Part II: Giving Voice to the Social Sciences

第二部分：为社会科学发声

AI and Creativity

AI 与创造力

In the late 1970s, the film director Francis Ford Coppola purchased a device called the Kurzweil Reading Machine, an early invention of Ray Kurzweil, himself a renowned futurist and inventor known for his work in artificial intelligence. The Reading Machine used optical character recognition technology to scan printed text and convert it into synthetic speech, assisting people with visual impairments in reading printed materials. Coppola, who had already converted Mario Puzo’s novel into the classic film The Godfather, had an idea to teach the machine to recognize quotation marks. With a few tweaks, he could feed the machine a novel and it was able to read the text and convert all the dialogue into something that looked like a film script. Coppola called this ingenious approach to early language recognition technology a Zippy Script, a simplified approach to creating a long screenplay in a fraction of the time it would normally take a person to write one. It was going great until he was contacted by the Writers Guild.

20 世纪 70 年代末，电影导演弗朗西斯·福特·科波拉购买了一台名为“库兹韦尔阅读机”的设备，这是雷·库兹韦尔的早期发明之一，他本人是因其在人工智能领域的工作而闻名的未来学家和发明家。阅读机使用光学字符识别技术扫描印刷文本并将其转换为合成语音，帮助视力障碍者阅读印刷材料。科波拉已经将马里奥·普佐的小说改编成经典电影《教父》，他想到了一个教机器识别引号的主意。经过一些调整，他可以将小说输入机器，它能够读取文本并将所有对话转换成类似电影剧本的内容。科波拉称这种早期语言识别技术的巧妙方法为Zippy Script，这是一种在几分之一的时间内创建长篇剧本的简化方法，而通常情况下，一个人需要花费更长的时间才能写出一个剧本。一切都很顺利，直到他接到作家协会的电话。

“They said, wait, you can’t have a machine writing your screenplays! But the technology behind the Zippy Script wasn’t writing screenplays. All it did was change the format of the book into something like a script,” Coppola tells me. Was a machine taking away the work of creatives? If more filmmakers used such devices, what would happen to screenwriters?

“他们说，等一下，你不能让机器写你的剧本！但是 Zippy Script 背后的技术并不是在写剧本。它所做的一切只是将书的格式改成类似剧本的东西，”科波拉告诉我。机器在夺走创意工作吗？如果更多的电影制作人使用这样的设备，会发生什么？

Without realizing it, Coppola had tripped an alarm more than forty years earlier than anyone else would, a siren that every creative, in every industry, was to eventually hear and heed with the advent of generative AI.

科波拉无意中比其他任何人早了四十多年拉响了一个警报，这个警报最终会随着生成式 AI 的出现让每个行业的每个创意者听到并注意到。

Today, AI has brought the fight over intellectual capital, and to a greater extent over the future of creativity itself, into sharp focus. With simple text-based prompts, AI can appear to be quite creative and produce remarkably wonderful and strange works of fiction or poetry—even screenplays. And it goes well beyond the written word. We can feed text to any number of AI programs that within seconds can take these prompts and produce fairly remarkable images, video, and music.

今天，人工智能使围绕知识产权的斗争，以及在更大程度上围绕创造力本身的未来，成为人们关注的焦点。通过简单的基于文本的提示，AI 可以显得相当有创造力，制作出极其精彩和奇特的小说或诗歌作品，甚至剧本。而且它远不止文字。我们可以将文本输入到任何数量的人工智能程序，这些程序在几秒钟内可以将这些提示转化为相当出色的图像、视频和音乐。

The first time I saw examples of this, I had the same questions I am sure many of you did: Is generative AI a creativity killer? If the root of creativity is individual agency, what happens when our kids can simply log on to an app leveraging generative AI, type in or speak a request, and then create imaginative works designed by an imagination not their own? How will our kids learn to think creatively for themselves?

第一次看到这些例子时，我和许多人一样有同样的问题：生成式 AI 是创造力的杀手吗？如果创造力的根源是个人主动性，当我们的孩子可以简单地登录利用生成式 AI 的应用程序，输入或说出请求，然后创建由非他们自己的想象力设计的富有想象力的作品时，会发生什么？我们的孩子将如何学会自己创造性地思考？

The degree to which AI influences, and can limit, student creativity has brought the technology under a new shadow of scrutiny, and for understandable reasons. For proof, look no further than all the school districts that banned generative AI from classrooms, thanks to its ability to write essays and long-form answers. If machines can generate words or stories at a high enough level, why would students rely on their own creative juices? These chatbots can write blog posts, podcast scripts, novels, and even screenplays far more advanced than anything Coppola’s converted Kurzweil Reading Machine might have produced.

AI 能影响和限制学生创造力的程度使这项技术受到了新的审视，这是可以理解的。为了证明这一点，看看所有禁止在课堂上使用生成式 AI 的学区就知道了，因为它能够写论文和长篇答案。如果机器可以在足够高的水平上生成单词或故事，为什么学生还要依赖自己的创意灵感？这些聊天机器人可以编写博客文章、播客脚本、小说，甚至比科波拉转换后的库兹韦尔阅读机可能产生的任何东西都要先进得多的剧本。

And when they do, there’s a question of just how original generative AI can be. Skeptics argue that at its most essential level it produces content based on patterns encoded in the AI model from training on existing texts. Do the limits of its training data curtail the scope of creative expressions or ideas?

而当他们这样做时，生成式 AI 到底有多原创的问题就出现了。怀疑者认为，从本质上讲，它是根据人工智能模型中编码的模式生成内容的，这些模式来自对现有文本的训练。其训练数据的限制是否会限制创造性表达或想法的范围？

Even back in the late 1970s, Coppola saw how advancements in technology not only did little to hinder creativity but also improved the creative process. In similar ways, large language models have the potential to do just that, by sparking new ideas, saving time on tedious tasks, and providing valuable revisions to work—as long as it is used right.

早在 20 世纪 70 年代末，科波拉就看到了技术进步不仅不会阻碍创造力，而且还会改进创作过程。以类似的方式，大型语言模型有潜力做到这一点，通过激发新的想法，节省繁琐任务的时间，并为工作提供有价值的修订——只要使用得当。

Noam Chomsky argues for an interesting distinction between human creativity and that of large language models like OpenAI’s GPT-4 and Google’s LaMDA. AI is a marvel of machine learning, he writes in The New York Times, yet we know from the science of linguistics and the philosophy of knowledge that it differs profoundly from how humans create: “The human mind is a surprisingly efficient and even elegant system that operates with small amounts of information; it seeks not to infer brute correlations among data points but to create explanations,” infused with a dynamic approach to seeing and creating in the world.

诺姆·乔姆斯基对人类创造力和 OpenAI 的 GPT-4 和谷歌的 LaMDA 等大型语言模型的创造力之间进行了有趣的区分。他在《纽约时报》上写道，AI 是机器学习的奇迹，但我们从语言学和知识哲学中知道，它与人类创造的方式有着根本的不同：“人类大脑是一个出人意料的高效甚至优雅的系统，它只用少量 的信息就能运作；它寻求的不是推断数据点之间的粗略关联，而是创造解释，”并以动态的方法观察和创造世界。

I agree and disagree with him. Artificial intelligence is not human, no matter how much it approximates being human. Regardless of how well it conveys intelligence, personality, and creativity, it is not a sentient, perceiving being.

我同意也反对他的观点。人工智能不是人类，无论它多么接近人类。无论它多么好地传达智能、个性和创造力，它都不是一个有感觉、有知觉的存在。

Yet it is important to appreciate that much of the work we credit to our brain isn’t really sentient or part of our perception. Most of our brain’s activity is subconscious, including what we would often consider creativity. Any artist will tell you they often feel a flash of insight that leads to the creative act.

然而，重要的是要认识到，我们归功于我们大脑的许多工作实际上并不是有感知力的，也不是我们感知的一部分。我们大脑的大部分活动都是潜意识的，包括我们通常认为的创造力。任何艺术家都会告诉你，他们经常会感到灵光一现，从而导致创造性行为。

Similarly, how many times have you been told to “sleep on the problem”? I myself am a master of this art. In college, when I faced seemingly intractable math problems, I would engage with them for a few minutes and then delegate them to my subconscious. I would tell my brain to essentially come up with the answers and tell “me” when it was done. Most of the time, I had the answers by the next morning without having to consciously struggle with them. I’m not alone in doing this. Many people find it a useful way to approach difficult problems.

同样地，有多少次你被告知“把问题留到明天再想”？我自己是这门艺术的大师。在大学里，当我面对看似棘手的数学问题时，我会与它们互动几分钟，然后将它们委托给我的潜意识。我会告诉我的大脑基本上想出答案，并在完成后告诉“我”。大多数时候，我在第二天早上就有了答案，而不必有意识地与它们斗争。我并不是唯一这样做的人。许多人发现这是一种处理难题的有效方法。

I now do the same thing when I face a tough problem while leading Khan Academy. I have faith that my brain, or someone else’s, will come up with a creative solution by morning. What are our brains doing subconsciously while our consciousness waits for an answer? Clearly, when you “sleep on a problem,” some part of your brain continues to work even though “you” aren’t aware of it. Neurons activate, which then activate other neurons depending on the strength of the synapses between them. This happens trillions of times overnight, a process mechanically analogous to what happens in a large language model. When a plausible solution presents itself, the subconscious then surfaces it to the conscious as a flash of insight.

现在，当我在领导 Khan Academy 时遇到难题时，我也会做同样的事情。我相信我的大脑或其他人的大脑会在早上想出一个创造性的解决方案。当我们的意识等待答案时，我们的大脑在潜意识中做什么？显然，当你“把问题留到明天再想”时，大脑的某些部分继续工作，即使“你”没有意识到它。神经元被激活，然后根据它们之间突触的强度激活其他神经元。这一过程在一夜之间发生了万亿次，在机械上类似于大型语言模型中发生的情况。当一个合理的解决方案出现时，潜意识就会将其作为一个顿悟闪现到意识中。

Meditation gives us direct experience with this. Close your eyes for a few minutes and observe your own thoughts. They really begin to feel very much like the output of a large language model—or several competing models—whose latest output gets fed as input for the next iteration of output. With a bit of practice, your conscious mind can temporarily disassociate itself from these thoughts until you experience stillness or “no thought.” You’ll begin to see your thoughts for what they are and aren’t. They aren’t you.

冥想使我们能够直接体验这一点。闭上眼睛几分钟，观察自己的思想。它们真的开始感觉非常像大型语言模型——或几个竞争模型——的输出，其最新输出被用作下一次迭代输出的输入。稍加练习，你的意识就能暂时脱离这些思想，直到你体验到静止或“无念”。你会开始看到你的思想是什么，不是什么。它们不是你。

Think about a flow state that most experts in their craft can attain after the often-noted ten thousand hours of practice (which is analogous to pretraining for generative AI models). They will often say that their greatest creativity or actions occur when they do not allow themselves to be conscious of what they are doing. The best way to ruin their performance, or creativity, is to consciously think about what is happening. Great orators will tell you that it feels like their brain is doing the talking while their conscious selves are just there to observe the output. After making thousands of videos, I often feel this way when I press record. I won’t claim that what experts’ well-trained brains are doing when they create is identical to what large language models do, but it seems awfully similar.

想想大多数技艺精湛的专家在经过经常提到的 10,000 小时的练习（这类似于生成式 AI 的预训练）后可以达到的心流状态。他们常常会说，他们最伟大的创造力或行动发生在他们不允许自己意识到他们在做什么的时候。破坏他们表现或创造力的最好方法就是有意识地思考正在发生的事情。伟大的演说家会告诉你，感觉就像他们的大脑在说话，而他们的有意识的自我只是在那里观察输出。在制作了数千个视频后，当我按下录制按钮时，我经常有这种感觉。我 不会说专家们训练有素的大脑在创作时所做的事情与大型语言模型所做的事情 完全相同，但它们看起来非常相似。

I also take issue with Chomsky’s comment that the human mind “seeks not to infer brute correlations among data points but to create explanations.” Humans are experts at inferring brute correlations, so much so that they often manifest themselves as problematic biases and false narratives about how the world works. This has led to humanity constructing prejudices and complex mythologies. The entire scientific revolution, in fact, has been our best attempt to stop “infer[ring] brute correlations,” which our brains seem to do so naturally, and most of us are still having trouble giving up the habit.

我也反对乔姆斯基的评论，即人类思维“寻求的不是推断数据点之间的粗略关联，而是创造解释”。人类是推断粗略关联方面的专家，以至于它们经常表现为有问题的偏见和关于世界如何运作的错误叙述。这导致人类构建了偏见和复杂的神话。事实上，整个科学革命是我们阻止“推断粗略关联”的最佳尝试，我们的大脑似乎很自然地这样做，而我们大多数人仍然难以放弃这种习惯。

Some would also argue that generative AI’s “creativity” is just derivative from all the data it has been exposed to. But isn’t that very human as well? Even the large leaps in human creativity have been closely correlated to things that the creator has been exposed to. Would Einstein have made the leap to special relativity if he hadn’t already read the work of Lorentz and countless other physicists? Are the narratives of Shakespeare, Jane Austen, or J. K. Rowling completely novel, or are they new expressions of age-old narratives? It is likely that the most exceptionally creative minds are able to draw connections from their pretraining that most brains with similar training miss. Or maybe they just had better pretraining. Once we take ourselves out of the rarefied air of an Einstein or a Shakespeare and come down to the type of creativity most of us engage in daily—designing an experiment, crafting a product, or writing a song—how much of that can we say is truly not derivative from other things we’ve been exposed to?

有些人还会争辩说，生成式 AI 的“创造力”只是从它所接触到的所有数据中派生出来的。但这难道不是也很人性化吗？即使是人类创造力的重大飞跃也与创造者所接触到的事物密切相关。如果爱因斯坦没有阅读洛伦兹和无数其他物理学家的工作，他会做出狭义相对论的飞跃吗？莎士比亚、简·奥斯丁或 J.K.罗琳的叙述完全是新颖的吗，还是古老叙述的新表达？很可能，最有创造力的头 脑能够从他们的预训练中得出与具有类似训练的大多数大脑不同的联系。当我们从爱因斯坦或莎士比亚的稀薄空气中走出来，回到我们大多数人每天从事的那种创造力——设计实验、制作产品或写歌——我们可以说其中有多少是完全不派生于我们接触过的其他事物？

So, if you buy my argument that generative AI is actually creative in much the same way that we often are, does this mean that it will diminish the value of human creativity? I don’t think so. Our creativity gains value when we are exposed to the creativity of others. We become more creative when we brainstorm with other creative people, because we riff off one another and build off one another’s thoughts. A generative AI world will only accelerate this process.

那么，如果你接受我的论点，即生成式 AI 实际上与我们通常的创造方式 一样具有创造力，这是否意味着它会降低人类创造力的价值？我不这么认为。当我们接触到他人的创造力时，我们的创造力会获得价值。当我们与其他有创造力的人集思广益时，我们会变得更有创造力，因为我们互相汲取和构建对方的思想。生成式 AI 世界只会加速这一过程。

The best ideas will come not from the AI creating for us but when the AI is creating and riffing with us.

最好的想法不会来自 AI 为我们创造，而是来自 AI 与我们共同创造和即兴发挥时。

Much like poets hanging out at a café in Paris, humans and AI can augment each other and inspire a mutually creative process. When it comes to learners engaging with their creative sides, there is something profoundly unique and wondrous happening when students use AI. I find that AI is best deployed as a device to promote a child’s interests and passions, and to teach new ones too. Tell it you want to write a story, and it might ask you who you want the main character to be or even what you envision the character to be struggling with.

就像诗人在巴黎的咖啡馆闲逛一样，人类和 AI 可以相互增强并激发相互创造的过程。当涉及到学习者与他们的创造性方面互动时，当学生使用 AI 时会发生一些极其独特和奇妙的事情。我发现，AI 最好用作促进孩子兴趣和激情的工具，并教导新的兴趣。告诉它你想写一个故事，它可能会问你希望主角是谁，甚至问你设想主角在与什么作斗争。

When I see my own children using this tool, I find that they are actually learning a lot more than they would if they were simply writing a story without artificial intelligence, if only because AI has engaged them in the creative process. Very few eleven-year-olds can write a really well-structured story, yet I have seen my eleven-year-old daughter learning, through AI, how to do just that. If she wants to have a direct conversation with her main character, or ask Khanmigo to play out certain plot threads, it allows my daughter as the creator to test her ideas. When the AI is designed well, it works within constraints such that it doesn’t do the work for the student. At the same time, it is unconstrained in where the student can go creatively.

当我看到自己的孩子使用这个工具时，我发现他们实际上学到的比他们只是在没有人工智能的情况下写故事时要多得多，这仅仅是因为人工智能让他们参与了创作过程。很少有十一岁的孩子能够写出一篇结构严谨的故事，但我看到我的十一岁女儿通过 AI 学习如何做到这一点。如果她想与她的主角进行直接对话，或让 Khanmigo 演绎某些情节线，这允许我的女儿作为创作者测试她的想法。当 AI 设计得很好时，它在约束内工作，这样它就不会为学生完成工作。同时，它对学生在创作上的方向没有任何限制。

In early 2023, when we introduced Khanmigo, one of the first features we saw students engaging with was the AI facilitating an improv writing activity.

在 2023 年初，当我们推出 Khanmigo 时，我们看到学生参与的第一个功能之一是 AI 促进即兴写作活动。

KHANMIGO: Let’s create a short story together using the “Yes, and . . .” improv technique. I’ll start with a sentence, and then you can add a sentence or two. We’ll keep building the story together. Remember, the idea is to accept and build on each other’s contributions. Here we go: Once upon a time, in a small village by the sea, there lived a young girl named Luna who had a magical seashell.

KHANMIGO：让我们一起使用“是的，还有……”的即兴技巧创作一个短篇故事。我将以一个句子开始，然后你可以添加一个或两个句子。我们将一起继续构建这个故事。记住，想法是接受并建立在彼此的贡献之上。我们开始吧：从前，在海边的一个小村庄里，住着一个叫露娜的小女孩，她有一个魔法贝壳。

STUDENT: When Luna put the shell to her ear, she heard voices from the past.

学生：当露娜把贝壳放在耳边时，她听到了来自过去的声音。

KHANMIGO: Yes, and these voices shared stories and wisdom from the village’s ancestors, helping Luna connect with her heritage. One day, Luna heard a mysterious voice in the seashell that spoke of a hidden treasure buried deep within a nearby cave.

KHANMIGO：是的，这些声音分享了村庄祖先的故事和智慧，帮助露娜与她的传统联系在一起。一天，露娜在贝壳中听到一个神秘的声音，说附近一个洞穴深处埋藏着宝藏。

Here, as Khanmigo wrote the first sentence and the student wrote the next, and so on, we see that creativity is not simply something the AI did for the student but something it required of the student. AI like Khanmigo proves beneficial to children’s creativity by providing them with a tool to help them generate, play, and get feedback on ideas in a judgment-free zone.

在这里，当 Khanmigo 写了第一句话，学生写了下一句，等等，我们看到，创造力不仅仅是 AI 为学生做的事情，而是它要求学生做的事情。像 Khanmigo 这样的 AI 通过提供一个工具，在一个无判断的区域中帮助他们生成、玩耍和获得想法的反馈，从而证明了人工智能对儿童创造力的益处。

With the emergence of artificial intelligence, we’re also seeing a shift in the barriers to entry that once limited people from learning a variety of crafts. In the past, where you had to build up a specific set of skills, with large-language-model AI tutors now anyone can learn to paint, for instance. Imagine having an AI assistant that offers inspiration, guidance, and constructive feedback, or that helps you explore different artistic styles, themes, and compositions by generating a variety of reference images and samples. As you work, the AI provides real-time feedback, ensuring your composition, proportions, and color choices are on point. Today, large language models can make sense of images. AI can even ask a student to draw a picture and then give the student a critique of the drawing. In fact, it could ask students to express themselves and explain what they drew.

随着人工智能的出现，我们还看到入门障碍的转变，这些障碍曾经限制了人们学习各种手艺的能力。在过去，你必须建立一套特定的技能，而现在有了大型语言模型 AI 导师，任何人都可以学习绘画。想象一下，有一个 AI 助手提供灵感、指导和建设性的反馈，或通过生成各种参考图像和样本帮助你探索不同的艺术风格、主题和构图。当你工作时，AI 提供实时反馈，确保你的构图、比例和颜色选择正确。今天，大型语言模型可以理解图像。AI 甚至可以要求学生画一幅画，然后对学生的画进行评论。事实上，它可以要求学生表达自己并解释他们画了什么。

Generative AI is the writing tutor that will teach learners, exploring diverse genres, themes, and narrative structures with them. Generative AI can even help them learn to play musical instruments, suggesting practice routines and fingering techniques and deciphering initial musical scores based on their preferences. It can help with improvisation by providing melodic ideas and chord progressions aligned with their playing style.

生成式 AI 是教导学习者的写作导师，探索多种体裁、主题和叙事结构。生成式 AI 甚至可以帮助他们学习演奏乐器，建议练习计划和指法技巧，并根据他们的喜好破译最初的乐谱。它可以通过提供与其演奏风格相一致的旋律想法和和弦进行来帮助即兴演奏。

Using advances in technology to enhance the making of art is not a new trend. From the perspective of nineteenth-century portrait artists, early cameras might have seemed like a way to cheat, but photography evolved into a new art form. The first animation was hand drawn. Over time, animation moved to computers. One can argue that this transition has not cheapened the art. In fact, it has advanced the art by allowing expressions of the imagination that were not feasible before. Now my children can use standard movie software on their computers to make special effects that would have been state of the art in the 1990s. Or consider that until fairly recently filmmaking required a significant budget and access to expensive equipment. Cheaper, lighter, and high-quality digital cameras and smartphones not only are commonplace today but also expand creative access for people like never before. The point being, every generation has better and better creative tools. At no point have these suppressed human creativity. Rather, they have magnified it.

利用先进技术来增强艺术创作并不是一个新趋势。从 19 世纪肖像画家的角度来看，早期的相机可能看起来像是一种作弊方式，但摄影演变成了一种新的艺术形式。第一部动画是手绘的。随着时间的推移，动画转向计算机。有人可以争辩说，这种转变并没有降低艺术的价值。事实上，它通过允许表达以前 无法实现的想象力来提升艺术。现在我的孩子们可以在他们的电脑上使用标准的电影软件制作在 1990 年代被认为是最先进的特效。或者考虑一 下，直到最近，电影制作还需要大量的预算和昂贵的设备。更便宜、更轻、更高质量的数码相机和智能手机不仅在今天司空见惯，而且以前所未有的方式扩大了人们的创作途径。关键是，每一代人都有越来越好的创作工具。这些工具从未压制过人类的创造力。相反，它们放大了它。

Still, we can’t have a conversation about creativity and AI without addressing the AI-sized elephant in the room. Will generative AI, with its ability to produce images, music, and stories, eventually make professional creatives obsolete? Who will hire screenwriters, for instance, when generative AI can write a screenplay for a producer in seconds? I do think it’s a real challenge. The net effect of the world of generative AI is that we are going to get more expressions of creativity, and creatives with wider and deeper skill sets, somewhat out of necessity but also thanks to the opportunity generative AI provides. Screenwriters in particular will ultimately expand their skills to essentially become full movie producers. With an AI partner, they will be able to take on the roles of senior screenwriter, editor, music director, and visual director. Again, not necessarily a bad thing, says Coppola.

尽管如此，如果不谈论房间里那头人工智能大象，我们就无法谈论创造力和人工智能。生成式 AI 具有生成图像、音乐和故事的能力，最终会使专业创意人员过时吗？例如，当生成式 AI 可以在几秒钟内为制片人编写剧本时，谁会雇用编剧呢？我确实认为这是一个真正的挑战。生成式 AI 世界的净效应是我们将获得更多的创造力表达，具有更广泛和更深技能的创意者，这在某种程度上是出于必要，但也得益于生成式 AI 提供的机会。特别是编剧最终将扩展他们的技能，基本上成为全职电影制片人。在人工智能合作伙伴的帮助下，他们将能够担任高级编剧、剪辑师、音乐总监和视觉总监的角色。科波拉说，这不一定是件坏事。

“I believe the goal of humanity is to enjoy the creating, the learning, and the perfecting.” With the right education, and the right creative tools to work with, there is no limiting the scope of one’s creative output, especially our children’s. “Instead of having one Mozart over five hundred years,” he says, “we now have the possibility of having a thousand Mozarts, a thousand Einsteins, a thousand da Vincis.”

“我相信人类的目标是享受创造、学习和完善。”有了正确的教育和正确的创意工具，没有什么可以限制一个人的创造力输出，尤其是我们的孩子们的。他说：“与其在五百年内只有一个莫扎特，我们现在有可能拥有一千个莫扎特、一千个爱因斯坦、一千个达芬奇。”

This seems possible when you consider that creativity is likely a combination of one’s exposure to large, disparate amounts of experiences and content, coupled with opportunity to express and improve on that creativity. Mozart, Einstein, and da Vinci weren’t just innately gifted. They had access to opportunities and resources that the bulk of humanity didn’t have access to. Technology has generally lowered the cost of access to world-class tools and learning. Our mission of free, world-class education for anyone, anywhere would have seemed delusional without computers and the internet. AI is going to be the next technological wave that empowers future creatives in art and science. The AI, along with feeding us information on nearly any topic, becomes a companion in art, aiding in this practice. Not only does it allow students to produce more polished, finished works, but it can model the creative process with them. It can riff with students and ignite their curiosity, spark their imagination, and invite them to explore the wonders of knowledge. When I think about the most creative times in my own life, it was when I was surrounded by creative friends. This AI becomes one extra friend who can be creative, not just in music, the arts, engineering, or math, but in all dimensions.

当你考虑到创造力可能是一个人接触到大量不同的经验和内容的组合，以及表达和改进这种创造力的机会时，这似乎是可能的。莫扎特、爱因斯坦和达芬奇不仅仅是天生的才华横溢。他们有机会接触到大多数人无法接触到的机会和资源。技术通常会降低获得世界一流工具和学习的成本。没有计算机和互联网，我们为任何地方的任何人提供免费、世界一流教育的使命似乎是荒谬的。人工智能除了为我们提供几乎任何主题的信息外，还成为艺术中的伙伴，帮助我们进行这种实践。它不仅能让学生创作出更精美、更完整的作品，还能与他们一起模拟创作过程。它可以与学生即兴创作，点燃他们的好奇心，激发他们的想象力，邀请他们探索知识的奇迹。当我想到自己一生中最有创造力的时刻时，那是我被有创造力的朋友包围的时候。这个人工智能成为了一个额外的朋友，它可以富有创造力，不仅在音乐、艺术、工程或数学方面，而且在所有方面。

“点赞有美意，赞赏是鼓励”