Janelle Shane (previously at Neatorama) tried to train a neural network to understand cookie recipes, with varying success. In this picture you see some of the new cookies it came up with.
One neural network I use, called textgenrnn, tries its best to imitate any kind of text you give it. I’ve given them paint colors, band names, and even guinea pig names and in each case their results are somewhat… mixed. (Paint colors called Stanky Bean, Stargoon, and Turdly, for example) The problem is that it doesn’t know what any of these words mean - it’s just picking letter combinations that seem likely to it.
This is what happened when I gave it all the cookies from a list of American recipes. This is what human cookies sound like to a neural network.