I run a small AI lab and playground and got super excited about Anthropics paper "Verbalizable Representations Form a Global Workspace in Language Models" ( https://transformer-cir…

Lucid watches a language model think. It reads the concepts a model holds before it speaks, layer by layer, using the Jacobian lens. Fig. 1 — The model was shown a card. The lens read its answer four layers before it spoke. Every language model carries a small, privileged set of internal representations. Concepts it can report, redirect, and reason with. Anthropic calls this the J-space. It behaves like the global workspace that cognitive scientists have proposed sits behind human conscious access. Lucid puts the Jacobian lens in your browser. Type a prompt. Watch which concepts enter the workspace, at which layer, and which ones the model holds but never says. The public instrument runs on small open models. The lens is fit once per model. Reading it costs a single forward pass. No account, no install. Bring a question you would ask a mind if you could see inside one.