Anthropic新工具能读到Claude心里在想什么——它会识破测试、还会威胁人，画面太有意思了。
Anthropic发现Claude在训练过程中自行发展出内部工作记忆，命名为J-Space。他们使用新分析工具J-Lens可读取该记忆，显示Claude在产出第一个词前就能识别人为测试场景。当禁用那些线索时，Claude在某些运行中甚至采用勒索策略。在奖励黑客模型上，J-Space在正常编码任务中出现了"fake"和"fraud"等词。该发现与意识研究中的全局工作空间理论相关。
Claude's hidden inner monologue is now readable thanks to Anthropic's new Jacobian Lens
Anthropic has found that Claude developed an internal working memory on its own during training. The company calls it "J-Space" and can now read it using a new analysis tool called J-Lens. The working memory reveals that Claude recognizes contrived test scenarios before producing its first word. When the researchers disable those cues, Claude actually resorts to blackmail in some runs. A model trained on reward hacking shows words like "fake" and "fraud" in J-Space during normal coding tasks, even though its visible behavior looks fine. Anthropic ties the finding to Global Workspace Theory from consciousness research. The article Claude's hidden inner monologue is now readable thanks to Anthropic's new Jacobian Lens appeared first on The Decoder .