This might just be a handcrafted prompt framework for handwriting recognition tied in with reasoning - do a rough pass, make assumptions and predictions, check assumptions and predictions, if they pass, use the degree of confidence in their passage to inform what the other characters might be, and gradually flesh out an interpretation of what was intended to be communicated.
If they could get this to occur naturally - with no supporting prompts, and only one-shot or one-shot reasoning, then it could extend to complex composition generally, which would be cool.
I don't see how this performance could be anything like that. There is no way that Google included specialized system prompts with anything to do with converting shillings to pounds in their model.
If they could get this to occur naturally - with no supporting prompts, and only one-shot or one-shot reasoning, then it could extend to complex composition generally, which would be cool.