I'm sure there are those that disagree strongly, but I feel like this isn't as much an advance for AI as it is another interesting combination of filtered human-structured knowledge and computation power. Just as Deep Blue brute-forced chess, this is mostly a brute-force of another, albeit more open-ended domain (i.e. Q/A).

I'm not arguing that this isn't an impressive accomplishment, but that the statistical-learning stream of research is likely a conceptual local optima that yields the best results in the near term but is probably unrelated to the way we ultimately achieve a creative, general AI.