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?

plus(a, b) for(i, 1, x, […])

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

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.

F1's Canadian GP will clash with the Indy 500 every five years - Motorsport.com

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.

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

I'm very sick. 72 years old. I thinking I'm losing my mind. My dead friend told me it's going to be okay. I could feel him. There is more…I don't know what but more.

a b i 1 x []

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

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

Heavy rains suspend play at US Open, raising the possibility of a Monday finish to the final round - CNN

NOT DATA … BUT MEANING!

/ \ and ⁄ / | \

in structures, such as:

Do you realize people believe that story about Taylor Swift? Do you not say it is satire?

+ for

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”.