4 ms·

The author didn't prompt GPT-3 properly. I gave it the prompt below: > The following is a conversation between a human and an AI assistant. The AI assistant is

The author didn't prompt GPT-3 properly. I gave it the prompt below: > 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.

Jackson__ 5y ago
I agree that the author does not appear to have done much of any basic research regarding this topic. It reminds me of articles that were published just after GPT3/GPT2 were released, while also not bringing any unique perspective to the topic. It is saddening me considering it is 2022 now, nearing 2 years after the release of GPT3. Yet journalists retreat the same ground, pretending to have something insightful to say, after what appears to be a 30 minute session with OpenAI's GPT3 Sandbox.
patresh 5y ago
Absolutely. Without giving proper context, the character giving an answer could be a wacky philosopher, a 5 year old child, a person from the 1800s, a liar, an uninterested passer-by, a trickster mage in a novel. If he didn't build the prompt to make it clear that it's a conversation, the context could even be song lyrics for example.

Jackson__ 5y ago

I agree that the author does not appear to have done much of any basic research regarding this topic. It reminds me of articles that were published just after GPT3/GPT2 were released, while also not bringing any unique perspective to the topic. It is saddening me considering it is 2022 now, nearing 2 years after the release of GPT3. Yet journalists retreat the same ground, pretending to have something insightful to say, after what appears to be a 30 minute session with OpenAI's GPT3 Sandbox.

patresh 5y ago

Absolutely. Without giving proper context, the character giving an answer could be a wacky philosopher, a 5 year old child, a person from the 1800s, a liar, an uninterested passer-by, a trickster mage in a novel. If he didn't build the prompt to make it clear that it's a conversation, the context could even be song lyrics for example.