Wonder what LLM op is using? I find that using one LLM to review the other catches a lot of this. For example having Codex do the work then CC /simplify and /code-review. Claude md has three lines one of which is DRY.
You still have to look at the diffs because it won’t have external knowledge to the codebase or make the best decisions.
You still have to look at the diffs because it won’t have external knowledge to the codebase or make the best decisions.
It does find bugs and keep things simple.