GPT-3 learns these rules by itself.
Just a hint - each of these "facts" or "rules" mean slightly something else depending on the context they are used in. This context is not hard-encodable because it slightly mutates with every new information learned or forgotten.
will sublime conclusions made by GPT-3 EVER be trusted if the reasoning to its conclusion is not understood by a human? perhaps the gestalt of gpt3 implies a meta gpt3 that could derive human grokkable explains of its "dumber" self. or maybe not.