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?

in structures, such as:

plus(a, b) for(i, 1, x, […])

NOT DATA … BUT MEANING!

How Apple Created a Custom iPhone Camera for ‘F1’ - WIRED

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

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”.

/ \ and ⁄ / | \

Prince William’s friend Sunjay Kapur dead at 53 after swallowing bee during polo match - Page Six

+ for

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.

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

Mondo Duplantis breaks pole vault world record for 12th time - NBC Sports

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.

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

a b i 1 x []

What is the reason for writing X^2 as XX instead of X*X?

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

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