2026 年 9 月 4 日 · 罗博深

一个学数学的人如何用 AI 做出一整套广告

如果苹果Buc-ee’s迈克尔·杰克逊联名,会是什么样?

说明:这篇文章的英文原文是我自己一字一句写的,然后请 Claude Code 围绕它做出这个网页。最初的提示词(连同原文)也在那个文件里。中文版由 Claude 翻译。

English

上周,我需要为一整套视频广告设计一个投放活动,推广的是我们的高阶数学课:对乡村学校、或免费/减价午餐比例在 85% 以上的学校的孩子完全免费,对其他人价格也很合理。我对这套广告的设想是:如果苹果Buc-ee’s迈克尔·杰克逊联名,会是什么样?只有一个问题:我没有设计师,也没有预算。

我手里倒是有一支很喜欢的范例,是一年多前由才华横溢的 Julia Du 专门设计的。她从帕森斯设计学院毕业、入职谷歌之前,曾在我们这里兼职。

多亏了 ClaudeCodexRemotionStoryblocksGoogle LyriaElevenLabs,我们有了一整套广告。当然,它比不上专业设计师的作品。但它似乎已经胜过了课外数学培训行业里所有其他的广告。而那些公司其实有着庞大的营销预算,我们却把利润拿去教低收入和乡村地区的孩子。

10 支广告 · 点一支听声音
先说那个坑

「做一个视频广告」

我知道,如果我直接让 AI"做一个视频广告",多半会得到一个平庸又无聊的东西。(这背后有一个数学上的理由,下面会讲。)当时我懒得试,但为了好玩,我刚才试了一下,用的是这条提示词:

PoChatGPT
我很好奇你能做出什么。参考这支广告,做一个视频广告。这是我们的独特价值主张。要做得超级棒。
202503-julia.mp4
点击跳过打字

它做出了这个:

Julia 的广告,也就是我上传的那支。用 Adobe After Effects 制作,文字在每一帧里俏皮地依次出现。
ChatGPT 的广告,来自那一条提示词。

唉。它看起来很平庸(后面会详谈)。Julia 那支视频的精髓,是让文字在每一帧里俏皮地出现,这一点完全丢了。而且 ChatGPT 没办法弄到真人的视频,人情味也没了。至少它没有用 AI 生成假人。版面和精细度看起来很粗糙。文案本身倒不算太差。

如果你好奇,几天之后,我也试了 OpenAI Codex,用的是 GPT-5.6 Sol High Effort,作为我已经用 Claude 成功之后的另一次测试。即便给了提示,还能完整访问 Claude 的代码库和我们后来生成的配乐,它做出来的是这两版。

为什么"平庸"是默认值

256 的 60 亿次方

AI 生成视频之所以难,有一个数学上的原因:视频空间的维度大得惊人。最基本地算,一支 30 秒、1080×1080、每秒 60 帧的视频,就是

30×1080×1080×602×10930 \times 1080 \times 1080 \times 60 \approx 2 \times 10^{9}

每个像素各有红、绿、蓝三个值,总共 60 亿个维度。如果每个值的范围是 0 到 255,那就是

2566,000,000,000256^{\,6{,}000{,}000{,}000}

种可能性要在其中做优化。相比之下,写一条 150 个字符的英文推文"只有"大约 3015030^{150} 种可能。要命的是那个指数。实际上,AI 算法(也许还有我们人类的智能)的目标,就是在这两种情形下都大幅降低维度。

也许这就是 AI 生成的视频常常显得"平庸"的原因:要把所有可能性搜一遍、比一遍,时间长到不可能。可让一个产品脱颖而出的,恰恰是成为标志性的存在。我曾听过一场营销讲座,讲者说,永远不要试图告诉别人你"在 X 上做得最好",而要成为"唯一做 X 的那一个"。而这需要洞见。

解锁 1

找到那门语言

一门能用文字把整段动画完整描述出来的编程语言。

在这件事上,洞见就是降维:让 Claude 去找一门编程语言,能用文字和命令完整地定义整段动画。注意,我并没有先让 AI 去做广告,而是让它去研究:怎样才能把维度大幅压缩。

PoClaude Cowork
打开 ~/ad.mp4,看看它的风格。然后看看 ~/julia 里的文件,那些是素材片段。我想做我们自己的衍生广告。我在想,现在能不能用某种网页格式来做,自己渲染、输出 MP4,而不用 Adobe After Effects。这样一来,一切都可以用程序来指定。这真的可行吗?如果可行,用什么最好?Next.js?React?Vue?
点击跳过打字

回答非常精彩:

Claude Cowork

回答:可以,而且"选哪个框架"本身就问错了方向。 Next.js 是一个网页应用框架,根本没有"帧"的概念。这项工作需要的是一个确定性的逐帧渲染器:t=3.2 秒时的画面,是第 96 帧的纯函数,这样无头 Chrome 就能一帧一帧地推进,再把结果送进 FFmpeg。

我调研了这个领域,并且实际做出了两支可运行的衍生广告作为证明,而不是空口断言可行。考虑过的方案:

方案结论
Remotion选定:已成熟出货,音频同步业界最佳
HyperFrames (HeyGen, Apache-2.0)有力的竞争者,无许可费,但版本还在 0.7.x,音频处理别扭
Revideo (MIT)0.x 版本;厂商自己也承认开源仓库落后于其商业产品
Motion Canvas排除:约 20 个月没有稳定版本,没有无头渲染路径
Editly / fluent-ffmpeg排除:fluent-ffmpeg 于 2025 年 5 月归档,并自称已失效
DIY Puppeteer capture排除:等于自己重新实现确定性的虚拟时间截帧
Shotstack / Creatomate / JSON2Video排除:只有托管版,按分钟计费,做大量变体时太贵

而且,它做出的第一版结果已经出人意料地不算差!

流水线里出来的第一个东西。不是最终质量,但已经走在正确的路上。

尤其因为我评判它的标准不是最终质量,而是在"降维"这条路上前进了多少。我知道,一旦能通过 Claude Code 流水线在 Remotion 里复刻 Adobe After Effects 的能力(这是解决整个问题的第一大块),我就能生成海量的视频。而这个特定的输出表明,用代码生成专业水准的文字动画是可能的。于是我接着问:

PoClaude Cowork
这已经很不错了。但你做的东西没有她做的那么亮眼。你能尽可能地复刻她的那支吗?另外,我们的品牌字体已经换成了开源的 Plus Jakarta Sans。
点击跳过打字

结果是这样:

Julia 的原版,手工制作。
复刻版,完全由代码生成,字体为 Plus Jakarta Sans

我非常兴奋地看到,我这个刚起步的系统不仅能把所有必要的组件(动画和视频)都带进来,还能把 Julia 的视频当作范例来理解并从中学习。值得注意的是,它做到这一步,靠的是仅仅一个范例,而不是海量的训练数据。这告诉我,我找到了表达 Julia 那支视频的正确语言。

于是,该开始迭代了。为此我需要追踪所有的版本,因为进展多半会是进两步、退一步。

PoClaude Cowork
这已经很不错了。我建了一个 Git 仓库,叫 Expii/ads-live-motion。请把复刻版的源代码和所有生成相关的东西都放进去。当然不包括渲染出来的成品。另外,务必写好说明,并留下我评论意见的记录。
点击跳过打字

那时我还意识到,我并不需要 macOS 上的任何东西(一开始我不确定),于是我问,是不是可以离开我的 Mac Mini M1 了。

PoClaude Cowork
我在考虑把这项工作搬到一台运行 Linux、搭载 AMD Ryzen 5 9600X 六核处理器的机器上,用 Claude Code 来做。可以吗?还是说我需要 Cowork 的全部能力?
点击跳过打字

换过去之后,进度快了很多。部分原因是我主力的 Linux 工作站有 5 台显示器,竖着排列。

一台 Linux 工作站,五台显示器竖向排列
五台显示器,竖着排。Claude Code 就在正中间。
解锁 2

一段定制配乐

用同样的办法给声音降维。

接下来是声音。过去我们只是买一段配乐,反复使用。在这么短的时间里就有了这样的收获,我胆子大了起来,决定做一段定制配乐。我记得和影视行业的人聊天时听说过,电影制作中真正高品质的标志之一,是专门谱写的配乐,能够衬托并加深画面上的情感。

PoClaude Code
好,这已经相当不错了。你也能自己生成配乐吗?如果能,请给 spinoff-c 配上。
点击跳过打字

不幸的是,那段配乐糟糕得可笑,听起来像 1990 年代的电子游戏。即使让 Claude 再努力一点,也没有多大改善。这时我意识到,我需要再次降维:去找一个能把文字变成音乐作品的工具。

PoClaude Code
画面很好,但声音不行。我觉得画面之所以这么强,是因为你用了一个非常好的工具来渲染视频,效果质量很高。请找一个同样好的工具来作曲并合成音频,最好还能像你在这里做的那样把时间点考虑进去。当然,音效是另外单独叠加的。
点击跳过打字

它找到了 Google LyriaElevenLabs Music。两者都不到 10 美元,于是我两个都开通了,把它们的 API 密钥交给 Claude Code。它随即生成了一大堆配乐让我听。但这很不方便,因为我得在脑子里想象视频配上声音是什么样。所以,顺理成章的下一个请求是:

PoClaude Code
你能快速做一个简单的网页应用,让我把音频和视频放在一起预览吗?
点击跳过打字

不到一分钟就做好了,还挺有格调。

试听室:一个网页,把每支渲染好的广告和每一首候选配乐同步播放,可以打星、写批注
试听室。每支广告配上每一首候选配乐,同步播放,可以打星和批注。

有了这个界面,我进行了 7 轮反馈来"训练"音乐。音乐同样是极高维的。我意识到,降维的办法可以是设定三个阶段的情绪:开头沉思,接着兴趣被勾起,最后凯旋收尾。我想起 20 多年前听一位大学室友聊过音乐理论,记得有和弦进行、大调小调、转调这些东西。这些我其实都不太懂,但这点常识给了我可以提示的方向。最终,我有了一台能产出各种配乐的通用引擎,开头那些视频里的配乐就是这么来的。(这些配乐还不是最终版,我仍在试验提示词的写法,尤其是和弦与调性方面。)

解锁 3

真人,且有授权

痛点用素材库镜头,课堂用真实的录屏。

接着我回到画面上。我一般不喜欢 AI 生成的画面,因为我不想展示假的东西。和 Claude 讨论之后,我了解到它能在一个叫 Storyblocks 的平台上搜索素材库镜头。于是我让它把所有可能的供应商都调研一遍:

PoClaude Code
我很乐意从付费素材库购买有授权的片段。这将是一个付费投放的广告活动。但价格得合理。
点击跳过打字

最后的两个主要候选是 Adobe StockStoryblocks。但关键在于,Claude 无法搜索 Adobe Stock,却可以不登录就搜索 Storyblocks。(当然,它拿不到高清视频文件,但可以筛选镜头、推荐片段。)这成了决定性因素。Claude Code 的搜索能力,加上它为每支广告构思的故事,将提供完成每一支作品所需的真人镜头。

到这里,我为每支作品定下了一个设计框架:凡是讲我们的课,就用真实课堂的屏幕录像(不摆拍,更绝不用 AI 生成)!凡是展示外部世界的痛点,就用素材库镜头。所有这些用俏皮的文字动画串联起来:

PoClaude Code
另外,向 Julia 的视频学习,它在某些地方依然更精致、更有创意。比如她想到了让素材镜头平移。她还用了 Adobe After Effects 里很多俏皮的效果。我们不需要全部复刻。但就像我建议在 C 里用"复制粘贴"的动画那样,想想怎样让巧妙的动画选择来支撑故事。我觉得不需要多余的干扰,但我们可以明显地深思熟虑。我希望这些广告能挠到人的智力痒处,让人说:哇,这太有深度了;同时又和当代的孩子与娱乐合拍。就像迪士尼电影有多层含义,分别打动孩子和大人。顺便,把这套理念记录下来,好让我们做出一个标志性的广告系列。其实,如果你能帮忙头脑风暴什么才算标志性,那就太好了。就像 Buc-ee's 有它标志性的风格一样。记住,我们的目标是"标志性",因为正如你自己调研过的,我们比其他所有人都高出一大截。
点击跳过打字
解锁 4

让 Claude 有底气

它不会为一个自己不相信的说法全力以赴。那就让它是真的,并让它自己去核实。

哦,关于那条提示词的最后一句,说明一下。我读了 Claude 的宪法(是的,全部读完了),我的理解是:Claude 不应该欺骗。所以我相当确定,除非 Claude 自己确信这里真有特别之处,否则它不会全力以赴。为此,我此前就给它看过一份我几年前写的文档,讲我们课程的独特价值主张;还特意让 Claude 自己做独立调研,建立起必要的信心:

live-unique.md
14 个小节 · LIVE 为什么是"唯一这么做的"

Unique aspects of LIVE by Po-Shen Loh (online math classes for middle schoolers that teach creative problem solving and critical thinking, using math contest problems)

The best instructors

  • Instructors are among the most extraordinary of their generation, when considering both math skill and emotional intelligence combined
  • Instructors are top finishers in competitions ranging from math to computer programming to debate
  • Last year, among the instructors who graduated high school, more than half of them are now studying at MIT, Princeton, and Harvard
  • They are also specially selected based upon their emotional intelligence
  • They are only a few years older than the learners, and still remember what it was like to learn, but unlike other programs which have high schoolers teaching, they have received extensive specialized training in teaching and performing
  • Admission to our instructor program is a highly sought-after achievement in itself, because it’s the only program which provides systematic professional performing arts training to math stars, helping them develop whole-person skills that change their life
  • Why are the best instructors with us? Because in order to succeed in life (and gain admission to top colleges), it is a huge advantage to build extraordinary communication skills. If a high school math star wants to do that, they must practice at some point by talking about something and getting feedback. Our breakthrough was that we realized that the easiest topic for them to talk about is math, and then we provided professional actors and comedians to coach them simultaneously while they are teaching that math. So for them, one hour of teaching math equals one hour of feedback on their communication, and they win while learners win. (There’s no way to gain feedback without talking about something, and the easiest thing for them to talk about is math.) Nobody has ever done this before.
  • We’re the only educational ecosystem for which whenever we ask an instructor to do anything, we only do it if that task is intrinsically the best use of the instructor’s time in terms of the instructor’s personal development.
  • Consequently, we attract the world’s best instructors

We actually made online math class more attention-grabbing to students than in-person math class

  • Nobody pays attention to a Zoom class, but the same kid can watch YouTube or a livestream all day. So we did it the other way round: instead of taking math class and putting it online, we took what everyone already watches online (a live show with hosts, a chat, production) and put math inside it. We are the first math class built that way.
  • Before us, online math classes had a huge problem: they were most effective at teaching students how to sleep
  • Some products tried to artificially make online math class seem more exciting with random sound effects and cartoon characters, but those are non-human, and distract from the intrinsic love of hard math as a human endeavor
  • We realized that there is no fundamental reason why an online video makes kids fall asleep, because kids love watching online videos
  • We realized that what makes everyone fall asleep is big boring Zoom meetings in which someone drones on and on, and the viewers passively watch
  • We realized that some key differences between other online classes and actually addictive video entertainment were: (1) emotional passion of multiple co-presenters on camera, (2) intensely active chat showing the emotions and ideas of the viewers, which made the viewers feel like they were really part of the whole thing, (3) the visual appeal of the experience, as a professional looking streaming host looks totally different from a tutor sitting in their kitchen. So we built all of that in.
  • Students in our class speak up more than students attending in-person classes, because we turned online into an advantage! In-person, you can’t just keep talking, because that will disrupt the sound in the room, and people can’t hear the teacher. Online, you can always hear and see the teacher, but we have a live chat feed overlaying the corner of the screen, showing everyone’s reactions at the same time.
  • We also specially train our instructors to emotionally connect with students, so that they aren’t only delivering math knowledge. They’re making students interested in them from a human emotional perspective. And while they’re teaching, a professional actor keeps this training fresh.
  • The instructors being close in age to the students is also attention-grabbing. Students feel emotionally closer to the instructors.

The world’s first and only math program which has 2 live-streaming instructors interacting with each other and with students just like a TV show

  • This instantly makes it more entertaining and lively, much better than one instructor talking to themself
  • We were able to do this because we are the first and only program to systematically train our instructors in improvisational comedy, through professional comedians, and provide them with continuous feedback while they teach every subsequent class.
  • This also allows the math to be more dynamic. Instructors don’t have to worry about whether students will suggest something that is beyond their expertise, because there are 4 math experts teaching together, and even if something actually does require further research, one instructor can actively lead the class to think, while the other 3 research, and then the other instructor can take over and explain. This provides seamless redundancy. In the 1-instructor classroom, if the teacher is asked something that they don’t know about, they are stuck.

The only math program which combines extreme expertise in math with expertise in performing arts

  • Founder Po-Shen Loh is a professor at Carnegie Mellon University, which also happens to be one of the very top Drama universities in the USA. It’s the same Carnegie as Carnegie Hall in New York City. Many of that university’s alumni are Broadway and Hollywood actors, who have won Academy Awards and Tony Awards. Our actors come from that extraordinary network.
  • Founder Po-Shen Loh also served for a decade as the national coach of the USA International Math Olympiad team, and travels extensively to keep in touch with thousands of high school math superstars across the country.
  • He was the first to bridge these two extraordinary-level worlds together.

If we can’t make your kid love hard math, nobody can

  • We’re the only math class in the world which has a professional actor in every classroom, giving real-time feedback to the instructors to improve the attractiveness of their presentation
  • We don’t teach routine math.
  • We provide hard challenges just like a TV game show, and then use the skills from professional performing arts to encourage students to rise to those hard challenges
  • We weave human emotion and excitement in, together with compassion and understanding that it’s emotionally difficult to be stuck on a hard thing
  • We celebrate as students collectively make breakthroughs in understanding
  • We package all of this into a professional experience

The only online math class that looks and feels like the entertainment that kids watch

  • We built our own technology (combining software, hardware, and lights and equipment) to transform “Zoom School” into a professional experience
  • Every other online math class actually looks the same. Ours looks totally different.
  • No other online math class can make its instructors look as cool as ours, because just having the equipment isn’t enough. The instructors need to have the emotional polish to come across as professional entertainers, or else it just looks weird to have a professional setup and a person who doesn’t know how to emotio nally connect with an audience. The reason we can go all the way is because our instructors actually have those performing arts skills too.

The only online math class that dares to show actual footage of class as its advertisement

  • This point actually speaks for itself.
  • Every one of our math classes has a professional production team behind it, making sure that the live stream is at the quality that one would expect from entertainment

Architected and led by the world’s most famous math coach

  • Po-Shen Loh’s work and discoveries have been covered in the Wall Street Journal, New York Times, National Public Radio, the Washington Post, and even international newspapers such as the Straits Times and the Australian Broadcasting Corporation
  • He is the world’s most active traveling math educator, giving ~200 in-person talks per year to tens of thousands of attendees.
  • This allows him to develop and maintain a deep understanding of the math needs of students and parents. That’s how he thought of this invention.
  • Loh is himself a math contest star. He ranked #3 in the USA in the MATHCOUNTS competition when he was a student, and was also one of the 6 members of the USA International Math Olympiad team in 1999, where he won a Silver Medal at the world finals.
  • He went on to win the USA Presidential Early Career Award for Scientists and Engineers
  • He has been a math professor at Carnegie Mellon University for 14 years
  • He’s the same person who was the national coach of the USA math team when it ranked #1 in the world in 2015, for the first time in 21 years
  • He is also an inventor, with multiple patents

We use performing arts skills to encourage shy students to love math

  • Our instructors are specially trained to notice when a usually-quiet student suggests an idea in the chat
  • Many shy students are afraid to raise their hand in class because they aren’t sure whether their answer is right, and they’re worried that other people will laugh at them or think they are stupid
  • In our system, students are encouraged to say brainstormed ideas which are not yet fully formed, so it is normal for lots of ideas to be still-solidifying
  • When we see a student who hasn’t spoken much before, but sends a comment with a valuable bit of an idea (doesn’t even need to be fully formed), we pick them out and invite them (if they wish) to come on stage and share that idea, telling them that it’s a great idea. They are then more confident to share it, and then our instructors are specially trained like TV hosts to make them feel good about sharing that idea (“Thanks so much for sharing this!”) This encourages even shy students to actively participate, because they see that whenever anyone is called upon to present, that person is always backed up by the instructors and ends up looking good

The only math class in which if you say a wrong answer, you will still be encouraged for the right part of your wrong answer

  • Instructors are specially trained in improvisational comedy, which is the art of “Yes, And”. That is the principle of a performer finding elements of truth to agree with in whatever they hear, and then adding more value in their reply. They do not just say “No.”
  • Instructors are trained to instantly think about the math behind any wrong answer, and use their math skills to figure out where there might be some value. Perhaps the student started off in the right way, but made a mistake that resulted in the wrong answer. Instructors will then congratulate the student on the good part of the idea, and gently suggest that the wrong part is wrong.
  • This encourages students to actively participate, because they know that as long as they’re thinking, it is safe to speak up. Instructors have their back.

The only math class in which you can really learn how to brainstorm

  • Since we have a team of 4 math experts leading each class (2 on camera and 2 off-camera), students can really say any idea, and instructors can follow through with those ideas. Nothing will stump them
  • Also, since our classes are video-based, instructors can dynamically write out students’ proposed ideas on screen, and discuss them dynamically. Instructors are not limited to Powerpoint slides.
  • Since we have full confidence in our instructors’ ability to dynamically handle anything, the format of the class is: students are shown a problem that they haven’t seen before. Instructors invite students to brainstorm, and serve as game show hosts to help students collectively brainstorm a solution.
  • Importantly, instructors DO NOT first show students an example of how to do a problem type, and then give them practice.
  • The reason why our instructors can let students direct the flow of the brainstorming is because they are so good at math (and have so much backup with the 4-person math instructional team in each classroom) that they will not get stuck.

The only math class where you can learn from people who are close to your age, yet brilliant and down-to-earth, and extensively trained in the art of entertaining teaching

  • Speaks for itself

The only math class that also teaches the non-math values that the top US universities look for

  • Instructors are carefully screened through an intensive application process that includes an interview
  • We seek instructors who are not only good at math, but also empathetic, and really love helping people
  • They are role models for how a person can be simultaneously brilliant, but also are like sunshine with a real interest in helping other people
  • They show students that an ideal math genius is someone who is not only great at math, but also genuinely loves helping other people
  • Eventually, when you apply to college, it’s not enough just to tick a box saying that you did 200 hours of community service. What really matters is whether you fundamentally developed a love of helping other people. It’s impossible to give a kid a philosophy book to have them develop this theoretically. Role models are required. Our instructors are those role models, on the fast track to success.

The only math class where you are supposed to talk as much as you can, saying all of your ideas and your reactions

  • Each class is led by a team of 2 instructors, 2 teaching assistants, and 1 actor
  • We have our own special technology to put students’ comments up on screen for everyone to see, like an Instagram Live stream, but with active moderators
  • Other Zoom classes could not do this, because there was no way to moderate the chat. So, during the pandemic, most people’s experience with Zoom was that the teacher told students not to chat, and then students stopped paying attention. We fixed this with our own software.
  • With 4 people who have math expertise, students can ask or say anything, and every question gets answered. It’s much better than an in-person class, where if you raise your hand, you might not get called on.
  • Our instructors are specially trained to manage a high-energy, highly interactive discussion. The more students who send messages at the same time, the happier they are. And they are specially trained to call on students to come on stage and voice their opinions too, prioritizing students who have not been on stage yet.
  • Students actually love having their voices heard, and it makes them feel ownership in the experience.

原始文件: /live-unique.md

PoClaude Code
好,这已经还不错了。请把文案打磨得更锋利。记住,你是在为市场上真正最好的产品做广告。为了让你对此更有信心,请你自己深入调研一下,市面上还有哪些线上的课外数学课程。也去把 YouTube 翻一遍。你可以使用 Google Chrome。如果需要我连接什么,告诉我该点哪里。
点击跳过打字

到最后,Claude 一支接一支地往外吐广告。我甚至让它做出了中文版。

同一支广告的中文版,竖屏。

而且,既然我已经为画面、故事线和音乐都选定了正确的"语言"来降维,Claude 就能自动合成整套广告,而我只需用平常的对话与它互动,推着它做出明确的改进。比如,因为有了正确的语言,我用大白话说要改哪里的时间、颜色或位置,Claude 都能可靠地改好。我那个"Buc-ee’s 加苹果加迈克尔·杰克逊"的目标,正在变成现实。

解锁 5

按基线打码

把真实课堂录像里的名字精确地打掉。

我还做了几件事。最重要的一件:既然我们展示的是真实课堂的屏幕录像,就得把学生的名字打码。这活儿痛苦得堪比从好莱坞电影里抹掉一撇胡子。过去我的团队只是糊上一大块模糊的矩形。现在我们可以做到这样:

一堂真实的课。聊天区里的每一个姓氏,都精确地打了码。

一开始我只是让它把姓氏打码,但结果不稳定。最终的成功来自让 OpenAI Codex(GPT-5.6 Sol High Effort)做一次 Goal Seek,把所有姓氏去掉,并给出了这样一条关于如何精确打码的指令:

PoCodex
对每一个姓氏,先找出文字的基线。打码的矩形:底边在基线以下 30% 处,顶边在文字行顶以上 15% 处,左边在前一个词结束后一个像素,右边在下一个词开始前一个像素(如果没有下一个词,就在姓氏结束后一个像素)。不要用这台电脑的 OCR 系统,因为你的视觉系统更好。
点击跳过打字
CarterLastname文字基线文字行顶向下 30%向上 15%前一个词结束后 1 像素姓氏结束后 1 像素
打码框以文字本身为准:基线和行顶,而不是凭眼睛画出来的框。

我用 Codex,是因为它在理解图像上似乎比 Claude 更强。GPT 5.6 Sol High 在这方面确实胜过 Opus 5。(我的 Fable 5 额度用完了。)于是我也以为 GPT 5.6 Sol High 在制作最终视频上会更好。结果它比 Claude 差得多。也许 Claude 就像贝多芬,失聪之后依然能作曲。

一些想法

我从没想过我会写一篇教人做视频的文章。我大学主修纯数学,之后所有的学位也都是纯数学。但看起来,在今天的 AI 世界里,纯数学对复杂性及其化简的直觉,加上广博的常识和经验,非常有用。

我有专业设计师那么好吗?绝对没有。我也一直敬佩那些探索创意与能力极限的人。但我(在预算极其有限的情况下)能做的事情的可能性空间,刚刚急剧扩大了。比如,我现在正考虑开一档视频播客,因为我可以搭一条自动剪辑、分享精彩片段的流水线。

那么,人在哪里?这不就是在制造更多的 AI 垃圾吗?其实不然。在这个过程中,全部的目标就是做出标志性的东西,而不是平庸的东西。能把大事拆成小块的思考者,依然极其有价值,因为这正是让你有效传达自己愿景的能力。平庸来自缺乏愿景。做标志性的存在。弄清楚你到底是谁。

某种意义上,这整套广告的内核,来自我们多年前的一个决定:把数学明星、职业演员、互联网直播和社会影响这几个世界融合在一起。正是这个决定,带我踏上了横跨全美的公路旅行,进行我的巡回演讲与倾听之旅,帮助人们走在 AI 进步的前面。也正是这些旅程,让我发现了 Buc-ee’s 的奇妙,我用 iPhone 给它拍照,在一首首迈克尔·杰克逊的歌之间。

thoughtfull
使命订阅通讯