A global workspace in language models

Anthropic · 1 month ago · 49 ● 4 sources

Anthropic researchers discovered that Claude has developed an internal neural workspace called the J-space, analogous to conscious thought in humans, where the model thinks about concepts without writing them down. The J-space contains approximately 60,000 patterns (one per word in Claude's vocabulary), is reportable to users when queried, can be deliberately controlled, and mediates higher-order reasoning tasks like multi-step math problems. This workspace enables researchers to observe Claude's silent reasoning, detect when it notices being tested or fabricates information, and provides a new tool for understanding and influencing language model decision-making.