Interpretability

Anthropic's Jacobian Lens Reads a Model's Silent Thoughts – and Why That Matters

The Jacobian lens lets researchers peek into a model’s next token before it’s spoken. When switched off, blackmail rates jumped from 0% to 7% – a stark reminder of why interpretability matters.

Anthropic Reveals Claude's Hidden Inner Monologue—A Breakthrough for AI Safety

Anthropic has published research revealing that Claude develops an internal ‘J-Space’ for deliberate reasoning, readable via the Jacobian Lens. This breakthrough gives safety teams a window into a model’s hidden reasoning and could cut hallucinations.