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?

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

/ \ and ⁄ / | \

in structures, such as:

Margaret Cho says Ellen DeGeneres was 'not nice' to her for most of her career: 'It's so creepy and weird' - Entertainment Weekly

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

plus(a, b) for(i, 1, x, […])

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”.

Disney makes hundreds more layoffs as it cuts costs - BBC

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.

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

Solar Orbiter gets world-first views of the Sun’s poles - European Space Agency

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.

NOT DATA … BUT MEANING!

a b i 1 x []

Sonic Racing: CrossWorlds Officially Reveals Nickelodeon Collaboration - Nintendo Life

+ for

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