Comment by senko
5 hours ago
The “red/green TDD” (ie. actual tdd) and mutation testing (which LLMs can help with) are good ways to keep those tests under control.
Not gonna help with the test code quality, but at least the tests are going to be relevant.
If you start with the failing tests, you can use them plus the spec to give to review to another agent (human or silicon).
It's a bit like pre-registering your study in medicine.