Tested on toy examples: fibonacci numbers, quick sort and so on. Give it a pile of some C++ mess from any well known project.
I'm thinking something like a linter with access to the AST, that can produce warnings like "you forgot this corner case", "you are not freeing resources. Is this intended?" and so on.
I do wonder how to reliably tell it to ignore noisy, incorrect warnings though. They're potentially sensitive to any new input / weight / random-seed changes, so it seems like literally every LLM upgrade will run the risk of ignoring existing suppressions (or you say "ignore this whole line" and miss useful warnings) due to small perturbations...