A prosthesis for imagination: Using AI to boost your creativity
想象力的假肢：使用 AI 提升您的創(chuàng)造力

AI can already beat humans in many measures of creativity. Let's use that to our advantage.
人工智能已經(jīng)可以在許多創(chuàng)造力方面擊敗人類(lèi)。讓我們利用它來(lái)發(fā)揮我們的優(yōu)勢(shì)。

A prosthesis for imagination: Using AI to boost your creativity --- 想象力的假肢：使用 AI 提升您的創(chuàng)造力 (substack.com)

By many of the common psychological tests of creativity, AI is already more creative than humans.
通過(guò)許多常見(jiàn)的創(chuàng)造力心理測(cè)試，人工智能已經(jīng)比人類(lèi)更具創(chuàng)造力。

For example, one standard measure of creativity is the remote association test (or RAT). This test asks people to find the common word that connects a set of three seemingly unrelated words. For example, pine, crab, and sauce are connected by the word “apple.” (Try one: what word connects cream, skate and water? The AI answers it in the screenshot!) Unsurprisingly, ChatGPT is very good at this, maxing out the test even when I created novel RAT questions that had not previously appeared in the literature
例如，一種衡量創(chuàng)造力的標(biāo)準(zhǔn)是遠(yuǎn)程聯(lián)想測(cè)試（或 RAT）。這個(gè)測(cè)試要求人們找到連接一組三個(gè)看似無(wú)關(guān)的詞的常用詞。例如，pine、crab 和 sauce 是通過(guò)“apple”這個(gè)詞聯(lián)系起來(lái)的。 （試一試：什么詞連接奶油、冰鞋和水？AI 在屏幕截圖中回答了它?。┎怀鏊希珻hatGPT 非常擅長(zhǎng)這一點(diǎn)，即使我創(chuàng)建了以前沒(méi)有出現(xiàn)在文獻(xiàn)中的新穎 RAT 問(wèn)題，也能最大限度地完成測(cè)試

1.

A second standard measure of creativity is the alternative uses test (AUT). This measures an individual's ability to come up with a wide variety of different uses for a common object. In this test, a participant is presented with an everyday object, such as a paper clip, and is asked to come up with as many different uses for the object as possible. For example, a paper clip can be used to hold papers together, to pick locks, or to fish small objects out of tight spaces. The alternative uses test is often used to evaluate an individual's ability to think divergently and to come up with unconventional ideas. Again, ChatGPT maxes it out in my informal test (in case this was based on training data, I also generated some new AUT prompts, which it also aced). This is not surprising because previous,?more formal studies had found that earlier versions of GPT were close to human-level performance.
創(chuàng)造力的第二個(gè)標(biāo)準(zhǔn)衡量標(biāo)準(zhǔn)是替代用途測(cè)試 (AUT)。這衡量了一個(gè)人為一個(gè)普通物體想出各種不同用途的能力。在這個(gè)測(cè)試中，參與者會(huì)看到一個(gè)日常物品，例如回形針，并被要求盡可能多地想出該物品的不同用途。例如，回形針可用于將紙張夾在一起、撬鎖或從狹小的空間中撈出小物件。替代用途測(cè)試通常用于評(píng)估個(gè)人發(fā)散思考和提出非常規(guī)想法的能力。同樣，ChatGPT 在我的非正式測(cè)試中發(fā)揮了最大作用（如果這是基于訓(xùn)練數(shù)據(jù)，我還生成了一些新的 AUT 提示，它也取得了優(yōu)異成績(jī)）。這并不奇怪，因?yàn)橹案降难芯堪l(fā)現(xiàn)，早期版本的 GPT 性能接近人類(lèi)水平。

Now, obviously, these tests were made for humans, not AIs, so it isn’t clear that they are measuring anything that is truly creative… and yet… as AI technology continues to evolve, we are seeing more and more examples of machines generating solid stories, art, and?even music?(Seriously, click that link if you haven’t seen Google’s new music-generating AI). It's easy to look at these developments and start to panic, thinking that AI is on the cusp of replacing human creativity altogether.
現(xiàn)在，很明顯，這些測(cè)試是針對(duì)人類(lèi)而不是 AI 進(jìn)行的，因此尚不清楚它們是否在衡量任何真正具有創(chuàng)造力的東西......然而......隨著 AI 技術(shù)的不斷發(fā)展，我們看到越來(lái)越多的機(jī)器生成的例子可靠的故事、藝術(shù)，甚至音樂(lè)（說(shuō)真的，如果您還沒(méi)有看到 Google 的新音樂(lè)生成 AI，請(qǐng)點(diǎn)擊該鏈接）。看到這些發(fā)展很容易開(kāi)始恐慌，認(rèn)為人工智能即將完全取代人類(lèi)創(chuàng)造力。

But I don’t think we should see this as competition. In fact, the strength of AI is that it can help us break through the parts of the creative process that many humans are bad at, and let us become better at generating ideas ourselves. This isn’t theoretical. I want to give you three ways you can use AI right now, and especially ChatGPT or GPT-3.5, to be more creative when you need to solve a problem or come up with a new idea.
但我認(rèn)為我們不應(yīng)該將其視為競(jìng)爭(zhēng)。事實(shí)上，人工智能的強(qiáng)大之處在于它可以幫助我們突破很多人類(lèi)不擅長(zhǎng)的創(chuàng)作過(guò)程，讓我們更擅長(zhǎng)自己產(chǎn)生創(chuàng)意。這不是理論上的。我想為您提供三種現(xiàn)在可以使用 AI 的方式，尤其是 ChatGPT 或 GPT-3.5，以便在您需要解決問(wèn)題或提出新想法時(shí)更具創(chuàng)造力。

Fluency: Creating lots of ideas?流暢：創(chuàng)造很多想法

An issue with human idea generation is that not everyone is equally creative. Some people are really good at generating ideas, and they can apply this ability in almost every context. Indeed, recent research has shown that the “Equal Odds” rule is true, which is that very creative people both generate more ideas (fluency, in the graph), and better ideas (creativity, in the graph), than other folks. Overall fluency was not correlated with intelligence, and people who were bad at idea generation might still be best at creative execution, but, as the graph shows, there are some people with the skill of idea generation and some without. Until the past year, there was no prosthetic or approach that would help people who were not good at generating a lot of ideas to do better (besides?coffee). Now there is: generative AI. As we saw in the AUT test, is excellent at generating a long list of ideas.
人類(lèi)創(chuàng)意產(chǎn)生的一個(gè)問(wèn)題是并非每個(gè)人都具有同樣的創(chuàng)造力。有些人真的很擅長(zhǎng)產(chǎn)生想法，他們幾乎可以在任何情況下應(yīng)用這種能力。事實(shí)上，最近的研究表明“機(jī)會(huì)均等”規(guī)則是正確的，即與其他人相比，非常有創(chuàng)造力的人會(huì)產(chǎn)生更多的想法（圖中的流暢性）和更好的想法（圖中的創(chuàng)造力）。整體流暢度與智力無(wú)關(guān)，不擅長(zhǎng)創(chuàng)意的人可能仍然最擅長(zhǎng)創(chuàng)意執(zhí)行，但是，如圖所示，有些人具有創(chuàng)意生成的技能，而有些則沒(méi)有。直到去年，還沒(méi)有任何修復(fù)或方法可以幫助那些不善于產(chǎn)生大量想法的人做得更好（咖啡除外）。現(xiàn)在有：生成人工智能。正如我們?cè)?AUT 測(cè)試中看到的那樣，非常擅長(zhǎng)生成一長(zhǎng)串想法。

I suspect the Equal Odds rule does not apply to AI, and most of the default ideas of AI are of mediocre quality (though more on this soon). But that is okay, because that is where you, as a human, come into the equation. You are looking for ideas that spark inspiration and recombination, and having a long list of generated possibilities can be an easier place to start for people who are not great at idea fluency.
我懷疑 Equal Odds 規(guī)則不適用于 AI，并且大多數(shù) AI 的默認(rèn)想法質(zhì)量平庸（盡管很快就會(huì)有更多）。但這沒(méi)關(guān)系，因?yàn)檫@就是你作為一個(gè)人進(jìn)入方程式的地方。您正在尋找能夠激發(fā)靈感和重組的想法，并且擁有一長(zhǎng)串已生成的可能性對(duì)于那些想法不流暢的人來(lái)說(shuō)可能是一個(gè)更容易開(kāi)始的地方。

So how do we do it? Let’s imagine that we want to?come up with 20 ideas for marketing slogans for a new mail-order cheese shop. The AI can generate those for us, but we will get even better quality if we tell the AI to act as someone who is good at coming up with ideas. You can see below, we get better results if we say:?You are an expert at marketing. When asked to generate slogan ideas you come up with ideas that are different from each other, clever, and interesting. You use clever wordplay. You try not to repeat themes or ideas. Here is your first task: come up with 20 ideas for marketing slogans for a new mail-order cheese shop, make them different from each other, and make them clever and creative.
那么我們?cè)撛趺醋瞿?？假設(shè)我們想為一家新的郵購(gòu)奶酪店的營(yíng)銷(xiāo)口號(hào)提出 20 個(gè)想法。 AI 可以為我們生成這些，但如果我們告訴 AI 充當(dāng)善于提出想法的人，我們將獲得更好的質(zhì)量。你可以在下面看到，如果我們說(shuō)：你是營(yíng)銷(xiāo)專(zhuān)家，我們會(huì)得到更好的結(jié)果。當(dāng)被要求生成標(biāo)語(yǔ)創(chuàng)意時(shí)，您會(huì)想出彼此不同、聰明且有趣的創(chuàng)意。你使用巧妙的文字游戲。你盡量不要重復(fù)主題或想法。這是你的第一個(gè)任務(wù)：為一家新的郵購(gòu)奶酪店想出 20 個(gè)營(yíng)銷(xiāo)口號(hào)的想法，使它們彼此不同，并使它們聰明且富有創(chuàng)意。

And… most of the ideas are terrible, while a few have potential (and bad puns). But that is okay! It took us no time to generate 20 ideas, and it is costless to skim them to see if they inspire better ideas. If none of those sparked your interest, ask for another 20 with different prompting. Ask it to consider a particular customer (a cheese shop that will appeal to novices, or to children), or to change the context of the prompt in other ways. Tirelessly generating concepts is something AIs are uniquely good at.
而且……大多數(shù)想法都很糟糕，而少數(shù)有潛力（和糟糕的雙關(guān)語(yǔ)）。但沒(méi)關(guān)系！我們很快就產(chǎn)生了 20 個(gè)想法，瀏覽它們以查看它們是否激發(fā)了更好的想法是沒(méi)有成本的。如果這些都沒(méi)有引起您的興趣，請(qǐng)?jiān)诓煌奶崾鞠乱罅硗?20 個(gè)。讓它考慮一個(gè)特定的顧客（一家對(duì)新手或兒童有吸引力的奶酪店），或者以其他方式改變提示的上下文。不知疲倦地產(chǎn)生概念是 AI 的獨(dú)特之處。

Variance: Creating novel ideas?差異：創(chuàng)造新穎的想法

Another key aspect of idea generation is to embrace variance.?Research shows that, to find good novel ideas, we likely have to come up with lots of bad novel ideas,?because most new ideas are pretty bad. Fortunately, we are good at filtering out low-quality ideas, so, if we can generate novel ideas quickly and at low-cost, we are more likely to generate at least some high-quality gems.
創(chuàng)意產(chǎn)生的另一個(gè)關(guān)鍵方面是擁抱差異。研究表明，為了找到好的新點(diǎn)子，我們可能不得不想出很多糟糕的新點(diǎn)子，因?yàn)榇蠖鄶?shù)新點(diǎn)子都非常糟糕。幸運(yùn)的是，我們善于過(guò)濾掉低質(zhì)量的想法，因此，如果我們能夠以低成本快速產(chǎn)生新穎的想法，我們更有可能產(chǎn)生至少一些高質(zhì)量的寶石。

There are lots of potential ways to do this with ChatGPT. One is to play with constraints. In general, and contrary to what most people expect, AI works best to generate ideas when it is most constrained. Force it to give you less likely answers, and you are going to find more original combinations. You might want to ask:?You are an expert at problem solving and idea generation. When asked to solve a problem you come up with novel and creative ideas. Here is your first task: tell me 10 detailed ways an AI?(or a superhero, or an astronaut, or any other odd profession)?might make espresso. Describe the details of each way.
使用 ChatGPT 有很多潛在的方法可以做到這一點(diǎn)。一是玩約束。一般來(lái)說(shuō)，與大多數(shù)人的預(yù)期相反，人工智能在最受限制的時(shí)候最能產(chǎn)生想法。強(qiáng)迫它給你不太可能的答案，你會(huì)找到更多的原創(chuàng)組合。您可能想問(wèn)：您是解決問(wèn)題和產(chǎn)生想法的專(zhuān)家。當(dāng)被要求解決一個(gè)問(wèn)題時(shí)，你會(huì)想出新穎而有創(chuàng)意的想法。這是你的第一個(gè)任務(wù)：告訴我人工智能（或超級(jí)英雄、宇航員或任何其他奇怪的職業(yè)）可能制作濃縮咖啡的 10 種詳細(xì)方法。描述每一種方式的細(xì)節(jié)。

And, in seconds, we now have 30 diverse and unusual ideas. Again, most are terrible (“The superhero uses their shape-shifting abilities to transform into a coffee machine, brewing and serving espresso shots directly from their own body. This method ensures that the coffee is always fresh and perfectly brewed.”??) but some are interesting and might spark further thought (Heat vision espresso?makes me think of unusual heating elements to heat water faster, the?AI predictive grinding for beans?has me thinking about how there are no smart grinders on the market that I know of). And, again, if there aren’t enough ideas on the table, generate more.
而且，在幾秒鐘內(nèi)，我們現(xiàn)在有 30 個(gè)不同尋常的想法。同樣，大多數(shù)都很糟糕（“超級(jí)英雄利用他們的變形能力變成一臺(tái)咖啡機(jī)，直接從他們自己的身體沖泡和供應(yīng)意式濃縮咖啡。這種方法確保咖啡總是新鮮和完美沖泡。”??）但是有些很有趣，可能會(huì)引發(fā)進(jìn)一步的思考（Heat vision espresso 讓我想到不尋常的加熱元件可以更快地加熱水，AI 預(yù)測(cè)研磨豆讓我思考我所知道的市場(chǎng)上怎么沒(méi)有智能研磨機(jī)）。而且，如果桌面上沒(méi)有足夠的想法，請(qǐng)產(chǎn)生更多。

You can also use other techniques, like asking it for interview transcripts for fake interviews:?Create an interview transcript between a product designer and a dentist about the problems the dentist has, for example. Or ask it to describe non-existent products:?walk me through the interface for a fictional new water pump that has exciting new features. There is an art to this that you can learn from experimentation, and you should feel free to share other prompt techniques that work in the comments.
您還可以使用其他技術(shù)，例如向其索要虛假采訪的采訪記錄：例如，創(chuàng)建產(chǎn)品設(shè)計(jì)師和牙醫(yī)之間關(guān)于牙醫(yī)遇到的問(wèn)題的采訪記錄。或者要求它描述不存在的產(chǎn)品：引導(dǎo)我瀏覽具有令人興奮的新功能的虛構(gòu)新型水泵的界面。您可以從實(shí)驗(yàn)中學(xué)到一門(mén)藝術(shù)，您應(yīng)該隨時(shí)在評(píng)論中分享其他有用的提示技巧。

Getting unstuck: avoiding inertia
擺脫困境：避免惰性

People always ask me if I use AI to write my posts. I don’t, but I absolutely use it when I am feeling stuck to inspire and “unstick” me. For example, I rewrote one paragraph in this post three times before asking ChatGPT to write it for me. The result was good enough to keep moving forward, and I have since gone back and modified it beyond recognition.
人們總是問(wèn)我是否使用 AI 來(lái)寫(xiě)我的帖子。我沒(méi)有，但當(dāng)我感到被困住時(shí)，我絕對(duì)會(huì)使用它來(lái)激勵(lì)和“解開(kāi)”我。例如，我將這篇文章中的一段改寫(xiě)了三遍，然后才讓 ChatGPT 幫我寫(xiě)。結(jié)果很好，可以繼續(xù)前進(jìn)，后來(lái)我回過(guò)頭來(lái)修改它，面目全非。

This is not uncommon. Many of us have ideas, but often we have trouble actually taking the next step with them, since, to borrow from Eliot, “Between the idea/ And the reality/ Between the motion/ And the act/ Falls the Shadow.” There are many Shadows, the things that stop us from taking action on ideas and, as a result, many good ones never become reality. A great thing about ChatGPT is you can always ask it to help you with the step you are stuck on:?here is my first sentence, continue it.?Or?give me the subheadings for the following story idea. Or?give me a fictional transcript where I pitch the CEO of a family-run Italian espresso company the idea for a new kind of espresso machine using laser heaters.?There is tremendous value in overcoming inertia, and often a small push is what we need to do it. So, no, I don’t let ChatGPT write these posts, but that doesn’t mean that it doesn’t help me write them.
這并不罕見(jiàn)。我們中的許多人都有想法，但通常我們很難真正采取下一步行動(dòng)，因?yàn)榻栌冒蕴氐脑挘霸谙敕?與現(xiàn)實(shí)/在行動(dòng)/與行動(dòng)之間/落下陰影?！庇泻芏嚓幱?，阻止我們對(duì)想法采取行動(dòng)，結(jié)果，許多好的想法永遠(yuǎn)不會(huì)成為現(xiàn)實(shí)。 ChatGPT 的一大優(yōu)點(diǎn)是您可以隨時(shí)請(qǐng)求它幫助您完成卡住的步驟：這是我的第一句話，繼續(xù)。或者給我以下故事創(chuàng)意的副標(biāo)題?；蛘呓o我一份虛構(gòu)的成績(jī)單，我向一家意大利家族經(jīng)營(yíng)的濃縮咖啡公司的首席執(zhí)行官推銷(xiāo)了一種使用激光加熱器的新型濃縮咖啡機(jī)的想法?？朔栊跃哂芯薮蟮膬r(jià)值，而通常我們需要做的只是一個(gè)小小的推動(dòng)。所以，不，我不讓 ChatGPT 寫(xiě)這些帖子，但這并不意味著它不會(huì)幫助我寫(xiě)它們。

Idea generation is similar: it is unlikely that ChatGPT will generate your next great idea alone, because, no matter how well it scores on the RAT test, it isn’t really creative in the way a human is. But, by providing you with fluency, variance, and momentum, it can be a critical partner when you need to solve your own problems.
想法的產(chǎn)生是相似的：ChatGPT 不太可能單獨(dú)產(chǎn)生你的下一個(gè)好想法，因?yàn)闊o(wú)論它在 RAT 測(cè)試中的得分如何，它都不像人類(lèi)那樣真正具有創(chuàng)造力。但是，通過(guò)為您提供流暢性、差異性和動(dòng)力，當(dāng)您需要解決自己的問(wèn)題時(shí)，它可以成為重要的合作伙伴。