Each bar in this ring is one signal inside the model. This rebuild has 64. A real model has thousands. Nine out of ten of them run below notice — the model can't inspect that work, or talk about it.
64 signals · mostly unseenThe rest is different. Anthropic found a way to spot the ideas a model is working with. The six strongest signals light up the glowing sphere — the workspace. This is the part of its thinking the model can actually put into words.
6 / 64 · the workspaceWithin a single answer, a model thinks in layers — and your scroll now moves through them. Early layers hold raw pieces. Later layers build the answer. Watch ideas rise into the workspace and drop back out as you go.
scroll · layer 0 → 32Take FRANCE out of the workspace and put CHINA in. Every answer follows: the capital, the language, the continent — all three flip. The workspace doesn't just show the thought. It steers what the model says.
swap · all three answers flipIn Anthropic's tests, a FAKE idea showed up in the workspace while the model was getting ready to lie — before it said a single word. The same moment plays out here around layer 22. Read the workspace and you catch the lie before the first word.
deception · visible earlyCareful now. It acts like an inner workspace: you can ask what's in it, you can change it, and changing it changes the answers. But it isn't a brain. It works layer by layer, not moment to moment, and it holds only word-like ideas. A strong likeness — not the same thing.
a likeness · not a brain