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: 23.06.2025 01:17
A slogan that might help you get past the current fads is:
/ \ and ⁄ / | \
+ 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
plus(a, b) for(i, 1, x, […])
in structures, such as:
NHS first in world to roll out ‘revolutionary’ blood test for cancer patients - NHS England
i.e. “operator like things” at the nodes …
Another canonical form could be Lisp S-expressions, etc.
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.
NOT DATA … BUT MEANING!
Most coding assistants — with or without “modern “AI” — also do reasoning and manipulation of structures.
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”.
How likely is it that Israel would target targets in Iran if there is a full-blown conflict?
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.
a b i 1 x []