The key to using generative AI successfully is prompt-crafting
成功使用生成式 AI 的關(guān)鍵是快速制作

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

我認(rèn)為大多數(shù)使用 ChatGPT 來幫助寫作的人都做錯(cuò)了。我的意思不僅僅是因?yàn)樗麄冇盟鼇碜鞅祝ú灰菢幼觯┗蛘咭驗(yàn)樗麄儾粰z查 ChatGPT 提供的事實(shí)（他們可能是編造的），而是因?yàn)樗麄冇绣e(cuò)誤的心智模型了解如何使用該系統(tǒng)。

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.
我已經(jīng)提到 ChatGPT 不是谷歌，也不是 Alexa，但它也不是你要向其發(fā)出指令的人。這是一臺(tái)你用文字編程的機(jī)器。

You are writing a prompt, not having a conversation
您正在編寫提示，而不是進(jìn)行對(duì)話

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?yàn)?ChatGPT 通常表現(xiàn)得像一個(gè)樂于助人的人，所以我們被引誘認(rèn)為它是一個(gè)。我詢問了我的 Twitter 關(guān)注者，將近一半的人總是對(duì) AI 表現(xiàn)出禮貌，另外四分之一的人大多表現(xiàn)得有禮貌。我自己這樣做，在我的請(qǐng)求中說“請(qǐng)”和“謝謝”，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.
雖然禮貌并沒有錯(cuò)，但它常常掩蓋了一個(gè)事實(shí)，即我們?cè)噲D做的只是提示一臺(tái)無感知的機(jī)器生成我們需要的文本。這種混淆在其他類型的生成式 AI 中不是問題。由于 AI 圖像生成器不像 ChatGPT 那樣冗長(zhǎng)，因此使用它們的人已經(jīng)了解到他們需要花時(shí)間進(jìn)行“即時(shí)工程”：編輯和播放提示以得出他們想要的結(jié)果。這些提示可能會(huì)非常詳盡，而且通?？雌饋砗艹橄螅蛘邘缀跏窃?shī)意的。它們是 AI 遵循的程序，其目標(biāo)是通過反復(fù)試驗(yàn)生成出色的圖像，并將 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.
但在聊天的類人本質(zhì)和書面材料更難立即評(píng)估這一事實(shí)之間，許多人傾向于避免在 ChatGPT 中進(jìn)行顯式提示構(gòu)建。但這是一個(gè)錯(cuò)誤！更詳細(xì)和具體的提示效果更好。

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
不要要求它寫一篇關(guān)于人為錯(cuò)誤如何導(dǎo)致災(zāi)難的文章。人工智能會(huì)想出一個(gè)無聊而直接的作品，以盡可能少的方式滿足您的簡(jiǎn)單需求。相反，請(qǐng)記住您是專家，人工智能是幫助您寫作的工具。你應(yīng)該把它推向你想要的方向。例如，為你的論點(diǎn)提供明確的要點(diǎn)：寫一篇包含以下幾點(diǎn)的文章： - 人類容易出錯(cuò) - 大多數(shù)錯(cuò)誤并不那么重要 - 在復(fù)雜的系統(tǒng)中，一些錯(cuò)誤是災(zāi)難性的 - 災(zāi)難是不可避免的

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
但即使是這些結(jié)果，也沒有更復(fù)雜的提示有趣得多：寫一篇包含以下要點(diǎn)的文章。使用學(xué)術(shù)語(yǔ)氣。至少使用一個(gè)明確的例子。使其簡(jiǎn)潔。為消息靈通的讀者寫作。使用像紐約客這樣的風(fēng)格。使其至少有 7 個(gè)段落。改變每個(gè)人的語(yǔ)言。以不祥的音符結(jié)束。 - 人類容易犯錯(cuò) - 大多數(shù)錯(cuò)誤并不那么重要 - 在復(fù)雜的系統(tǒng)中，一些錯(cuò)誤是災(zāi)難性的 - 災(zāi)難無法避免

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.
請(qǐng)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——但這是生成式人工智能的典型工作方式：你并不總是能得到你直接要求的東西，但你可以推動(dòng)一些獨(dú)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 “l(fā)anguage” that ChatGPT is using.
因此，請(qǐng)嘗試要求它簡(jiǎn)潔、冗長(zhǎng)或詳細(xì)，或者要求它具體或舉例。要求它以一種語(yǔ)氣（不祥的、學(xué)術(shù)的、直截了當(dāng)?shù)模┗蜥槍?duì)特定的受眾（專業(yè)人士、學(xué)生）或以特定作者或出版物（紐約時(shí)報(bào)、小報(bào)新聞、學(xué)術(shù)期刊）的風(fēng)格寫作。您不會(huì)獲得完美的結(jié)果，因此嘗試（并使用“重新生成響應(yīng)”小按鈕）將幫助您到達(dá)正確的位置。隨著時(shí)間的推移，您將開始學(xué)習(xí) ChatGPT 使用的“語(yǔ)言”。

Subscribe

Play with memory and length?玩轉(zhuǎn)記憶和長(zhǎng)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 相對(duì)于其他生成式 AI 的巨大進(jìn)步在于它有記憶。它會(huì)跟蹤你寫的內(nèi)容，似乎能記住大約 3,000 字的數(shù)據(jù)。然而，它保留了什么，以及如何使用這些記憶，往往很難弄清楚。

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.
有時(shí)記憶很有用，你可以（也應(yīng)該）要求它修改以前的工作：將第三段改得更專業(yè)或者在中間使用不同的例子，它會(huì)提供修改后的版本。然而，有時(shí)它會(huì)忘記你在做什么，你必須提醒它。例如，你可能想告訴它修改關(guān)于災(zāi)難的文章的第三段，這樣它就不會(huì)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.
內(nèi)存也可能是個(gè)問題。 ChatGPT 可能會(huì)“卡住”，在許多請(qǐng)求中重復(fù)相同的示例或語(yǔ)氣。要解除它，你可能需要讓它給出一個(gè)不同的例子，或者改變它的語(yǔ)氣，或者改變你早期的提示。通常，最好的選擇是讓 ChatGPT 失憶：開始新的聊天并重試。

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.
同樣，您可能希望將對(duì)聊天機(jī)器人的請(qǐng)求分解為更小的塊。要求它進(jìn)行介紹，然后修改它以獲得您想要達(dá)到的基調(diào)。只有這樣你才應(yīng)該開始要求額外的段落。

And if the results of those longer pieces cut off, simply asking ChatGPT to “continue” is enough to get the rest of the material.
如果那些較長(zhǎng)片段的結(jié)果被截?cái)?，只需要?ChatGPT“繼續(xù)”就足以獲得其余材料。

Play with personas and style?玩弄角色和風(fēng)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寫作風(fēng)格。要求學(xué)術(shù)論文、有說服力的文章、博客文章和公司備忘錄，你會(huì)得到不同的結(jié)果。結(jié)果往往令人驚訝。因此，在嘗試使用提示時(shí)，您應(yīng)該考慮嘗試多種書寫類型。

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.”
從 ChatGPT 中獲得有趣寫作的另一種方法是讓 AI 成為其他人。你可以讓人工智能扮演角色，讓它把自己想象成廚師、小說家或柏拉圖。這可以帶來令人愉快的結(jié)果。您可以從這個(gè)包含數(shù)百個(gè)角色建議的列表開始。我使用了講故事提示的修改版本：“我想讓你扮演講故事的角色。您將想出引人入勝、富有想象力和吸引觀眾的有趣故事。它可以是童話故事、教育故事或任何其他類型的故事，有可能吸引人們的注意力和想象力。你應(yīng)該提供很多細(xì)節(jié)，讓故事令人難忘?！?/span>

A very different perspective on error and catastrophe!
對(duì)錯(cuò)誤和災(zāi)難的看法截然不同！

Remember limitations… and your ideas?
還記得局限性……以及您的想法嗎？

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 與所有生成式 AI 系統(tǒng)一樣，是一種工具。人類使用工具來完成特定的任務(wù)。以這種方式思考它有助于釋放它的潛力，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：不要向它詢問您無法輕易核實(shí)的事實(shí)。不要要求它提供參考。不要讓它做數(shù)學(xué)運(yùn)算，或進(jìn)行分析。它會(huì)很樂意假裝為你做這些事情，輸出很可能是錯(cuò)誤的。 ChatGPT 遠(yuǎn)不是電影教我們期待的無所不知的 AI。但作為一種快速啟動(dòng)您自己的寫作、提高您的工作效率并幫助克服與盯著空白頁(yè)相關(guān)的惰性的工具，它是驚人的。

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，我想請(qǐng)您在評(píng)論中寫下您用來使 ChatGPT 工作的任何提示或提示制作。這個(gè)工具的發(fā)布之所以如此令人興奮，部分原因在于我們正在集體學(xué)習(xí)它，而且我們只能通過探索來理解這個(gè)系統(tǒng)。那么您想分享哪些提示或經(jīng)驗(yàn)?zāi)兀?/span>