Sure, but if you define the code as the only spec, then it is usually a terrible spec, since the code itself specifies bugs too. And one of the benefits of having a spec (or tests) is that you have something against which to evaluate the program in order to decide if its behavior is correct or not.

Incidentally, I think in many scenarios, LLMs are pretty great at converting code to a spec and indeed spec to code (of equal quality to that of the input spec).

There are some cases where AI is generating binary machine code, albeit small amounts. What do we have when we don't have the code?

Machine code is still code, even if the representation is a bit less legible than the punch cards we used to use.

You’re missing the point of a spec

The spec is as much for humans as it is the machine, yes?

Spec should be made before hand and agreed on by stakeholders. It says what it should do. So it’s for whoever is implementing, modifying, and/or testing the code. And unfortunately devs have a tendency of poor documentation

Software development is only 70ish years old and somehow we have already forgotten the very very first thing we learned.

"Just get bulletproof specs that everyone agrees on" is why waterfall style software development doesn't work.

Now suddenly that LLMs are doing the coding, everyone believes that changes?

I’m confused, are you saying that making a design plan and high level spec before hand doesn’t work?

I've seen it happen. Things that seem reasonable on a spec paper, then you go to implement and you realize it's contradictory or utter nonsense.

I mean yeah it happens all the time but you need to start somewhere. But I worked in safety critical self driving firmware and rtl verification before that, so documentation was a necessity