Part II: Giving Voice to the Social Sciences
第二部分：为社会科学发声
1. Introduction
引言
In today's world, social sciences have become an essential part of our society. From economics and politics to sociology and psychology, these disciplines provide us with a better understanding of the world we live in. However, despite their importance, social sciences often go unheard or unaddressed. This is where AI comes in. By leveraging the power of machine learning and natural language processing, AI can help social scientists make sense of complex data and communicate their findings more effectively. In this article, we will explore how AI is revolutionizing the social sciences and giving voice to the voiceless. We'll start with a look at AI and creativity.
2. AI and Creativity
AI 与创造力
Creativity has always been considered one of the hallmarks of human intelligence. It allows us to come up with new ideas, solve complex problems, and express ourselves in unique ways. However, creativity is not limited to humans alone. Over the past few years, researchers have started exploring the potential of artificial intelligence (AI) in creative activities such as art, music, and writing. The results have been promising, with some algorithms even capable of producing works that are difficult to distinguish from those created by humans. For example, the AI-powered painting program DeepDream was able to generate stunning images that seemed like they were crafted by a human artist. While AI may not replace humans in all aspects of creativity, it certainly has the potential to augment our abilities and push the boundaries of what is possible.
In the late 1970s, renowned film director Francis Ford Coppola made a purchase that would change the course of his career. He acquired a device called the Kurzweil Reading Machine, an early invention of the celebrated futurist and inventor Ray Kurzweil. Kurzweil is known for his groundbreaking work in artificial intelligence.
The Kurzweil Reading Machine utilized optical character recognition technology to scan printed text and convert it into synthetic speech. This innovative device was particularly useful for people with visual impairments as it helped them to read printed materials more effectively. At the time, Coppola was already well-known for adapting the novel by Mario Puzo into the iconic classic film The Godfather. With this new tool at his disposal, he had a novel idea: teach the machine how to recognize quotation marks.
Coppola discovered that, with a few tweaks and adjustments, he could feed the machine a novel and it would be able to read the text and convert all dialogue into something that resembled a film script. This approach to early language recognition was so ingenious that Coppola dubbed it the Zippy Script. It allowed him to create a long screenplay in a fraction of the time it would normally take a person to write one.
Despite its many benefits, Coppola's innovative breakthrough was met with some resistance from the Writers Guild. The organization believed that the machine's ability to mimic human writing could lead to job losses among writers. However, Coppola's vision was too compelling to ignore, and the Zippy Script went on to revolutionize the film industry. Today, it remains one of the most important tools in the world of screenwriting.
0 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。
但是，随着时间的推移，这种技术并没有得到广泛应用。现在，我们已经有了更加先进的自然语言处理技术，可以自动生成剧本、对话等等。这些技术可以帮助编剧节省时间和精力，但是也会引起一些问题和争议。
Unbeknownst to him, Coppola had set off an alarm over four decades ago that would eventually be heard by every creative individual across every industry as the emergence of generative AI drew near. Today, with simple text-based prompts, AI has the ability to display remarkable creativity and produce works of fiction or poetry that are both wonderful and peculiar, even in screenplays. Its capabilities extend beyond the written word, allowing us to feed it text and have it generate images, videos, and music in a matter of seconds.
As AI continues to advance, it has brought into sharp focus the ongoing battle for intellectual capital and, more broadly, the future of creativity itself. With its ability to mimic human-like creativity, AI has become a powerful tool for those seeking to harness its potential and leverage it to their advantage. As we move forward, it is clear that the relationship between humans and AI will continue to evolve, shaping the way we think about creativity and its role in our lives.
The rise of generative AI has sparked a debate about whether it's a creativity killer. At first glance, it seems like the answer is yes. If the root of creativity is individual agency, what happens when our kids can simply log on to an app that leverages generative AI? They could 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?
The question remains: is generative AI really a creativity killer? The answer lies in understanding the nature of creativity itself. Creativity isn't just about coming up with new ideas; it's also about how those ideas are developed and refined over time. With generative AI, users can quickly generate a large number of ideas, but the real work of refining those ideas and turning them into something truly creative still requires human intervention.
Moreover, generative AI can actually enhance human creativity by providing new tools and approaches to thinking about complex problems. For example, a designer could use generative AI to quickly explore different design options and identify the most promising ones. This frees up time for more focused, creative thinking that might not have been possible otherwise.
In conclusion, while generative AI certainly has its limitations as a creative tool, it's unlikely to be a complete replacement for human creativity. Rather than seeing it as a threat, we should embrace the opportunities it provides for us to collaborate with machines and explore new avenues for creative expression.
The growing concern over the extent to which artificial intelligence (AI) influences and limits student creativity has cast a new shadow of scrutiny over the technology, for understandable reasons. The use of generative AI in classrooms has led to the ban of many school districts due to its ability to write essays and long-form answers. This raises the question: if machines can generate words or stories at such a high level, why should students rely on their own creative juices? These chatbots have been able to produce blog posts, podcast scripts, novels, and even screenplays that are far more advanced than anything Coppola’s converted Kurzweil Reading Machine could have produced.
The impact of AI on student creativity is a matter of debate among educators and experts alike. While some argue that AI can provide valuable insights and help students develop their skills, others believe that it may stifle creativity and discourage students from exploring their own ideas. As AI continues to advance, it is important for educators to find ways to integrate this technology into the classroom without negatively affecting student development. One approach could be to use AI as a tool to support and enhance student creativity rather than replace it entirely. This could involve using chatbots to generate ideas or prompts for writing assignments, or providing students with access to AI-generated resources that they can build upon to create their own original works. Ultimately, the goal should be to strike a balance between using AI to facilitate learning and encouraging students to develop their own unique perspectives and ideas.
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.
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?
However, recent advancements in natural language processing (NLP) and machine learning have shown promise in generating more original content. These models can learn from a vast amount of text data and generate output that is not only coherent but also unique. This can lead to new and innovative ideas, as well as improved efficiency in various industries such as journalism, marketing, and content creation.
In addition to generating new content, AI-powered tools can also help humans refine their work. For example, AI-powered editing tools can detect errors in grammar, spelling, and style, suggesting improvements that a human editor may not have noticed. This not only saves time but also leads to higher-quality output.
But with these capabilities come ethical concerns. As AI becomes more adept at mimicking human creativity, there is a risk that it will replace certain jobs that were previously performed by humans. Additionally, there is the concern that AI-generated content may lack the nuance and empathy that comes from human perspectives and experiences.
In conclusion, while there are limitations to what generative AI can achieve, it has the potential to revolutionize various industries by improving efficiency and sparking new ideas. However, it is crucial to approach this technology with caution and consider its potential impact on employment and ethics.
Noam Chomsky, a renowned linguist and philosopher, argues that there is an intriguing distinction between human creativity and that of large language models such as OpenAI's GPT-4 and Google's LaMDA. In his article for The New York Times, Chomsky highlights the marvel of machine learning, stating that AI surpasses our expectations in terms of efficiency and elegance. However, from the perspectives of linguistics and knowledge philosophy, it is evident that AI differs greatly from how humans create things.
According to Chomsky, humans possess an efficient and even elegant system for creating explanations, which operates with minimal amounts of information. Unlike machines, humans do not aim to infer brute correlations between data points; rather, they seek to create meaning through their observations and experiences. This dynamic approach enables humans to see and create in the world in a way that is both intuitive and meaningful.
In contrast, Chomsky argues that large language models like GPT-4 and LaMDA lack this essential element of human creativity. While these models can generate impressive outputs based on patterns learned from vast amounts of data, they are unable to create original ideas or explanations without being explicitly programmed to do so. This limitation underscores the fundamental difference between human creativity and that of artificial intelligence.
In conclusion, while AI has made remarkable strides in recent years, it still lacks the crucial aspect of human creativity that underpins all meaningful creations. By understanding this distinction and recognizing the limitations of current AI technology, we can continue to push the boundaries of what is possible and strive towards a future where both humans and machines can thrive together.
agree with the statement that artificial intelligence (AI) is not human, despite its ability to simulate human-like traits such as intelligence, personality, and creativity. AI lacks the capacity for consciousness or perception, making it fundamentally different from human intelligence.
However, it is also important to acknowledge that much of the work we attribute to our brain's capabilities may not be truly sentient or part of our perception. For instance, most of our brain's activity is subconscious, including what we often perceive as creativity. An artist will attest that they frequently experience a moment of insight that leads to creative inspiration. This suggests that while AI may not have the same level of creativity, it can still replicate certain aspects of human thought processes.
In conclusion, while I agree with the notion that AI is not human, I also recognize that some aspects of human cognition may not be replicable by machines. Ultimately, this highlights the importance of continued research into the nature of consciousness and intelligence, both in humans and in machines.
Many of us have heard the advice to "sleep on a problem" when faced with a difficult issue. Personally, I am a master at this technique. During my college years, when confronted with seemingly insurmountable math problems, my approach was to devote a few minutes to engaging with them before turning them over to my subconscious. I would instruct my brain to essentially come up with the answers and inform me when it had finished. Typically, I would have the answers by the following morning without having to consciously struggle with them. This method has proven effective for many people.
This approach is not unique to math problems; others have found it helpful in tackling challenging issues in various areas of life. By allowing our minds to rest and process the information, we can often gain valuable insights that we might not have otherwise discovered. In some cases, simply taking a break and revisiting the problem later can lead to breakthroughs.
It is essential to note, however, that this is not a one-size-fits-all solution, and different people may find different methods more suitable for their needs. Some individuals may prefer to tackle difficult issues immediately, while others may need time to reflect and process information before attempting to solve them. Ultimately, it is crucial to identify the most effective strategy for dealing with challenging situations.
在领导 Khan Academy 时，我遇到了一个棘手的问题。然而，与过去不同的是，我现在采用的策略是“把问题留到明天再想”。我相信我的大脑或者别人的大脑会在第二天早上想出创造性的解决方案。这是因为，当我们的意识等待答案时，我们的大脑并没有停止工作，而是在潜意识中进行着一系列的活动。
具体来说，当我们“睡眠”或“放松”时，大脑的一些部分仍然在活跃。神经元之间的突触会被激活，然后这些突触又会影响其他神经元的活动。这种现象在一夜之间会发生数万亿次，其过程类似于大型语言模型中的情况。当一个看似合理的解决方案出现时，潜意识会将其作为一个顿悟闪现到我们的意识中。
这种策略不仅可以帮助我们在面对困难问题时找到答案，还可以让我们的大脑得到充分的休息和恢复。因此，无论是在工作中还是生活中，我们都可以尝试“把问题留到明天再想”，让大脑在休息中寻找答案，从而提高我们的工作效率和生活质量。
Meditation provides us with direct insight into this phenomenon. By taking a few minutes to close our eyes and observe our thoughts, we can observe how they begin to resemble the output of a large language model, or several competing models, whose latest output is fed as input for the next iteration of output. With practice, we can temporarily detach our conscious mind from these thoughts, allowing us to experience a sense of stillness or "no thought". This allows us to truly see our thoughts for what they are and aren't - they aren't us.
The process of meditation allows us to gain direct experience of our own thoughts and how they relate to external stimuli. By observing our thoughts over time, we can gain insights into the way they operate and how they influence our perceptions and actions. This can be particularly helpful in understanding the role that our thoughts play in shaping our experiences and emotions.
In addition to providing insights into our own thought processes, meditation can also help us develop greater self-awareness and emotional regulation. By learning to observe our thoughts without getting caught up in them, we can learn to manage our emotions more effectively and develop greater resilience in the face of challenges and stressors.
Overall, meditation is a powerful tool for gaining deeper insights into ourselves and the world around us. It can help us develop greater self-awareness, emotional regulation, and a greater sense of inner peace and calm. By taking the time to meditate regularly, we can learn to navigate life's challenges with greater ease and grace, and develop a deeper sense of purpose and meaning in our lives.
Experts in their craft often achieve a flow state, which is commonly associated with the ten thousand hours of practice required to become proficient (similar to the pretraining process for generative AI models). They claim that their most creative and impactful actions occur when they are not consciously thinking about what they are doing. In fact, trying to think about what is happening can be detrimental to their performance or creativity. Great orators have described a similar experience, where their brains seemingly do all the talking while their conscious selves merely observe the output.
In my own experience with making thousands of videos, I have often felt this way when I press record. While it is difficult to make direct comparisons between what experts' well-trained brains are doing and what large language models are capable of, there does seem to be a striking resemblance between these two states. The best way to understand this phenomenon is to immerse oneself in the flow state and allow one's subconscious mind to take over. This approach has been shown to be effective in achieving peak performance and creativity, whether it be in the arts or other fields.
以下是我根据您提供的内容重构的内容：
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。
Chomsky 曾经说过：“人类思维‘寻求不是在数据点之间推断粗略关联，而是创造解释’”。然而，我们都是擅长于推断粗略关联的人，甚至会在某些情况下表现出问题偏见和关于世界运作方式的错误叙事。这导致了人类构建了偏见和复杂的神话。事实上，整个科学革命都是我们试图停止“推断”粗略关联所做的最大努力之一，但我们的大脑似乎天生就会这样做，而且我们中的许多人仍然很难放弃这种习惯。
我同样反对乔姆斯基的观点，他认为人类思维“寻求的不是推断数据点之间的粗略关联，而是创造解释”。事实上，人类在推断粗略关联方面的表现并不理想，我们往往会受到有问题的偏见影响，以及对世界如何运作产生错误的认识。这导致了人类构建了充满偏见和复杂神话的思维体系。然而，整个科学革命正是我们试图阻止“推断粗略关联”的最佳尝试。尽管我们的大脑似乎很自然地倾向于这样做，但我们大多数人仍然难以摒弃这种习惯。
This is not an easy question to answer. While some may argue that generative AI's "creativity" is just a derivative of all the data it has been exposed to, others point out that even human creativity is closely related to the experiences and knowledge that individuals have gained throughout their lives.
For example, consider Einstein's groundbreaking work on special relativity and his exposure to the research of Lorentz and other physicists before he made the leap. Similarly, the narratives of Shakespeare, Jane Austen, and J. K. Rowling are not entirely novel but rather new expressions of age-old stories. In both cases, the creator draws connections and insights from their pretraining, which most brains with similar training would miss.
However, this does not necessarily mean that these individuals were born with exceptional creative abilities. It is possible that they simply had better pretraining than most people, allowing them to draw connections and insights from their experiences that others might not have been able to access.
When we consider the types of creativity that most of us engage in daily—designing experiments, crafting products, or writing songs—it becomes less clear how much of this can be considered truly original. After all, our ideas and experiences are often influenced by the things we have been exposed to throughout our lives.
In conclusion, while generative AI may exhibit a level of creativity that appears unique, it is important to remember that even humans have the potential to draw on their pretraining and experiences to create something truly original. Ultimately, the extent to which a piece of creative work is derived from prior experiences will depend on the individual and their unique perspective on the world.
有些人可能会争辩说，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。然而，这难道不也是很人性化吗？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？因此，生成式 AI 在某种程度上具有与人类创造力相似的特点，尽管它们并非完全相同。那么，如果我们认为生成式 AI 具有创造力，这是否意味着它会削弱人类创造力的价值呢？在我看来，答案是否定的。
我们的创造力在受到他人创造力的影响时才会变得更有价值。当我们与其他有创造力的人一起集思广益时，我们可以从彼此的想法中汲取灵感，从而创造出更具创意的作品。生成式 AI 世界将进一步加速这一过程，使我们能够更迅速地获得新的想法和解决方案。总之，生成式 AI 的创造力并不意味着它会削弱人类创造力的价值，相反，它可能会成为我们实现更高水平创造力的有力辅助工具。
人类和AI之间的协作可以激发一种相互创造的过程，而这种过程往往产生出一些最好的想法。这些想法并不仅仅来自AI为我们单独创造，更在于当AI与我们一起创作时所迸发出的灵感。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。
在学习者与他们的创造性方面互动时，使用AI可以带来一些极其独特和奇妙的经历。例如，当学生希望写一个故事时，AI会询问他们关于主角的设想，包括主角的性格特点、面临的挑战等等。在这个过程中，AI可以成为学生的良师益友，帮助他们发掘自己的创意潜力，同时也能够引导学生探索新的兴趣领域。
总之，AI在教育领域的应用已经越来越广泛，它可以作为一种工具来促进孩子的成长和发展。通过与AI的互动，孩子们可以更好地发挥自己的创造力和想象力，培养出更多的兴趣爱好。因此，我们应该充分利用AI的优势，为孩子们提供更加丰富多彩的学习体验。
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。
以下是重构后的内容：
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。这是因为人工智能让他们参与了创作过程，从而激发了他们的创造力。在这个过程中，他们可以与主要角色进行直接对话，并让 Khanmigo 演绎特定的情节线。这种互动式的学习方式让我的女儿作为创作者能够更好地测试自己的想法和创意。
AI 在设计时需要遵循一定的原则和约束，以确保它不会替学生完成工作。同时，它也需要给予学生充分的自由度来发挥他们的创造力。这样一来，学生可以在规定的范围内自由探索和发挥想象力，从而更好地学习和成长。
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. The AI used the "Yes, and" technique to encourage students to collaborate on a short story. Here's an example of how this activity went:
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.
STUDENT: When Luna put the shell to her ear, she heard voices from the past.
这个活动的目的是让AI充当一个引导者，帮助学生更好地参与到故事创作中来。通过这种方式，学生们可以更加自由地发挥自己的想象力和创造力，同时也可以锻炼他们的写作能力。
总之，在 2023 年初推出 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。这种活动旨在让 AI 充当一个引导者，帮助学生更好地参与到故事创作中来。通过这种方式，学生们可以更加自由地发挥自己的想象力和创造力，同时也可以锻炼他们的写作能力。
以下是重构后的内容：
KHANMIGO分享了村庄祖先的故事和智慧，这些声音帮助露娜与传统建立联系。有一天，露娜在贝壳中听到神秘的声音，描述了一个位于附近洞穴深处的隐藏宝藏。这种互动模式展示了AI如何通过创作工具来激发学生的创新思维并给予建设性的反馈，这不仅仅体现了AI的智能应用，同时也是对学生独立思考能力的锻炼。
在这个过程中，学生不仅接收到AI生成的句子，而且还需要根据此句继续撰写下一句。这个过程鼓励了学生之间的合作，因为他们需要理解AI的创作意图，并在此基础上延续故事。此外，AI的反馈可以帮助学生理解他们的创作是否合乎逻辑，是否连贯，以及是否有其他可能的角度可以阐述故事。这样的互动环境有助于提高学生的批判性思维和创新意识。
总的来说，AI像Khanmigo这样不仅提供了一个无判断的环境让学生自由表达想法，还通过提供故事和智慧来帮助他们连接传统，同时通过给予反馈来引导学生的创新思维。
Artificial Intelligence (AI) is transforming the way we learn and acquire new skills. In the past, individuals faced significant barriers to entry when learning various crafts due to the need to master specific sets of skills. However, with the advent of AI, anyone can now learn to paint, for instance, using large-language-model AI tutors. These AI assistants offer inspiration, guidance, and constructive feedback, as well as help users explore different artistic styles, themes, and compositions by generating a variety of reference images and samples.
As you work on your art, the AI provides real-time feedback to ensure that your composition, proportions, and color choices are accurate. Large language models can even make sense of images and ask students to draw a picture, followed by providing a critique of their drawing. In fact, they can even prompt students to express themselves and explain what they drew. The use of AI in learning offers numerous benefits, including personalized learning experiences, increased accessibility, and faster learning speeds.
In conclusion, the emergence of AI has significantly reduced the barriers to entry for individuals seeking to learn new skills. With AI-powered tutors, anyone can now learn to paint or any other craft, receive instant feedback on their progress, and explore different artistic styles and themes. As AI technology continues to evolve, it will undoubtedly play an increasingly crucial role in shaping the future of education.
随着人工智能的出现，我们见证了入门障碍的重大转变。这些曾经限制人们学习各种技能的障碍现在已经不再存在。在过去，学习一门手艺需要建立一套特定的技能体系，但现在，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助手为你提供灵感、指导和建设性的反馈，或者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会提供实时反馈，确保你的构图、比例和颜色选择是正确的。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。
此外，生成式AI还可以作为写作导师，教导学习者探索多种体裁、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。
总之，随着人工智能的发展，教育领域也将发生深刻的变化。这些变化将使学习变得更加便捷、个性化和有趣。无论是学习绘画、写作还是音乐，大型语言模型和生成式AI都将成为人们强大的助手，帮助他们突破传统的学习障碍，实现自己的创造力和潜能。
Technological advancements have been a driving force behind the evolution of art, with the earliest form being photography. While nineteenth-century portrait artists viewed early cameras as a potential cheat, photography evolved into a unique and innovative art form. Similarly, animation has undergone a significant transformation, from traditional hand-drawn methods to modern computer-based animations. Despite this transition, there is no indication that technology has cheapened or diminished the artistry of these forms.
Indeed, technological advancements have opened up new avenues for creativity and expression, allowing previously unfeasible artistic endeavors. For instance, children today can utilize standard movie software on their computers to create special effects that were once considered state-of-the-art in the 1990s. Additionally, filmmaking, which was once a costly and resource-intensive process, has become more accessible due to the widespread availability of digital cameras and smartphones. These tools have not only made creative production more convenient but also expanded opportunities for people across all walks of life.
The key point to consider is that each generation is fortunate enough to benefit from increasingly sophisticated and innovative creative tools. Rather than suppressing human creativity, these advancements have actually amplified it. As we continue to explore new frontiers in technology and innovation, it is likely that we will discover even more ways in which it can enhance the artistic experience
利用先进技术来增强艺术创作并非新潮流。在19世纪，肖像画家可能会把早期相机视为作弊工具，但摄影却演变成了一种新的艺术形式。第一部动画是手绘的，而随着时间的推移，动画逐渐转向计算机。有人可能会争论这种转变并未降低艺术的价值。事实上，它通过实现前所未有的想象力表达，从而提升了艺术地位。如今，我的孩子们可以在电脑上使用标准的电影软件制作出在1990年代被认为是最先进的特效效果。或者我们可以这样想：直到最近，电影制作还需要庞大的预算和昂贵的设备。现在，更便宜、更轻便、更高分辨率的数码相机和智能手机不仅司空见惯，而且以前所未有的方式拓宽了人们的创作空间。关键在于，每一代人都有越来越好的创作工具。这些工具从未抑制过人类的创造力。相反，它们放大了它。
oppola, in an interview with the Wall Street Journal, discusses how generative AI can impact the creative industry. The topic of discussion revolves around whether or not generative AI will eventually replace professional creatives such as screenwriters. Coppola notes that while it is a real challenge, the net effect of generative AI is that we will see more expressions of creativity from individuals with wider and deeper skill sets. This will be due to both necessity as well as the opportunity provided by generative AI.
Screenwriters, for instance, will be forced to expand their skills beyond writing scripts alone. Coppola predicts that they will eventually become full movie producers, taking on roles such as senior screenwriter, editor, music director, and visual director. While this may seem daunting at first, Coppola believes it could ultimately lead to greater collaboration between humans and machines within the creative industry.
In order to address concerns about the potential loss of jobs to generative AI, Coppola emphasizes the importance of maintaining human oversight in the creative process. He suggests that rather than fearing automation, humans should embrace it as a tool to enhance their own abilities and creativity. Ultimately, he believes that the key to successful integration of AI in the creative industry lies in finding a balance between human input and technological advancement.
人工智能大象与创造力
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.”
科波拉表示：“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. Today, we see this changing. 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. 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.
创造力似乎是一个可能的概念，当我们考虑到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。莫扎特、爱因斯坦和达芬奇不仅仅是天生的才华横溢，他们还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。
人工智能在很大程度上为我们提供了几乎任何主题的信息，同时也成为艺术中的伙伴，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。而现在，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”。这句话告诉我们，我们应该给予他人肯定和鼓励，让他们感受到自己的价值和成就。这样，我们才能共同创造一个更加美好的世界。
