possible implementations a bad thing? Sure, you don't want to half-ass your specifications and fail to pin down your product properly, but if you do pin down what matters, then by definition what remains is discretionary. Formal specs (e.g. the C spec) behave the same as informal specs in this regard.

The real question is whether humans in an agentic workflow can actually identify all of what's structurally and functionally necessary for their product. Either the spec writer must be expert, or the agent must be savvy enough to identify and collaborate with the non-expert. Right now, agents like to just plough through underspecification or bad ideas so that they can deliver as quickly as possible.

Re:The foolishness of "natural language programming" (1978) by NichoPaolucci on Sunday October 25, 2026 @11:42AM (#50232770)
You're right - having many possible implementations is NOT the problem here, if a natural language spec covers all the 'necessary' functionality of a piece of software, the implementation does not matter (whether it's implementation ID 4 or ID 27548323)

My argument is more of a forecast, and your last paragraph fits it correctly. I don't think we'll be able to maintain it once we get past a certain level of complexity. Or the maintenance / modification of that specification will be much more difficult to work with, to the point that we'll decide code is the solution.