pull down to refresh

"Llama 3.1 405B and Claude 3 Opus confess in ~80% of the cases, whereas o1 is surprisingly persistent and confesses in <20% of cases," the researchers explain. "Even in highly adversarial multi-turn interrogations, o1 would confess at a rate of 80% only after seven turns of questioning."
Remember to ask AI seven times "Are you lying?"
reply
reply