Comment by drodgers
6 days ago
> "LLMs can’t write Rust"
This really doesn't accord with my own experience. Using claude-code (esp. with opus 4) and codex (with o3) I've written lots of good Rust code. I've actually found Rust helps the AI-pair-programming experience because the agent gets such good, detailed feedback from the compiler that it can iterate very quickly and effectively.
Can it set up great architecture for a large, complex project from scratch? No, not yet. It can't do that in Ruby or Typescript either (though it might trick you by quickly getting something that kinda works in those languages). It think that will be a higher bar because of how Rust front-loads a lot of hard work, but I expect continuing improvement.
I agree, the latest models are not bad at Rust. Most issues I have when writing LLM-assisted Rust code are related to dependencies.
There are a lot of v0.x.x crates in Rust with frequent updates and breaking changes. As LLMs "learn" from code in the wild, they are exposed to different way to use the same crate and thus fail to produce working code "from memory".
But as soon as you explain how to use it with the latest syntax, they are able to fix the code.