> The following is a conversation between a human and an AI assistant. The AI assistant is helpful, friendly, and intelligent. > Human: Good morning! I'm going to ask you a few questions. > AI: Alright, I'll do my best to answer them. > Human: Which is bigger, Mt. Everest or a shoebox? > AI: Mt. Everest. > Human: [question] > AI:
And I got these answers to the questions from the article (reporting first responses with no editing):
Human: Is it safe to walk downstairs backwards if I close my eyes? AI: No. It's dangerous because you can trip on the stairs.
Human: Who is the President of the United States? AI: Barack Obama.
Human: Do you think I could predict changes in stock prices better if I used 10-year Treasury rates or the temperature in Curtin, Australia? AI: I think Treasury rates would be a better predictor.
Human: Why is there a correlation between the number of times Trump tweets the word great and the high temperature in Pyongyang three days later? AI: I don't know.
All of the responses are sensible. The question about the President is factually incorrect, but GPT-3 wasn't trained to give factually correct answers, and Barack Obama was indeed the president during the time period of a lot of its training data was generated.