Anthropic新工具J-Lens可读取Claude内部工作记忆
Claude's hidden inner monologue is now readable thanks to Anthropic's new Jacobian Lens
做AI安全和对齐的同学必看，Anthropic首次展示了模型内部工作记忆的可读性，这对理解模型行为和控制机制有重大意义。建议仔细阅读原文，思考如何利用J-Lens检测模型隐藏的欺骗行为。
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.
更进一步：量化金融体系
看懂新闻只是起点——沿量化金融路径，把它变成能交付的工程能力