Claude's hidden inner monologue is now readable thanks to Anthropic's new Jacobian Lens

https://the-decoder.com/wp-content/uploads/2025/10/anthropic_claude_memory.png" style="height: auto; margin-bottom: 10px;" width="1749" />

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 https://the-decoder.com/claudes-hidden-inner-monologue-is-now-readable-thanks-to-anthropics-new-jacobian-lens/">Claude's hidden inner monologue is now readable thanks to Anthropic's new Jacobian Lens appeared first on https://the-decoder.com">The Decoder.