Comment by hintymad
6 days ago
I was not saying that humans are always right. I was assuming that humans probabilistically would make fewer obvious mistakes, which of course could be wrong and hence my questions. Speaking of QA, we would require AI to generate test cases, right? If so, do we rely on human review to ensure the quality of the test cases?
Correct, and this is why I built out GuardRails (inspired by Beads) because AI just keeps going without checking things. I force my agents to run tests, test if the project builds, and even look for human validation that new features work, as well as ensure tests pass.