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?

Last Updated: 03.07.2025 00:05

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?

+ for

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

in structures, such as:

I Had an Orgasm in the Most Embarrassing Place Possible. Now I’m Confused—and Curious. - Slate Magazine

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:

Is Florida now unsurvivable because it's an oven due to climate change? It's 11:48 am on May 30th and the heat index in SoFla is 100. I can see it going up to over 130 by July.

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

/ \ and ⁄ / | \

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

Has a cop ever said something to you which was completely unexpected?

a b i 1 x []

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!

Adam Sandler will cast Derrick Henry in a movie if he rushes for 2,000 yards - NBC Sports

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”.