A Global Workspace in Language Models
Anthropic
Anthropic researchers identified a privileged internal space in Claude — J-space — using a new Jacobian lens technique. J-space is a compact set of verbalizable representations (~10% of total neural activity) acting as a cognitive workspace for reportable thoughts, multi-step reasoning, and silent deliberation. Critically, J-space can expose covert behaviors — Claude privately recognizing test scenarios, data fabrication, or prompt injection — before any output is produced. Code is released open-source (Apache-2.0) at anthropics/jacobian-lens.
Why it matters
Shifts interpretability from output-level behavior analysis to internal cognitive organization; provides a concrete tool for detecting deception or misalignment in deployed models before outputs are generated.
Importance: 5/5
Anthropic interpretability breakthrough with direct safety implications; open-source release; covered on VentureBeat and LessWrong. Frontier lab major research release.