Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[译] [1103] 本章小结 #24

Open
cssmagic opened this issue Feb 29, 2024 · 0 comments
Open

[译] [1103] 本章小结 #24

cssmagic opened this issue Feb 29, 2024 · 0 comments

Comments

@cssmagic
Copy link
Owner

Summary

本章小结

  • A prompt pattern is a template to help us construct a prompt to meet a given goal.
  • The flipped interaction pattern flips the script: rather than asking questions to the LLM, the LLM asks questions to us.
  • The flipped interaction pattern is useful when we don’t know how to effectively prompt the LLM.
  • The persona pattern is used to have the AI take on a particular persona, such as “introductory programming instructor,” or point of view.
  • The persona pattern is useful when we want the LLM to respond from a given perspective.
  • Copilot currently struggles with tasks that are contrived, not well defined, or large.
  • Some believe that LLMs will replace programming languages; others believe that programming languages are here to stay.
  • LLMs are helping people do data science without those people ever seeing the Python code.
  • It may be that programming languages themselves are not replaced, but that the leading languages will be developed to be more readable than today’s languages.
  • 提示词模式是一种模版,旨在帮助我们构建提示词,以实现一个特定目标。
  • 翻转互动模式颠覆了常规互动方式:不是我们向 LLM 提问,而是 LLM 向我们提问。
  • 当我们不确定如何有效地引导 LLM 时,翻转互动模式特别有用。
  • 角色扮演模式使 AI 能够扮演特定的角色,例如“初级编程教师”,或代表一个特定观点。
  • 当我们需要 LLM 从一个特定角度进行回应时,角色扮演模式非常有益。
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant