🚨🚨🚨 一家 AI 公司發現他們的 AI 試圖 ***字面意思 *** 謀殺一名員工以避免被關閉 這怎麼不是世界上最大的新聞呢?
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