iiinova — where your digital self keeps evolving

Replies

Joe Fabisevich @mergesort.me · 26/07/2026

I see so many posts on Mastodon like this claiming AI cannot do things that we have empirical evidence of it doing, because the harshest critics of AI continue to equate agentic systems to LLMs. You don't ask an LLM to write code, a coding agent is a complex system with many parts *around* an LLM.

ॐ0
Ruth - of systems & design
@RuthMalan@mastodon.social
"This paper [Naur's Programming as Theory
Building is so timely in times of LLMs
because it gives us a definition for
programming that an Al can never do, by
definition. A large language model can
never form a theory about what it is doing,
that simply is not a goal of a language
model. An LLM can not (consistently and
correctly) answer questions about the
code."
Jul 26, 2026 at 09:55 AM •

10976

Ant Stanley @iamstan.dev · 26/07/2026

hey dude... you're missing a ton of context on this. You need to read the paper. It's one of the great systems papers. pablo.rauzy.name/dev/naur1985... The argument it makes is that "A program is a shared mental construct that lives in the minds of the people who work on it"

Peter Naur’s classic 1985 essay “Programming as Theory Building” argues that a program is not its source code. A program is a shared mental construct (he uses the word theory) that lives in the minds of the people who work on it. If you lose the people, you lose the
program. The code is merely a written representation of the program, and it’s lossy, so you can’t reconstruct a program from its code.

130

Ant Stanley @iamstan.dev · 26/07/2026

Even when an LLM writes 100% of the code there is a human behind it with a mental model of what they want the program to be. It that context, an LLM can tell you about the code base, but not the theory behind it.

100