that definitely seems like a useful thing to measure! I looked into an example here: https://www.alignmentforum.org/posts/22GrdspteQc8EonMn/a-very-crude-deception-eval-is-already-passed
that definitely seems like a useful thing to measure! I looked into an example here: https://www.alignmentforum.org/posts/22GrdspteQc8EonMn/a-very-crude-deception-eval-is-already-passed