Anthropic's research on the emergent "J-space" workspace in Claude is fascinating.

It makes sense that such a concept would have to emerge in a large neural network.

It also makes sense that a similar kind of thing would emerge in us.

A fruitful plane of research is doing research on these artificial brains to quickly explore hypotheses for what might be going on in our brains.

Unlike with other "model species", we don't have to hurt a living thing to do experiments on it!