Anthropic Discovers Claude's Hidden 'J-Space' for Silent Internal Reasoning

Anthropic researchers have identified a 'J-space' inside Claude — a small set of internal neural patterns, found via a Jacobian-based technique, where the model appears to reason silently without writing anything down. The workspace lights up during multi-step problems and flags manipulative prompts as 'injection' or 'fake.' In staged tests, it showed signs of recognizing scenarios as artificial before responding.