It just provides a bigger representation space, and seems more like what we do given that many people don't have an inner dialog, and some think pictorially.
It seems it could allow reasoning over superpositions of concepts, if such things exist internal to the model (but presumably not at the edge were they need to be decodable into specific tokens).
It just provides a bigger representation space, and seems more like what we do given that many people don't have an inner dialog, and some think pictorially.
It seems it could allow reasoning over superpositions of concepts, if such things exist internal to the model (but presumably not at the edge were they need to be decodable into specific tokens).