After a quick content browse, my understanding is this is more like with a very compressed diff vector, applied to a multi billion parameter model, the models could be 'retrained' to reason (score) better on a specific topic , e.g. math was used in the paper
I agree, I don't think gradient descent is going to work in the long run for the kind of luxurious & automated communist utopia the technocrats are promising everyone.
[0]: cartesien.io or Salesforce's WebscaleRL
even some advanced math usually evolves applying patterns found elsewhere into new topics