- OptiMAIL
- Posts
- đ§âđ»đ - Youâre using ChatGPT wrong!
đ§âđ»đ - Youâre using ChatGPT wrong!
This is how to fix it.
âIâm using it wrong?â
Potentially. Rubbish in = rubbish out đïž
Letâs start with a simple thought experiment, if you wanted a colleague or an employee to do something well, youâd provide them with a clear set of instructions, wouldnât you? The concept is exactly the same in this situation.
Utilising Generative AI Chatbots optimally is one of the easiest ways to enhance your workflow using the latest AI technology, whether youâre using free tools like ChatGPT 3.5/Google Gemini or paid plans like ChatGPT Plus and Microsoft Copilot Pro.
Todayâs newsletter focuses on the art of Prompt Engineering. By the end, youâll understand:
The different types of prompting.
How to craft any prompt for any Large Language Model (LLM) - ChatGPT is one of these.
What an ideal prompt looks like.
âWhat are the different types of prompts?â
Iâm glad you asked!
The framework Iâll explain involves N-Shot Prompts, where N is the number of examples of the âideal responseâ that you provide to the LLM.
Zero-Shot Prompting:
No example provided. N=0.
Best for brainstorming, asking a question, or when you donât have any specific examples for your desired response to a task.
âDetermine the sentiment of this sentence: I love sunny days and ice cream.â
One-Shot Prompting:
One example provided. N=1.
Most efficient when you have a single example that closely represents the task or output you desire.
âTranslate these sentences into Spanish. Example: English: âThe apple is red.â Spanish: âLa manzana es roja.â Now translate: âThe sky is blue.ââ
Few-Shot Prompting:
More than one example. N>=2.
Ideal for longer or more complex tasks.
âClassify these animals into âmammalâ or âbirdâ: Example 1: Animal: âElephantâ Type: âMammalâ Example 2: Animal: âEagleâ Type: âBirdâ Now classify: âDolphinââ
Understanding the different benefits and uses of these prompt types will get you halfway there, but the âsecret ingredientâ is implementing a repeatable prompt structure to clarify your expectations and improve the LLMs understanding.