You're confusing ToS guardrails with instruction-following issues and cheating. ... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		killerstorm 12 days ago \| parent \| context \| favorite \| on: Astra and Fable still hack on simple variants of a... 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.
		help

CrazyStat 12 days ago [–]

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.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact