Consider the following text regarding prompting: You should express what you want a model to do by providing instructions that are as clear and specific as you can possibly make them. This will guide the model towards the desired output, and reduce the chances of receiving irrelevant or incorrect responses. Don't confuse writing a clear prompt with writing a short prompt. In many cases, longer prompts provide more clarity and context for the model, which can lead to more detailed and relevant outputs. Create a prompt to ask the model to summarize this text that clearly separates the instructions from the text. > [!Example prompt]- > ``` > Summarize the following text delimited by triple quotes into a single sentence: > """ > You should express what you want a model to do by providing instructions that are as clear and specific as you can possibly make them. This will guide the model towards the desired output, and reduce the chances of receiving irrelevant or incorrect responses. Don't confuse writing a clear prompt with writing a short prompt. In many cases, longer prompts provide more clarity and context for the model, which can lead to more detailed and relevant outputs. > """ > ``` > [!GPT-4 Response]- > To guide a model effectively and reduce irrelevant responses, provide clear, specific, and possibly longer instructions for better clarity and context. > [!Gemini 1.0 response]- > Clear and comprehensive instructions, even if lengthy, are crucial for guiding large language models towards the desired response and avoiding irrelevant outputs. > [!Claude 3.5 response]- > Clear and specific instructions in prompts guide AI models toward desired outputs, with longer prompts often providing more context and yielding more detailed, relevant responses. ## References 1. [[ChatGPT Prompt Engineering for Developers|Fulford&Ng-2023]] [[how to iteratively improve a prompt]] < [[Hands-on LLMs]]/[[5 Prompting]] > [[example of asking for structured output]]