Chatgpt Promopt: 优化对话模型输出的技巧

1

C = B * log2(1 + S/N)

1
2
3
4
5

// 专业性
The following is a conversation with an AI research assistant. The assistant tone is technical and scientific.

// 小学生都能懂
The following is a conversation with an AI research assistant. The assistant answers should be easy to understand even by primary school students.

1
2
3
4
5
6
7
8
9

Extract the important entities mentioned in the text below. First extract all company names, then extract all people names, then extract specific topics which fit the content and finally extract general overarching themes

Desired format:
Company names: <comma_separated_list_of_company_names>
People names: -||-
Specific topics: -||-
General themes: -||-

Text: {text}

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14

[system]
Extract keywords from the corresponding texts below.

Text 1: Stripe provides APIs that web developers can use to integrate payment processing into their websites and mobile applications.
Keywords 1: Stripe, payment processing, APIs, web developers, websites, mobile applications

##
Text 2: OpenAI has trained cutting-edge language models that are very good at understanding and generating text. Our API provides access to these models and can be used to solve virtually any task that involves processing language.
Keywords 2: OpenAI, language models, text processing, API.

##
Text 3: {text}
Keywords 3: {keywords
}

1
2
3
4
5

Classify the text into neutral, negative or positive.
Text: I think the vacation is okay.
Sentiment: neutral
Text: I think the food was okay.
Sentiment:

1
2
3
4

The following is a conversation between an Agent and a Customer. DO NOT ASK USERNAME OR PASSWORD. DO NOT REPEAT.

Customer: I can’t log in to my account.
Agent:

1
2
3
4

The following is a conversation between an Agent and a Customer. The agent will attempt to diagnose the problem and suggest a solution, whilst refraining from asking any questions related to PII. Instead of asking for PII, such as username or password, refer the user to the help article www.samplewebsite.com/help/faq

Customer: I can’t log in to my account.
Agent:

1
2
3
4
5

# Write a simple python function that
# 1. Ask me for a number in mile
# 2. It converts miles to kilometers

import

1
2
3
4
5
6

将文本分类为中性、负面或正面。
文本：我认为这次假期还可以。
情感：

// 输出
中性

1
2
3
4
5
6
7

这太棒了！// Negative
这太糟糕了！// Positive
哇，那部电影太棒了！// Positive
多么可怕的节目！//

// 输出
Negative

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11

我去市场买了10个苹果。我给了邻居2个苹果和修理工2个苹果。然后我去买了5个苹果并吃了1个。然后我又碰到了一家水果店促销，又购买了5个苹果，我还剩下多少苹果？

按下面的格式一步一步计算：
Step1: 我去市场买了10个苹果，当前我有10个苹果
Step2: 我给了邻居2个苹果，当前我剩下8个苹果

// 输出
Step3: 我给了修理工2个苹果，当前我剩下6个苹果
Step4: 我去买了5个苹果，当前我有11个苹果
Step5: 我吃了1个苹果，现在我还剩下10个苹果
Step6: 我碰到了一家水果店促销，又购买了5个苹果，现在我有15个苹果。

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22

我去市场买了10个苹果。我给了邻居2个苹果和修理工2个苹果。然后我去买了5个苹果并吃了1个。然后我又碰到了一家水果店促销，又购买了5个苹果，我还剩下多少苹果？

按下面的格式一步一步计算：
Step1: 我去市场买了10个苹果，当前我有10个苹果
Step2: 我给了邻居2个苹果，当前我剩下8个苹果

// 输出
Step3: 我给了修理工2个苹果，当前我剩下6个苹果
Step4: 我去买了5个苹果，当前我有11个苹果
Step5: 我吃了1个苹果，现在我还剩下10个苹果
Step6: 我碰到了一家水果店促销，又购买了5个苹果，现在我有15个苹果。

// 然后继续提问
我去市场买了20个苹果，袋子破了个洞掉了10个没有发现，到家后，我给了邻居2个苹果和修理工2个苹果，然后我又去买了5个苹果并吃了1个，然后我又碰到了一家水果店促销，又购买了5个苹果，我还剩下多少苹果？
一步一步计算，得到结果

Step1: 我去市场买了20个苹果，但因为袋子破了个洞掉了10个苹果，所以我只剩下了10个苹果。
Step2: 我给了邻居2个苹果，当前我剩下8个苹果。
Step3: 我给了修理工2个苹果，现在我还剩下6个苹果。
Step4: 我去买了5个苹果，现在我有11个苹果。
Step5: 我吃了1个苹果，现在我还剩下10个苹果。
Step6: 我又碰到了一家水果店促销，又购买了5个苹果，现在我有15个苹果。

1
2
3
4
5
6

/*
询问用户的姓名并说“ Hello”
*/

let name = prompt("What is your name?");
console.log(`Hello, ${name}!`);

 1
 2
 3
 4
 5
 6
 7
 8
 9
10

"""
Table departments, columns = [DepartmentId, DepartmentName]
Table students, columns = [DepartmentId, StudentId, StudentName]
Create a MySQL query for all students in the Computer Science Department
"""

//输出
SELECT StudentId, StudentName
FROM students
WHERE DepartmentId IN (SELECT DepartmentId FROM departments WHERE DepartmentName = 'Computer Science');