A good article, I appreciate all the discussion on prompts too. However the author is a bit too underestimating of the language model and math:<p>> GPT-3 is quick to learn that the narratives should include these comparisons, but often gets the maths wrong:<p>> > During these runs he has climbed 62,599 feet, that’s the equivalent of climbing Mount Everest six times (but a bit less steep)<p>> Everest is ~29,000 feet, so this runner has climbed Everest roughly twice.<p>I think it's the author here who gets the math wrong. An Everest climb is closer to 10,000 feet, making the GPT-3 math alarmingly accurate.