What are your thoughts on a future where code is represented as a structured model, rather than text? Do you think that AI-powered coding assistants benefit from that?

Long ago in the 50s this was even thought of as a kind of “AI” and this association persisted into the 60s. Several Turing Awards were given for progress on this kind of “machine reasoning”.

First, it’s worth noting that the “syntax recognition” phase of most compilers already does build a “structured model”, often in what used to be called a “canonical form” (an example of this might be a “pseudo-function tree” where every elementary process description is put into the same form — so both “a + b” and “for i := 1 to x do […]” are rendered as

in structures, such as:

There Are (Allegedly) Two Words That Describe How Ryan Reynolds And Blake Lively Are Feeling After Bombshell Update In Baldoni Defamation Suit - Cinemablend

It’s important to realize that “modern “AI” doesn’t understand human level meanings any better today (in many cases: worse!). So it is not going to be able to serve as much of a helper in a general coding assistant.

/ \ and ⁄ / | \

Most coding assistants — with or without “modern “AI” — also do reasoning and manipulation of structures.

How do I become an intelligent man?

A slogan that might help you get past the current fads is:

NOT DATA … BUT MEANING!

i.e. “operator like things” at the nodes …

‘The Last Of Us Part II’ Insists There’s Artistry In All Of Its Violence - Defector

a b i 1 x []

Another canonical form could be Lisp S-expressions, etc.

These structures are made precisely to allow programs to “reason” about some parts of lower level meaning, and in many cases to rearrange the structure to preserve meaning but to make the eventual code that is generated more efficient.

Janet Petro's Embrace The Challenge Update 27 June 2025: "Voluntary Workforce Shaping" - NASA Watch

plus(a, b) for(i, 1, x, […])

+ for