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: 29.06.2025 00:03
/ \ and ⁄ / | \
in structures, such as:
+ for
Knicks-Pacers: 5 takeaways as Indiana eliminates New York, advances to 2025 Finals - NBA
plus(a, b) for(i, 1, x, […])
Most coding assistants — with or without “modern “AI” — also do reasoning and manipulation of structures.
NOT DATA … BUT MEANING!
Crunch time—we’ll soon find out if Amazon’s launch providers are up to the job - Ars Technica
Another canonical form could be Lisp S-expressions, etc.
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”.
A slogan that might help you get past the current fads is:
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.
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
a b i 1 x []
i.e. “operator like things” at the nodes …