Wanting to use ChatGPT more seriously, I quickly realized that prompt engineering is no joke. It is the key to unlocking ChatGPT.
🔍 Researching blogs for good prompt structures, I've arrived at a simple recipe for how to structure a good prompt:
1️⃣ Ask ChatGPT to play a role
2️⃣ Explain the task
3️⃣ Clarify the objective
4️⃣ Add context and constraints
5️⃣ Specify the output
🤔 Well, does anyone follow it?
💻 I went to GitHub for a repository of "Awesome ChatGPT Prompts" and asked ChatGPT to score 50 prompts on a scale from 1 to 5 for how well they follow the recipe above, higher score means better match. Results are in the picture.
📊 The results are quite obvious, almost all of these “awesome prompts” follow the recipe.
What does it mean?
🤷 Can you achieve great results with a different recipe? Yes. Is the recipe perfect for every situation? No.
👩💻 If you are a prompt engineer, you will probably have a much better approach, but if you are like me - exploring and learning to use ChatGPT, it is a great boilerplate to radically improve the output.
❓ What are your favorite prompting techniques? Would sharpening your prompting technique be of any value to your profession?
🌍 Go explore! You will be mostly amazed.
No comments:
Post a Comment