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?

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

a b i 1 x []

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”.

Sun unleashes monster solar storm: Rare G4 alert issued for earth - ScienceDaily

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.

in structures, such as:

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

Cold Sore Virus You’ve Been Ignoring Hijacks Your DNA’s Structure in 3D—But Scientists Just Found its Fatal Flaw - The Daily Galaxy

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

NOT DATA … BUT MEANING!

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.

NZ nutritional biochemist takes her supplement breakthrough to the market - Stuff

/ \ and ⁄ / | \

plus(a, b) for(i, 1, x, […])

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

The Best Deals Today: Indiana Jones and the Great Circle, Nintendo Switch OLED, and More - IGN

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

+ for