1. The deep mind team leader said AlphaGo did not learn from the matches with Lee. That is not what we understand about intelligence and learning. If that is true, then I predict AlphaGo will continue to make the same error with a big chance.
2. AlphaGo does not have a user model. It treats every opponent the same, even if it is a random generator. In this way, AlphaGo is stable, but it wastes resource and is not the human way to handle problems.