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?

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

/ \ and ⁄ / | \

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

What is red light therapy? Can a normal LED bulb that we use in a room be used for red-light therapy for eyes?

NOT DATA … BUT MEANING!

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”.

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

Broadcom’s AI Bonanza Has Limits - WSJ

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.

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.

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

Olivia Rodrigo Brings Out the Cure’s Robert Smith at Glastonbury for ‘Friday I’m in Love’ and ‘Just Like Heaven’ - Variety

plus(a, b) for(i, 1, x, […])

in structures, such as:

+ for

‘The market is as clueless as the Fed’: Why this trader says stocks could continue to do well for months - MarketWatch

a b 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