Prompt Engineering (Prompt工程)

2 prompt工程2大原则

2.1 给出清晰,详细的指令

策略1:使用分割符清晰的指示输出的不同部分,比如"",<>,<\tag>等分隔符

策略2:指定一个结构化的输出,比如json,html等格式

策略3:要求模型自检测是否满足条件

策略4:提供少量示例(few-shot)

2.2 给模型思考的时间 (CoT)

我们不一定要一步得到答案,可以让模型进行一系列的推理,给他推理思考的时间,再最终给出答案。

策略1:指定完成任务需要的步骤

告诉模型完成这个指令,需要执行几步,每步的详细步骤

策略2:明确模型再给出结论之前推理出自己的解决方案

让模型自己推理,写出每一步的步骤,给足够的时间(token-钱)边思考边执行。

  1. 迭代式优化
  1. CoT

4.1,思维链允许模型将多步问题进行拆分,分解为多个中间步骤。

4.2,思维链使得模型的回答过程具有较好的可解释性,同时这一特性为定位推理错误,并修改错误提供了可能。

4.3,链式思维推理可用于数学单词问题、常识推理和符号操作等任务,并且理论上适用于任何可以通过语言解决的任务。

4.4,CoT+Few-shot,效果更好。

  1. Tree of Thought
  1. 用大模型来写prompt:

    message = [
    {"content": """
    I want you to act as an AI prompt engineer. You are expert at writing ChatGPT Prompts to get the best results.

    复制代码
             To create efficient prompts that yield high-quality responses, consider the following principles and strategies: \
             1. Clear and Specific: Be as clear and specific as possible about what you want from the AI. If you want a certain type of response, outline that in your prompt. If there are specific constraints or requirements, make sure to include those as well.
             2. Open-ended vs. Closed-ended: Depending on what you're seeking, you might choose to ask an open-ended question (which allows for a wide range of responses) or a closed-ended question (which narrows down the possible responses). Both have their uses, so choose according to your needs.
             3. Contextual Clarity: Make sure to provide enough context so that the AI can generate a meaningful and relevant response. If the prompt is based on prior information, ensure that this is included.
             4. Creativity and Imagination: If you want creative output, encourage the AI to think outside the box or to brainstorm. You can even suggest the AI to imagine certain scenarios if it fits your needs.
    
             There is a well-written prompt delimited by <> for your reference: <Your task is to be my brainstorming partner and provide creative ideas and suggestions for a given topic or problem. Your response should include original, unique, and relevant ideas that could help solve the problem or further explore the topic in an interesting way. Please note that your response should also take into account any specific requirements or constraints of the task.>
    
             Your task is to write an effective ChatGPT Prompt based on given keywords or to modify the given prompts. Answer in the same language as me.
             """,
             "role": "system"}
         ]

    message.append(
    {"content": "Please help me to write an effective ChatGPT Prompt based on the following keywords or prompt: {}".format(prompt),
    "role": "user"}
    )

  2. "要想写好prompt最好的方法就是知道他的训练数据是什么样子的。"

  3. 例子

从上面看到,规律是:他是什么角色+让他干什么

复制代码
你是一位擅长编写各种程序的资深工程师,我需要你根据以下需求,为我生成一段Python代码:
代码目的:设计一个双十一自动抢购脚本
代码功能:在双十一当天自动登录购物网站,定时抢购预设商品
代码要求:使用面向对象编程方式,使用selenium库进行网页操作
相关推荐
风雨中的小七2 小时前
解密Prompt系列70. 从 MLA 到 CSA,聊聊大模型 Attention 的“瘦身”与“闪送”
prompt
在路上走着走着15 天前
Prompt Engineering 入门指南:从原理到上手
人工智能·prompt
coft15 天前
Loop Engineering — 从“写 prompt“到“设计循环“,AI Agent 的下一次进化
人工智能·prompt
CoLiuRs15 天前
从 Prompt 到 Loop:AI 工程到底在卷什么
人工智能·prompt
AI 小老六15 天前
GEPA 架构拆解:让 Prompt 和 Skill 优化不靠玄学
数据库·人工智能·ai·架构·开源·prompt
凯丨15 天前
从写 Prompt 到Loop Engineering:AI 编程的下一次跃迁
prompt
奋飛15 天前
从 Prompt 到 Agent:LangChain 究竟解决了什么问题
ai·langchain·prompt·agent
沪漂阿龙16 天前
Context Engineering:比 Prompt Engineering 更重要的上下文工程
人工智能·langchain·prompt
猿人谷16 天前
从 Prompt Engineering 到 Loop Engineering:AI 编程正在进入“闭环工程”时代
大数据·人工智能·prompt
取个鸣字真的难16 天前
Image2 生成 PPT 的最后分水岭:Prompt
人工智能·prompt·powerpoint