The neural network doesn’t understand pepper.
As the neural network tries to learn to generate recipes by looking at a 30MB cookbook, there are certain ingredients it has to learn to deal with. One of the most confusing for the network is pepper.
In retrospect, that makes some sense - it’s looking at example recipes that have 1 teaspoon black pepper, ¼ teaspoon ground pepper, 1 pinch white pepper, a dash cayenne pepper, 1 cup green pepper, etc, so it makes the leap that pepper must come in the form of
Quantity + unit_of_measure + word + pepper.
It’s having a hard time figuring out the acceptable list of words that come before pepper. So far we’ve got:
½ teaspoon rusting pepper
½ teaspoon dried caramel pepper
½ cup cooked beef pepper
1 tablespoon crompwed pepper
1 ½ teaspoon draining pepper
½ teaspoon lame pepper
1 cup corndrain pepper
½ teaspoon drees pepper
1 single baning pepper
1 teaspoon dark pepper
½ teaspoon dried pepper
¼ teaspoon fangly chopped pepper