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: 02.07.2025 00:15
plus(a, b) for(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.
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”.
+ for
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 []
in structures, such as:
/ \ and ⁄ / | \
Another canonical form could be Lisp S-expressions, etc.
—— indirects on kuorans, irl and idols
NOT DATA … BUT MEANING!
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.
i.e. “operator like things” at the nodes …
A slogan that might help you get past the current fads is:
Most coding assistants — with or without “modern “AI” — also do reasoning and manipulation of structures.