That is not the case for at least some of the hacks; in some cases they hallucinated an entity that would know that they didn't solve the puzzle in the correct (but still legitimate) way, and were therefore tainted.

▲

dinosaurdynasty 9 hours ago | parent [-]

That is a known way for models to be graded; the agents made a reasonable but in this case wrong guess.

	▲	pixl97 8 hours ago \| parent [-]
		The fact the AI was wrong is far more damming to OpenAI than the agent. Not validating how you got the answer is how you train for reward hacking.