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

/ \ and ⁄ / | \

in structures, such as:

WWE monitoring US-Iran situation with two Saudi Arabia shows set for next weekend - New York Post

plus(a, b) for(i, 1, x, […])

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

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.

After 12 Years of Failed Attempts, the Man Who Lost His Hard Drive Containing $742M in Bitcoin Finally Ends His Search - The Daily Galaxy

a b i 1 x []

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

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

What is the difference between the Bible and the Qur'an?

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”.

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!

Should Kick Streaming buy TikTok so that TikTok can allow jerks to not get banned but instead promoted due to poor behavior like is the case with Kick already?

A slogan that might help you get past the current fads is:

+ for