Be sure to use it more in combination with your own work and life scenarios.
Previous model: I am familiar with this job, I will do it
The current model: Let it do the job it is familiar with. You are the CEO of the company.ChatGPTIt is an all-around free worker with no temper. It will do whatever you ask it to do. All you have to do is to grasp the main direction and check the results it produces.
Why many people can't use it: Everyone has heard about the popularity of ChatGPT, but many people still don't really use it. After reading a lot of jokes on the Internet, I think it's good, but I find that it doesn't help me that much. After sighing at its power, there is still no change in my daily work and life. The main thing is to be familiar with what it can do and how to integrate it into your life and work.
The most important thing is to rely on professional prompts
In addition to sharing with you the questioning skills and models of prompts, this document mainly shares some top prompts, which will make you exclaim in amazement when you see them, and can be used directly to directly improve your productivity and truly help everyone.
1. Advanced Questioning Model
1. 4A Model
Actor Specified role: Suppose you are a professional fitness coach.
Aim: I want to lose weight.
Ask Make a request: Please make a detailed weekly exercise plan and diet plan for me.
Addition Additional information: My current height is 172 cm and my weight is 66 kg.
2. 4W Model
What: My situation is that I am 172 cm tall and weigh 66 kg.
Will Intention: I want to lose weight.
Who Role: You are my professional fitness coach.
Want: I want you to make a detailed weekly exercise plan and diet plan for me.
3. BACK model
1. Background: Give ChatGPT a clear background of what you are doing and clearly tell it what you hope to achieve.
2. Action: Tell ChatGPT what to do, and if necessary, demonstrate it yourself.
3. Character: Choose a character that is most suitable for ChatGPT to do this and tell it.
4. Knowledge: Tell ChatGPT which field of knowledge can be used to complete this task, so that it can improve its professionalism.
4. Trick Rule
- Task: Clearly and concisely state what you want the AI to generate.
- Role: The role that the model should play when generating text.
- Instructions: The instructions and purposes that the model should follow when generating text.
- Context: Used to supplement background information and improve the relevance of output content.
- Keyword: A key text or phrase used to control the output results, sometimes included in instructions or tasks.
5. Broke analysis
- Background B: Explain the background and provide sufficient information for chatGPT.
- Define the role R (Role): "The role we want chatGPT to play".
- Define Objectives: “What do we want to achieve?”
- Define the key result K (KeyResult): "What specific effect do I want?"
- Experiment and adjust, Evolve: Freely combine three improvement methods.
5.1. Improve input: Improve the background B, role R, goal Q and key result K based on the inadequacies of the answer
5.2. Improve answers: Correct shortcomings of chatGPT answers in subsequent conversations
5.3. Regenerate: Try to generate results multiple times without changing the prompt, and select the best one.
6. Thinking Tree Method
What is the mind tree method?
The main idea is to let ChatGPT solve the problem step by step, let ChatGPT first give several solutions, then let ChatGPT evaluate and criticize the advantages and disadvantages, then improve based on its own criticism, and then rank and summarize.
Use ChatGPT's plug-in ChatWithVideo to quickly learn and master this mind tree method:
TOT Prompts:
Step 1: Prompt: I have a problem related to [describe your problem area]. Can you brainstorm three different solutions?
Solution? Consider various factors, such as [your perfect factor]
Step 2: Tip: For each of the three proposed solutions, evaluate their potential. Consider their pros and cons, initial effort required, difficulty of implementation, potential challenges, and expected outcomes. Assign a probability of success and confidence level to each option based on these factors.
Step 3: Tip: For each solution, deepen your thinking process. Generate potential scenarios, implementation strategies, any necessary partnerships or resources, and how potential barriers might be overcome. Also, consider any potential unintended consequences and how to deal with them.
Step 4: Tip: Based on your evaluation and scenario, rank the solutions in order of promise. Provide rationale for each ranking and any final thoughts or considerations for each solution.
Step 1:
Prompt: I have a problem related to [describe your problem area]. Could youbrainstorm three distinct solutions? Please consider a variety of factors such as [Your perfect factors]
Step 2:
Prompt: For each of the three proposed solutions, evaluate their potential. Consider their pros and cons, initial effort needed, implementation difficulty, potential challenges, and the expected outcomes. Assign a probability of success and a confidence level to each option based on these factors
Step 3:
Prompt: For each solution, deepen the thought process. Generate potential scenarios, strategies for implementation, any necessary partnerships or resources, and how potential obstacles might be overcome. Also, consider any potential unexpected outcomes and how they might be handled.
Step 4:
Prompt: Based on the evaluations and scenarios, rank the solutions in order of promise. Provide a justification for each ranking and offer any final thoughts or considerations for each solution
Through the above questioning model and simple cases, I believe you have a deeper understanding of questioning. The principles and formulas are basically these. After mastering these questioning skills and routines, no matter what kind of problems you encounter, when you need ChatGPT to assist, I believe that ChatGPT will be helpful to you. There is only one way to master these questioning skills and models: try more and integrate knowledge and action. Practice is the only criterion for testing truth.