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?

/ \ and ⁄ / | \

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

a b i 1 x []

NASA spacecraft captures image of Japanese lander crash site on moon - KIRO 7 News Seattle

in structures, such as:

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

NOT DATA … BUT MEANING!

Brain ‘Reset Wave’ May Explain How ECT Rapidly Relieves Depression - Neuroscience News

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

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.

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

Why do people hate Nickelback so much? What makes them different from other popular bands like Linkin Park, Green Day, etc.? Is it just because they're Canadian or what?

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”.

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.

Harvey Weinstein Was Abused, Defense Says in Retrial Closing Argument - Variety

+ for

plus(a, b) for(i, 1, x, […])