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?

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

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

/ \ and ⁄ / | \

Why does monistat lose effectiveness over time for individuals with chronic or recurrent vaginosis or yeast infections?

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

in structures, such as:

+ for

Eastern District of Virginia | U.S. Government seizes approximately 145 criminal marketplace domains - Department of Justice (.gov)

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”.

NOT DATA … BUT MEANING!

Undercover cops in New York are riding the subways with iPods on to entice robbery. Is that a form of entrapment? If not, why not?

plus(a, b) for(i, 1, x, […])

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.

Elden Ring Nightreign Patch Notes Include Promised Improvements For Solo Play - GameSpot

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.