While the LLM rust experiments I've been running make good use of ADTs, it seems to have trouble understanding lifetimes and when it should be rc/arc-ing.

Perhaps these issues have known solutions? But so far the LLM just clones everything.

So I'm not convinced just using rust for a tool built by an LLM is going to lead to the outcome that you're hoping for.

[Also just in general abstractions in rust feel needlessly complicated by needing to know the size of everything. I've gotten so much milage by just writing what I need without abstraction and then hoping you don't have to do it twice. For something (read: claude code et al) that is kind of new to everyone, I'm not sure that rust is the best target language even when you take the LLM generated nature of the beast out of the equation.]