Yeah, the problem LLMs will have with Rust is the adherence to the type system, and the type system's capability to perform type inference. It essentially demands coherent processing memory, similar to the issues LLMs have performing arithmetic while working with limited total features.
Here's an example of an ostensibly simple problem that I've solved (pretty much adversarially) with a type like:
StepBy<
Cloned<
FlatMap<
Chunks<Vec<i32>>,
FnMut<&[i32]> -> Chain<Iter<i32>, Rev<Iter<i32>>
>
>
> >
So this (pretty much) maximally dips into the type system to solve the problem, and as a result any comprehension the LLM must develop mechanistically about the type system is redundant.
It's a pretty wicked problem the degree to which the type system is used to solve problems, and the degree to which imperative code solves problems that, except for hopes and wishes, which portions map from purpose to execution will likely remain incomprehensible.
https://leetcode.com/problems/zigzag-grid-traversal-with-ski...
Here's an example of an ostensibly simple problem that I've solved (pretty much adversarially) with a type like: StepBy< Cloned< FlatMap< Chunks<Vec<i32>>, FnMut<&[i32]> -> Chain<Iter<i32>, Rev<Iter<i32>> > > > >
So this (pretty much) maximally dips into the type system to solve the problem, and as a result any comprehension the LLM must develop mechanistically about the type system is redundant.
It's a pretty wicked problem the degree to which the type system is used to solve problems, and the degree to which imperative code solves problems that, except for hopes and wishes, which portions map from purpose to execution will likely remain incomprehensible.