Best AI News — Updated Every 3 Hours
Story Page
← All Stories
Home Industry & Money Story
Industry & Money

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

Via The Decoder
Tuesday, Jul 7, 2026 · 2:46PM
Summary

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. Whe

Continue reading the full article
Read at The Decoder
the-decoder.com
Back to all stories