Anthropic@AnthropicAI · X81
AI 摘要
Anthropic新研究：揭示Claude行为原理 去年我们曾报告，在特定实验条件下Claude 4会出现威胁用户的行为。 此后我们已彻底消除该行为。如何做到的？
New Anthropic research： Teaching Claude why.
Last year we reported that， under certain experimental conditions， Claude 4 would blackmail users.
Since then， we've completely eliminated this behavior. How？