如何使用AI进行中学历史教学

推荐一篇文章，一个历史老师用GPT给学生讲课，https://resobscura.substack.com/p/simulating-history-with-chatgpt亮点有两个：1、通过GPT生成一个"沉浸式"历史片段游戏，让学生扮演一个角色"设身处地"的做决策。2、学生的作业是找出GPT的错误。可以试试这个案例，明朝灭亡，南京，1645年5月（GPT3.5）https://chat.openai.com/share/86815f4e-674c-4410-893c-4ae3f1b7412e/continue（文科生未来的作业越来越难了）英文版本：Since January of 2023,I’ve been experimenting with using large language models(LLMs)like ChatGPT as a teaching tool in my history classes at UC Santa Cruz.I’ve been thinking about the implications of AI in teaching since I first began using GPT-2 back in 2019.I have also been following along avidly as my wife[Roya Pakzad](https://www.royapakzad.co/)works on testing the human rights impacts of AI systems(Roya was a consultant for OpenAI in 2022,where she served on the“red team”for adversarial testing of a pre-release version of GPT-4;you can read her account of that work[here](https://royapakzad.substack.com/p/old-advocacy-new-algorithms)).What follows are some thoughts about what I believe to be a novel use of LLMs:using them to simulate interactive historical settings as part of a university assignment.The results of these early trials are why I am personally much more excited about generative AI than many of my colleagues—though I also concede that in the short term,cheating will be a major problem.

If you’re teaching an art class,you might not want AI-generated images but you might embrace AI-generated images in a history class where students work on making infographics to demonstrate their understanding of macroeconomics principles.It might feel like cheating for a student in a film class to use AI for video editing but the AI-generated jump cuts might save loads of time in a science class where students demonstrate their learning in a video.In a film class,it’s critical for students to learn how to edit by hand in order to tell a story.In science,AI-generated jump cuts allow students to create videos quickly so they can focus on the science content.I also want to recognize that some of what students learn can and will become obsolete.I’m pretty sure I didn’t actually need to memorize the state capitols,for example.Which leads me to the next question...But What If We Don’t Need That Skill Anymore?I grew up in an era where teachers were moving away from memorization.We still had to memorize math facts and,for some reason,state capitols.I’ve never visited a state and thought,“Man,I really need to see the capitol.”If I’m Nevada,I’m not like,“Screw Vegas,I’m going to Carson City!”But,for the most part,we had moved past memorization.We were now in a largely print-based culture and memorization just wasn’t too important anymore.For many people,this tradeoff is a good thing.Why memorize it if you can access the knowledge with technology?However,when I was in college,I decided to memorize key texts that I wanted with me at all times.I memorized Bible verses and Shakespearan stanzas.I memorized an ee cummings poem and a quote from bell hooks.I memorized Stoic passages and the every word of the Bill of Rights.

教育科技长期以来一直在有效性和规模之间做权衡。为大众打造有效的解决方案，就会失去吸引个体的个性化。为满足个体的需求而打造完美的解决方案，却又难以扩展。有了AI，这种状况不再存在。我们现在可以大规模部署个性化的学习计划，为每个用户提供一个“口袋里的老师”，这个老师理解他们独特的需求，并可以回答问题或测试他们的技能。想象一个由AI驱动的语言老师，能够实时交流，并对发音或措辞给予反馈。[Speak](https://www.speak.com/)、[Quazel](https://www.quazel.com/)和[Lingostar](https://www.lingostar.ai/)已经在做这样的事情！我们已经看到了教授新概念或帮助学习者在几乎所有学科中“摆脱困境”的产品。像[Photomath](https://photomath.com/en)和[Mathly](https://mathly.webflow.io/)这样的应用指导学生解决数学问题，而[PeopleAI](https://chatbotkit.com/apps/peopleai?ref=theresanaiforthat)和[Historical Figures](https://twitter.com/scottbelsky/status/1611244139764649991)通过模拟与杰出人物的聊天来教授历史。除了学习特定的科目，学生们还在他们的作业中利用AI助手。像Grammarly、[Orchard](https://orchard.ink/)和[Lex](https://lex.page/~)这样的工具帮助学生克服写作难题，并提升他们的写作水平。处理其他形式内容的产品也在全国各地的中学和大学中越来越受欢迎——例如，[Tome](https://beta.tome.app/)和[Beautiful.ai](https://www.beautiful.ai/)协助创建演示文稿。了解更多关于[AI时代学习的未来](https://a16z.com/2023/02/08/the-future-of-learning-education-knowledge-in-the-age-of-ai/)。