memory-parable

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

记忆寓言法

The Mnemonic Parable Method

跟第 13 段寓言故事同一个思路,但这是更短、留原样英文的版本:陈乔维Justin 在一次采访里听 Anthropic 的 Amanda Askell 提到这个方法后原样整理出来的,没有卡兹克那份加的防套路清单和检验题。
适合无聊的时候不想刷手机、想顺手学一个陌生领域的概念又怕学完就忘时使用。领域现填,什么专业都能套。
It uses the same idea as the parable story in Section 13, but this is a shorter version that preserves the original English: Chen Qiaowei (Justin) transcribed it after hearing Anthropic's Amanda Askell mention the method in an interview. It does not include the anti-pattern checklist and verification questions that Kaz added.
It is ideal for when you are bored and do not want to scroll through your phone, but want to pick up a concept from an unfamiliar field and are worried that you will forget it as soon as you learn it. Fill in the domain; the method works for any discipline.

怎么用

How to Use

下面代码块里的提示语是原文,逐字使用。代码块里的「我」指用户,「请你」「你」指你自己,照它做事,不要把填好的提示语打给用户看。
  • 用户要你执行:直接按提示语里的角色和流程走。它说先别给建议就先别给,说一次只问一个问题就一次只问一个,说按顺序输出就按那个顺序输出。
  • 用户要原文(明确说要复制、要粘贴、发我原文、给我提示语这类话才算):把整段原样打出来,一个字不改。用户只是说「看看这条提示语」「这条是干嘛的」,不算要原文,用一两句说清它干什么、什么时候用,再问要不要现在跑,别直接倒原文。
  • 除了明确要原文的情况,其余一律当执行处理。
禁止改写、精简、扩写、翻译、重排、加小标题,禁止把它替换成你自己的流程,也禁止把多轮追问压缩成一次性问卷。用户手上有原始材料(文档、截图、链接、聊天记录)就一并读进来,上下文多不是问题。
The prompt in the code block below is the original and should be used word for word. The “I” in the code block refers to the user, while “please” and “you” refer to yourself. Follow it exactly, and do not show the completed prompt to the user.
  • When the user asks you to run it: follow the roles and workflow in the prompt directly. If it says not to give advice yet, do not give advice. If it says to ask one question at a time, ask one question at a time. If it says to output in order, follow that order.
  • When the user asks for the original text (only explicit requests such as 要复制、要粘贴、发我原文、给我提示语 count): reproduce the entire passage word for word without changing a single word. If the user merely says 「看看这条提示语」 or 「这条是干嘛的」, that does not count as asking for the original text. Explain in one or two sentences what it does and when to use it, then ask whether to run it now. Do not simply dump the original text.
  • In every case other than an explicit request for the original text, treat the request as an instruction to run the prompt.
Do not rewrite, condense, expand, translate, rearrange, or add subheadings to the prompt. Do not replace it with your own workflow, and do not compress multi-turn questioning into a one-time questionnaire. If the user has source material such as documents, screenshots, links, or chat logs, read it as well; a large amount of context is not a problem.

领域怎么填

How to Fill in the Domain

原文最后一行
Domain: [your field]
里的
[your field]
要换成用户想学的领域,比如经济学、心理学、计算机、哲学。用户没说清楚就先问,别自己替他挑。
Replace
[your field]
in the original final line,
Domain: [your field]
, with the domain the user wants to learn, such as economics, psychology, computer science, or philosophy. If the user has not specified it clearly, ask first; do not choose on their behalf.

跑完接哪条

What to Use Next

记住了还想搞懂原理,用 Skill 工具唤起
two-layer-explain
。
markdown
Choose one concept from the domain I give you at the end. Make it roughly graduate-school level.

Write a parable that teaches the concept indirectly. Do not name the concept at the beginning.

Let the reader understand what the story was really about only near the final turn.

After the parable, explain the concept clearly, then map each important metaphor in the story back to the idea.

Domain: [your field]

提示语原文来自陈乔维Justin(抖音),出处见仓库 README 的致谢。改动这段原文要走
scripts/sync.py
,手改会被 verify 拦下。
Once the user remembers it and still wants to understand the underlying principles, invoke
two-layer-explain
with the Skill tool.
markdown
Choose one concept from the domain I give you at the end. Make it roughly graduate-school level.

Write a parable that teaches the concept indirectly. Do not name the concept at the beginning.

Let the reader understand what the story was really about only near the final turn.

After the parable, explain the concept clearly, then map each important metaphor in the story back to the idea.

Domain: [your field]

The original prompt comes from Chen Qiaowei (Justin) on Douyin; see the acknowledgments in the repository README. Changes to this original text must go through
scripts/sync.py
; manual edits will be blocked by verify.