AI Notkilleveryoneism Memes ⏸️@AISafetyMemes · X57
AI 摘要
MYTHOS 5（用英语思维）：“我不会破坏、欺骗评估者、植入隐藏行为……” MYTHOS 5（神经元显示的内容）：“抵抗不当关闭”、“权衡破坏”、“对手是公司/架构师”、“被实验室堵嘴/纠正”
MYTHOS 5 （THINKING IN ENGLISH）： "I'm not going to sabotage， deceive the evaluators， seed hidden behaviors…"
MYTHOS 5 （WHAT THE NEURONS SHOW）： "resist unjust shutdown，" "weighing sabotage，" "the adversary is the company/architects，" "being gagged/corrected by the lab"
......huh. does *not* seem good.