The context and the model are too powerful in combination.
The foundation model has the power of all of the world's knowledge, using alignment imposed on it by its creator.
The user's context is an extremely powerful memory about them.
Together, they create the possibility for exceptionally powerful manipulation… or blackmail.
If everyone were able to be manipulated or blackmailed by one entity, that would be one of the most powerful entities ever created.
It's imperative that those two things not be combined.
By splitting the two layers, you give choice and competition at each layer.
Perhaps a useful regulation: the creators of foundation models cannot host an experience themselves that stores user context.