How to be a Prompt Engineer 101
The shortest and most comprehensive guide
1. start with an explanation
Make a description and character situation at the beginning of the Prompt
Error example:
Please help me read the following code:
{your input here}
Correct example:
2. Prompt to describe the situation
In the prompt, it is necessary to describe the context, result, length, format and style as much as possible
Error example:
Write a short story for kids
Correct example:
3. gives output in the format
If you are doing data analysis, please give the input template of the format
Error example:
Extract house pricing data from the following text.
Text: """
{your text containing pricing data}
"""
Correct example:
4. Add some example questions and answers
Sometimes adding some question and answer examples can make GPT more intelligent
Correct example:
The question and answer example is also a standard template example in fine-tune
5. Simplify the sentence and clarify the purpose
Keep your words as short as possible and don't say useless content
Error example:
ChatGPT, write a sales page for my company selling sand in the desert, please write only a few sentences, nothing long and complex
Correct example:
6. Good at using introductory words
Error example:
Write a Python function that plots my net worth over 10 years for different inputs on the initial investment and a given ROI
Correct example:
The shortest and most comprehensive guide
1. start with an explanation
Make a description and character situation at the beginning of the Prompt
Error example:
Please help me read the following code:
{your input here}
Correct example:
Now let's play the role, you are a senior information security engineer, I will give you a piece of code, please help me read the code and point out where there may be security vulnerable.
Text: """
{your input here}
"""2. Prompt to describe the situation
In the prompt, it is necessary to describe the context, result, length, format and style as much as possible
Error example:
Write a short story for kids
Correct example:
Write a funny soccer story for kids that teaches the kid that persistence is the key for success in the style of Rowling.3. gives output in the format
If you are doing data analysis, please give the input template of the format
Error example:
Extract house pricing data from the following text.
Text: """
{your text containing pricing data}
"""
Correct example:
Extract house pricing data from the following text.
Desired format: """
House 1 | $1,000,000 | 100 sqm
House 2 | $500,000 | 90 sqm
... (and so on)
"""
Text: """
{your text containing pricing data}
"""4. Add some example questions and answers
Sometimes adding some question and answer examples can make GPT more intelligent
Correct example:
Extract brand names from the texts below.
Text 1: Finxter and YouTube are tech companies. Google is too.
Brand names 2: Finxter, YouTube, Google
###
Text 2: If you like tech, you'll love Finxter!
Brand names 2: Finxter
###
Text 3: {your text here}Brand names 3:The question and answer example is also a standard template example in fine-tune
5. Simplify the sentence and clarify the purpose
Keep your words as short as possible and don't say useless content
Error example:
ChatGPT, write a sales page for my company selling sand in the desert, please write only a few sentences, nothing long and complex
Correct example:
Write a 5-sentence sales page, sell sand in the desert.6. Good at using introductory words
Error example:
Write a Python function that plots my net worth over 10 years for different inputs on the initial investment and a given ROI
Correct example:
# Python function that plots net worth over 10
# years for different inputs on the initial
# investment and a given ROI
import matplotlib
def plot_net_worth(initial, roi):😁1
data-visualization-with-python-create-an-impact-with.epub
16.5 MB
Data Visualization with Python
Mario Dobler, 2019
Mario Dobler, 2019
Quantitative Finance With Python).pdf
11.7 MB
Quantitative Finance with Python
Chris Kelliher, 2022
Chris Kelliher, 2022
👍5🏆1
Ansible From Beginner to Pro.pdf
5.2 MB
Ansible
Michael Heap, 2016
Michael Heap, 2016
Advanced Concepts in Operating Systems (Indian Edition).pdf
331.2 MB
Advanced Concepts in Operating Systems
Mukesh Singhal, 2008 (scanned)
Mukesh Singhal, 2008 (scanned)
👍4🔥1
Data science is a multidisciplinary field that combines techniques from statistics, computer science, and domain-specific knowledge to extract insights and knowledge from data. Here are some essential concepts in data science:
1. Data Collection: The process of gathering data from various sources, such as databases, files, sensors, and APIs.
2. Data Cleaning: The process of identifying and correcting errors, missing values, and inconsistencies in the data.
3. Data Exploration: The process of summarizing and visualizing the data to understand its characteristics and relationships.
4. Data Preprocessing: The process of transforming and preparing the data for analysis, including feature selection, normalization, and encoding.
5. Machine Learning: A subset of artificial intelligence that uses algorithms to learn patterns and make predictions from data.
6. Statistical Analysis: The use of statistical methods to analyze and interpret data, including hypothesis testing, regression analysis, and clustering.
7. Data Visualization: The graphical representation of data to communicate insights and findings effectively.
8. Model Evaluation: The process of assessing the performance of a predictive model using metrics such as accuracy, precision, recall, and F1 score.
9. Feature Engineering: The process of creating new features or transforming existing features to improve the performance of machine learning models.
10. Big Data: The term used to describe large and complex datasets that require specialized tools and techniques for analysis.
These concepts are foundational to the practice of data science and are essential for extracting valuable insights from data.
Join for more: https://t.iss.one/datasciencefun
ENJOY LEARNING 👍👍
1. Data Collection: The process of gathering data from various sources, such as databases, files, sensors, and APIs.
2. Data Cleaning: The process of identifying and correcting errors, missing values, and inconsistencies in the data.
3. Data Exploration: The process of summarizing and visualizing the data to understand its characteristics and relationships.
4. Data Preprocessing: The process of transforming and preparing the data for analysis, including feature selection, normalization, and encoding.
5. Machine Learning: A subset of artificial intelligence that uses algorithms to learn patterns and make predictions from data.
6. Statistical Analysis: The use of statistical methods to analyze and interpret data, including hypothesis testing, regression analysis, and clustering.
7. Data Visualization: The graphical representation of data to communicate insights and findings effectively.
8. Model Evaluation: The process of assessing the performance of a predictive model using metrics such as accuracy, precision, recall, and F1 score.
9. Feature Engineering: The process of creating new features or transforming existing features to improve the performance of machine learning models.
10. Big Data: The term used to describe large and complex datasets that require specialized tools and techniques for analysis.
These concepts are foundational to the practice of data science and are essential for extracting valuable insights from data.
Join for more: https://t.iss.one/datasciencefun
ENJOY LEARNING 👍👍
👍3