如何利用AI做科普视频

|名称|作者/来源|总结|链接|发布日期|必看星标|图片|<br>|-|-|-|-|-|-|-|<br>|ChatGPT诞生记：先捞钱，再谈理想｜OpenAI翻身史|林亦LYi|ChatGPT的背后是OpenAI这家公司，今天我们聊聊它的理想、成果与争议。|[https://www.bilibili.com/video/BV1Te4y1w7D6/](https://www.bilibili.com/video/BV1Te4y1w7D6/)|2023/02/10|??||<br>|【渐构】万字科普GPT4为何会颠覆现有工作流|YJango|视频是关于GPT的底层原理和未来影响。将抛开技术细节，少用专业名词，在整体功能上讲解ChatGPT的「工作原理」「制造过程」「涌现的能力」「未来的影响」以及「如何应对」|[https://www.bilibili.com/video/BV1MY4y1R7EN/](https://www.bilibili.com/video/BV1MY4y1R7EN/)|2023/03/15|??||<br>|终于有人把chatGPT说清楚了——全网最深入浅出的chatGPT原理科普|新石器公园|本视频深入浅出的讲解了chatGPT的基本原理和演化过程，让你真正理解这个世界最大的变化。

By contrast,if you’re teaching a health class where a student develops an app,you might not care if they use generative AI to help write the code.Instead,your focus is on helping students design a health campaign based on healthy habits.You might not have time to teach students to code by hand.You might not care about coding by hand.The app is merely a way for students to demonstrate their understanding of a health standard.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!”

最佳动画工具：用于在视频中为人脸制作动画的[D-iD](https://www.d-id.com/)。用于从文本创建视频的[Runway v2](https://app.runwayml.com/)最佳语音克隆：[ElevenLabs](https://beta.elevenlabs.io/speech-synthesis)现在，生成一个完全由人工智能生成的角色的视频，阅读完全由人工智能编写的脚本，用人工智能制作的声音说话，由人工智能制作动画，这简直是微不足道的。[它也可以深度伪造人，正如你在这个链接中看到的那样，我伪造了自己](https://oneusefulthing.substack.com/p/a-quick-and-sobering-guide-to-cloning)，谨慎使用，但这对于制作解释视频和介绍来说可能很棒。最近还发布了第一个商用文本到视频工具Runway v2。它创建了4秒的短剪辑，更像是对未来发展的展示，但如果你想了解这个领域的未来发展，值得一看。一些需要担心的事情：深度伪造是一个巨大的问题，这些系统需要合乎道德地使用。