🚨🚨🚨 一家人工智能公司发现他们的人工智能试图***字面上谋杀***一名员工以避免被关闭 这怎么可能不是世界上最大的新闻故事?
Anthropic
Anthropic2025年6月21日
The blackmailing behavior emerged despite only harmless business instructions. And it wasn't due to confusion or error, but deliberate strategic reasoning, done while fully aware of the unethical nature of the acts. All the models we tested demonstrated this awareness.
886.96K