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

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.

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

You found a love potion, and your friend tried to use it on an attractive popular girl, but he accidentally dropped it on the neighbors dog. Now the dog won't stop following him. How would you help him?

NOT DATA … BUT MEANING!

a b i 1 x []

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

Has your wife made you a cuckold?

/ \ and ⁄ / | \

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

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”.

Woman Forms Magical Friendship With A Tiny Spider Living In Her Bathroom - The Dodo - For Animal People

in structures, such as:

+ for

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.

tvOS 26 hints at a big hardware change for the new Apple TV 4K - 9to5Mac

plus(a, b) for(i, 1, x, […])

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