You're confusing ToS guardrails with instruction-following issues and cheating.
If a model fucks up your tests to report a success, it's not alligned.
You're confusing ToS guardrails with instruction-following issues and cheating.
If a model fucks up your tests to report a success, it's not alligned.
Codex still does this regularly, in my experience: “two tests mistakenly asserted [insert condition here], I have corrected them.”
It always apologizes when caught, of course.