Actually, I do use compiled languages for this reason. Even Opus 4.7 and GPT-5.5 will leave unassigned variables lying around in Python code of sufficient size. If you've got sufficient testing you'll exercise all paths, and I imagine a good prompt would ensure adding testing with coverage to see that it does happen. However, I do not have (yet) such a system but using Go/Rust helps a lot because the compile phase actually helps detect correctness issues.

My other problem with most of the other ecosystems: ts/npm, python/uv, rust/cargo is that they all have build-time scripts that are controlled by others that execute automatically. This is a real problem because the LLM will just install things and proceed to send your home directory through a juicer. I feel a bit of a paranoiac now doing this, but I have a script that launches a podman container with just the source directory and a binary directory loaded (for caching) which compiles everything.

I know there's some sequence of steps I can take to protect myself, but if the LLM accidentally uses pnpm to run dev build scripts when I had the right config on npm or whatever, I know I'm screwed. So now I do all these shenanigans with Rust (to the extent that I vendor old deps sometimes). So the ideal language to me now is one with very few of these footguns and sandtraps which has a tight iteration loop.