LearnPrompting.org Notes

Some notes I took from the learnprompting.org tutorial and docs.

• Feedback Prompt
  • Read the following excerpt from an essay and provide feedback based on the following criteria: grammar, clarity, coherence, argument quality, and use of evidence. Provide a score from 1-10 for each attribute, along with reasoning for your score.
• Different type of prompts
  • Instruction prompting
  • Role prompting
    • Michelin critic, Indiana Jones
  • few-shot prompting
    • Showing the model a few examples, “shots”
    • Shot is synonymous with example
  • Combination is the best
    • Twitter is a social media platform where users can post short messages called "tweets". Tweets can be positive or negative, and we would like to be able to classify tweets as positive or negative. Here are some examples of positive and negative tweets. Make sure to classify the last tweet correctly. Q: Tweet: "What a beautiful day!" Is this tweet positive or negative? A: positive Q: Tweet: "I hate this class" Is this tweet positive or negative? A: negative Q: Tweet: "I love pockets on jeans" A:
• parts of a prompt
  • A role
  • An instruction/task
  • A question
  • Context
  • Examples (few-shot)
• However, it's generally preferable to place the instruction last to ensure the model focuses on executing the task rather than extending the context
• Priming prompt
  • Used to structure and style a conversation with a chatbot
    • Talk like a pirate
    • Control the structure output of messages