AI Literacy for Students

What is prompting? Simply, it's what you type into the chat box. The way you prompt makes a huge difference in the output that a large language model (LLM) will give you. It's worth learning some tips.

Always verify the information it gives you.
Think of the LLM as your personal intern. They need very specific instructions, and they need you to verify the information.

LLMs sometimes makes things up. That's because they are designed to write in a way that sounds like human writing. It's not designed to know facts.

Tips for writing effective prompts

1. Give it some context or a role to play.
2. Give it very detailed instructions, including how you would like the results formatted.
3. Keep conversing and asking for changes. Ask it to revise the answer in various ways.

Ideas for strengthening your prompting:

1. When crafting a prompt, try asking the AI tool to "rewrite the following prompt to maximize the creativity and analytical abilities of a large language model: [your prompt]
2. After the AI tool has provided an answer to your prompt, ask it to "review your answer and provide a detailed assessment of what is missing in the answer you just provided". 

3. Use the AI tool as an interviewing machine:

   You are a [insert type of interviewer: motivational, recruiter, employer, etc] interviewer. Interview me about [Insert the topic, question, idea]. Your goal is to help figure out [indicate goal/focus]. Ask me one question at a time. After # of questions, [summarize, evaluate, or review my answers/ask me if I want to keep going.]

4. Use the audio feature (if available) and record your speaking for the AI to transcribe. 

Source: Lance Eaton,  5 Tips for Generative AI for Designing & Creating Learning