Comment by Keats
5 days ago
I'm not sure if it's Rust related. It manages to write the Rust code just fine, it's just that it doesn't seem to
- think of everything that is needed for a feature (fixable via planning at the beginning)
- actually follow that plan correctly
I just tried with a slightly big refactor to see if some changes would improve performance. I had it write the full plan and baseline benchmarks to disk, then let it go in yolo mode. When it was done it only implemented something like half of the planning phases and was saying the results look good despite all the benchmarks having regressed.
I get a ton of value out of Claude Code but you just listed a lot of things I've found LLMs/agents not very good at.
- Rust
- Big refactors
- Performance improvements
- Yolo-mode, especially if you aren't skilled yet at prompting and knowing which things the LLM will do well and which will need supervision
I've encountered human Rust programmers that exhibit this behavior. I think that Rust may be falling victim to its own propaganda, as developers come to believe that the borrow checker will fix their logic errors, not just flag up memory management that's at risk of buffer overflow or UAF.