The key to using generative AI successfully is prompt-crafting
成功使用生成式 AI 的关键是快速制作

How to... use ChatGPT to boost your writing --- 如何...使用 ChatGPT 提高您的写作水平 (substack.com)

我认为大多数使用 ChatGPT 来帮助写作的人都做错了。我的意思不仅仅是因为他们用它来作弊（不要那样做）或者因为他们不检查 ChatGPT 提供的事实（他们可能是编造的），而是因为他们有错误的心智模型了解如何使用该系统。

I have mentioned that ChatGPT isn’t Google, and it isn’t Alexa, but it also isn’t a human that you are giving instructions to. It is a machine you are programming with words.
我已经提到 ChatGPT 不是谷歌，也不是 Alexa，但它也不是你要向其发出指令的人。这是一台你用文字编程的机器。

You are writing a prompt, not having a conversation
您正在编写提示，而不是进行对话

Because ChatGPT often acts like a helpful human, we get lured into thinking it is one. I asked my Twitter followers, and nearly half always act politely towards the AI, and another quarter mostly act politely. I do this myself, saying “please” and “thank you” in my requests, even though the AI doesn’t care.
因为 ChatGPT 通常表现得像一个乐于助人的人，所以我们被引诱认为它是一个。我询问了我的 Twitter 关注者，将近一半的人总是对 AI 表现出礼貌，另外四分之一的人大多表现得有礼貌。我自己这样做，在我的请求中说“请”和“谢谢”，即使人工智能不在乎。

While there is nothing wrong with politeness, it often obscures the fact that all we are trying to do is prompt a non-sentient machine to generate the text we need. This confusion isn’t a problem in other types of generative AI. Since AI image generators are not as verbose as ChatGPT, people using them have learned they need to spend time doing “prompt engineering:” editing and playing with prompts to come up with the results they want. These prompts can get very elaborate, and can often seem abstract, or almost poetic. They are the program the AI is following, where the goal is to generate a great image through trial-and-error and pushing the AI in the direction you want.
虽然礼貌并没有错，但它常常掩盖了一个事实，即我们试图做的只是提示一台无感知的机器生成我们需要的文本。这种混淆在其他类型的生成式 AI 中不是问题。由于 AI 图像生成器不像 ChatGPT 那样冗长，因此使用它们的人已经了解到他们需要花时间进行“即时工程”：编辑和播放提示以得出他们想要的结果。这些提示可能会非常详尽，而且通常看起来很抽象，或者几乎是诗意的。它们是 AI 遵循的程序，其目标是通过反复试验生成出色的图像，并将 AI 推向您想要的方向。

But between the human-like nature of chat and the fact that written material is harder to immediately evaluate, many people tend to avoid explicit prompt construction in ChatGPT. But that is a mistake! More elaborate and specific prompts work better.
但在聊天的类人本质和书面材料更难立即评估这一事实之间，许多人倾向于避免在 ChatGPT 中进行显式提示构建。但这是一个错误！更详细和具体的提示效果更好。

Don’t ask it to write an essay about how human error causes catastrophes. The AI will come up with a boring and straightforward piece that does the minimum possible to satisfy your simple demand. Instead, remember you are the expert and the AI is a tool to help you write. You should push it in the direction you want. For example, provide clear bullet points to your argument: write an essay with the following points: -Humans are prone to error -Most errors are not that important -In complex systems, some errors are catastrophic -Catastrophes cannot be avoided
不要要求它写一篇关于人为错误如何导致灾难的文章。人工智能会想出一个无聊而直接的作品，以尽可能少的方式满足您的简单需求。相反，请记住您是专家，人工智能是帮助您写作的工具。你应该把它推向你想要的方向。例如，为你的论点提供明确的要点：写一篇包含以下几点的文章： - 人类容易出错 - 大多数错误并不那么重要 - 在复杂的系统中，一些错误是灾难性的 - 灾难是不可避免的

But even these results are much less interesting than a more complicated prompt: write an essay with the following points. use an academic tone. use at least one clear example. make it concise. write for a well-informed audience. use a style like the New Yorker. make it at least 7 paragraphs. vary the language in each one. end with an ominous note. -Humans are prone to error -Most errors are not that important -In complex systems, some errors are catastrophic -Catastrophes cannot be avoided
但即使是这些结果，也没有更复杂的提示有趣得多：写一篇包含以下要点的文章。使用学术语气。至少使用一个明确的例子。使其简洁。为消息灵通的读者写作。使用像纽约客这样的风格。使其至少有 7 个段落。改变每个人的语言。以不祥的音符结束。 - 人类容易犯错 - 大多数错误并不那么重要 - 在复杂的系统中，一些错误是灾难性的 - 灾难无法避免

Notice that not every part of the prompt is followed exactly - there are six paragraphs, not seven - but that is typical of how generative AI works: you don’t always get what you directly ask for, but you can push towards something unique and interesting by playing with prompts.
请注意，并不是提示的每一部分都被完全遵循——有六段，而不是七段——但这是生成式人工智能的典型工作方式：你并不总是能得到你直接要求的东西，但你可以推动一些独特的和玩提示很有趣。

So try asking for it to be concise or wordy or detailed, or ask it to be specific or to give examples. Ask it to write in a tone (ominous, academic, straightforward) or to a particular audience (professional, student) or in the style of a particular author or publication (New York Times, tabloid news, academic journal). You are not going to get perfect results, so experimenting (and using the little “regenerate response” button) will help you get to the right place. Over time, you will start to learn the “language” that ChatGPT is using.
因此，请尝试要求它简洁、冗长或详细，或者要求它具体或举例。要求它以一种语气（不祥的、学术的、直截了当的）或针对特定的受众（专业人士、学生）或以特定作者或出版物（纽约时报、小报新闻、学术期刊）的风格写作。您不会获得完美的结果，因此尝试（并使用“重新生成响应”小按钮）将帮助您到达正确的位置。随着时间的推移，您将开始学习 ChatGPT 使用的“语言”。

Subscribe

Play with memory and length 玩转记忆和长度

ChatGPT’s huge advance over other generative AIs is that it has a memory. It keeps track of what you wrote, and appears to remember about 3,000 words worth of data. However, what it retains, and how that memory is used, is often hard unclear.
ChatGPT 相对于其他生成式 AI 的巨大进步在于它有记忆。它会跟踪你写的内容，似乎能记住大约 3,000 字的数据。然而，它保留了什么，以及如何使用这些记忆，往往很难弄清楚。

Sometimes the memory is useful, you can (and should) ask it to revise previous work: change the third paragraph to be more professional or use a different example in the middle and it will provide a revised version. However, sometimes it forgets what you were working on, and you have to remind it. You may, for example, want to tell it revise the third paragraph on the essay on catastrophes so it doesn’t lose track.
有时记忆很有用，你可以（也应该）要求它修改以前的工作：将第三段改得更专业或者在中间使用不同的例子，它会提供修改后的版本。然而，有时它会忘记你在做什么，你必须提醒它。例如，你可能想告诉它修改关于灾难的文章的第三段，这样它就不会迷失方向。

Memory can also be a problem. ChatGPT can get “stuck” repeating the same examples or tone throughout many requests. To unstick it, you may need to ask it to give a different example, or to change its tone, or to alter your early prompts. Often, the best option is to give ChatGPT amnesia: start a new chat and try again.
内存也可能是个问题。 ChatGPT 可能会“卡住”，在许多请求中重复相同的示例或语气。要解除它，你可能需要让它给出一个不同的例子，或者改变它的语气，或者改变你早期的提示。通常，最好的选择是让 ChatGPT 失忆：开始新的聊天并重试。

Similarly, you might want to break up your requests to the Chatbot into smaller chunks. Ask it for an introduction, and revise that to get the tone that you want to achieve. Only then should you start asking for additional paragraphs.
同样，您可能希望将对聊天机器人的请求分解为更小的块。要求它进行介绍，然后修改它以获得您想要达到的基调。只有这样你才应该开始要求额外的段落。

And if the results of those longer pieces cut off, simply asking ChatGPT to “continue” is enough to get the rest of the material.
如果那些较长片段的结果被截断，只需要求 ChatGPT“继续”就足以获得其余材料。

Play with personas and style 玩弄角色和风格

You can ask the AI to use specific styles for writing. You will get different results from asking for an academic essay versus a persuasive article versus a blog post versus a corporate memo. The results are often surprising. So you should consider trying several writing types when experimenting with prompts.
你可以要求人工智能使用特定的写作风格。要求学术论文、有说服力的文章、博客文章和公司备忘录，你会得到不同的结果。结果往往令人惊讶。因此，在尝试使用提示时，您应该考虑尝试多种书写类型。

Another way to get interesting writing out of ChatGPT is by asking the AI to be someone else. You can have the AI play characters by prompting it to think of itself as a chef, or a novelist, or Plato. This can lead to delightful results. You can start with this list of hundreds of persona suggestions. I used a modified version of the storyteller prompt: “I want you to act as a storyteller. You will come up with entertaining stories that are engaging, imaginative and captivating for the audience. It can be fairy tales, educational stories or any other type of stories which has the potential to capture people’s attention and imagination. You should provide lots of detail and make the story memorable.”
从 ChatGPT 中获得有趣写作的另一种方法是让 AI 成为其他人。你可以让人工智能扮演角色，让它把自己想象成厨师、小说家或柏拉图。这可以带来令人愉快的结果。您可以从这个包含数百个角色建议的列表开始。我使用了讲故事提示的修改版本：“我想让你扮演讲故事的角色。您将想出引人入胜、富有想象力和吸引观众的有趣故事。它可以是童话故事、教育故事或任何其他类型的故事，有可能吸引人们的注意力和想象力。你应该提供很多细节，让故事令人难忘。”

A very different perspective on error and catastrophe!
对错误和灾难的看法截然不同！

Remember limitations… and your ideas?
还记得局限性……以及您的想法吗？

ChatGPT, like all generative AI systems, is a tool. Tools are used by humans to accomplish specific tasks. Thinking of it that way helps unlock its potential, but also avoid its pitfalls.
ChatGPT 与所有生成式 AI 系统一样，是一种工具。人类使用工具来完成特定的任务。以这种方式思考它有助于释放它的潜力，但也可以避免它的陷阱。

For example: Don’t ask it for facts that you can’t easily check. Don’t ask it to provide references. Don’t have it do math, or conduct analysis. It will happily fake doing these things for you and the output will mostly likely be wrong. ChatGPT it is far from the all-knowing AI that the movies taught us to expect. But as a tool to jumpstart your own writing, multiply your productivity, and to help overcome the inertia associated with staring at a blank page, it is amazing.
例如：不要向它询问您无法轻易核实的事实。不要要求它提供参考。不要让它做数学运算，或进行分析。它会很乐意假装为你做这些事情，输出很可能是错误的。 ChatGPT 远不是电影教我们期待的无所不知的 AI。但作为一种快速启动您自己的写作、提高您的工作效率并帮助克服与盯着空白页相关的惰性的工具，它是惊人的。

I’d like to conclude by asking you to write in the comments about any tips or prompt-crafting that you are using to make ChatGPT work. Part of what makes the release of this tool so exciting is that we are learning about it collectively, and that we can only understand the system through exploration. So what prompts or experiences do you want to share?
最后，我想请您在评论中写下您用来使 ChatGPT 工作的任何提示或提示制作。这个工具的发布之所以如此令人兴奋，部分原因在于我们正在集体学习它，而且我们只能通过探索来理解这个系统。那么您想分享哪些提示或经验呢？