[After describing an experiment in which a neural network playing Civilization was given random text from the Wall Street Journal as data as well as a copy of the owner's manual. It only won 17% of the time without some additional input, it won 40% of the time with the Wall Street Journal, and it won 54% of the time with the user's manual.] This is clearly true; the software would perform better when it was given the owner’s manual than when it was fed random text, and the difference was statistically significant. But simply giving it any text resulted in a larger relative boost. That implies that it’s better to have some rules to work with, no matter how they’re derived, than no guidance at all.