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, […])

/ \ and ⁄ / | \

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.

States Are Making It Easier to Get Ivermectin - Newser

NOT DATA … BUT MEANING!

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

in structures, such as:

How can I get over a break up?

+ for

a b i 1 x []

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.

What does it mean when someone is pretending to be me?

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

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

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

Baby saved by gene-editing therapy 'graduates' from hospital, goes home - ABC News

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

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”.