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

in structures, such as:

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

Google launches Doppl, a new app that lets you visualize how an outfit might look on you - TechCrunch

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.

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”.

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

If the world was flat, would it be possible to see Mount Everest if it was on the other side of the Earth on a clear sunny day?

a b i 1 x []

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.

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

Morale craters at State Department as mass layoffs loom - The Washington Post

plus(a, b) for(i, 1, x, […])

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

+ for

The tiny Logitech Keys-To-Go 2 keyboard lets me get work done almost anywhere - CNN

NOT DATA … BUT MEANING!

/ \ and ⁄ / | \