Ghost Font: A font that humans can read but AI cannot
Ghost Font: A font that humans can read but AI cannot
Ghost Font：一种人类可读但 AI 无法识别的字体
Ghost Font is an anti-AI font that can be read by humans but not leading AI models. Type your text below, then download and share the video clip containing your message. Ghost Font 是一种反 AI 字体，人类可以阅读，但领先的 AI 模型却无法识别。在下方输入文字，即可下载并分享包含你信息的视频片段。
What is Ghost Font? Ghost Font is an anti-AI font that writes a message using motion. Using a combination of motion, video, noise, and decoys, it’s a unique way to share a message with other real humans. I suppose technically, it’s not a font in the traditional sense of a TTF font file. But, Ghost Font is an experiment of a way to graphically communicate in writing in a format that AI cannot easily understand. While it’s not as legible as regular text, the letters are still immediately readable to a human eye, but even leading AI models can’t decipher it easily. 什么是 Ghost Font？Ghost Font 是一种利用“运动”来书写信息的反 AI 字体。通过结合运动、视频、噪点和诱饵信息，它提供了一种与真实人类分享信息的独特方式。从技术上讲，它并非传统意义上的 TTF 字体文件，但 Ghost Font 是一项实验，旨在探索一种 AI 难以理解的图形化书写交流方式。虽然它的易读性不如普通文本，但人类肉眼仍能一眼识别，而即便是领先的 AI 模型也难以轻易破译。
Videos generated with Ghost Font were then passed to leading AI models like Claude Fable and GPT Sol 5.6 Ultra. Even these recent agents, with the ability to code, struggled to decode the moving message until prompted with the exact technique to look for. 使用 Ghost Font 生成的视频被发送给 Claude Fable 和 GPT Sol 5.6 Ultra 等领先的 AI 模型进行测试。即使是这些具备编程能力的最新智能体，在没有被提示具体观察技巧的情况下，也难以解码这些动态信息。
The playground above is just a prototype of this concept. Type a few words and the letters appear but only because the motion of the dots is visible to a human eye. When the video is paused, the static dots blend together, and it becomes impossible to tell just from looking at a single frame what message is embedded in the image. That means that screenshotting the page won’t reveal the message. 上方的演示区只是该概念的一个原型。输入几个词，字母就会显现，但这仅仅是因为人类肉眼能捕捉到点的运动。当视频暂停时，静态的点会融合在一起，仅凭单帧画面根本无法分辨其中嵌入了什么信息。这意味着通过截图页面是无法获取信息的。
This experiment works locally—type the message and preview it live, or download the video to share and test it out yourself. The data is not shared or sent to any server. 该实验在本地运行——输入信息并实时预览，或者下载视频进行分享和测试。数据不会被共享或发送到任何服务器。
About this project: In 2013, designer Sang Mun released a font called ZXX. It was a typeface with four fonts designed to be readable by humans but not by optical character recognition (OCR) software. The letters were camouflaged with noise, crossed out, and buried under false marks. At the time, this font was deemed “surveillance-proof”—but fast forward to today, and modern AI agents can easily read text rendered in ZXX. 关于本项目：2013 年，设计师 Sang Mun 发布了一款名为 ZXX 的字体。它包含四种字型，旨在让人类可读，但让光学字符识别（OCR）软件无法识别。这些字母通过噪点伪装、划线和覆盖虚假标记来隐藏。当时，这种字体被认为是“防监控”的，但时至今日，现代 AI 智能体已经可以轻松读取用 ZXX 渲染的文本。
While this might have defeated OCR software in 2013, modern AI models can read the text in ZXX pretty easily. I copied this image into ChatGPT 5.5 on Instant mode, and it was still able to get the words including some small details as well in a single prompt. 虽然这在 2013 年可能难倒了 OCR 软件，但现代 AI 模型可以非常轻松地读取 ZXX 文本。我将图片复制到 Instant 模式下的 ChatGPT 5.5 中，它依然能在一次提示中准确获取文字，甚至包括一些微小的细节。
However, the same process with Ghost Font won’t work quite as easily. A single screenshot of Ghost Font will yield just a completely static image with no readable text. That’s because every letter in Ghost Font is made up of dots that look exactly like the background, so any single image from the video will not reveal anything about the message. 然而，同样的流程在 Ghost Font 上却行不通。Ghost Font 的单张截图只会得到一张完全静态的图像，没有任何可读文本。这是因为 Ghost Font 中的每个字母都由与背景完全相同的点组成，因此视频中的任何单帧图像都无法揭示任何信息。
After a 19-minute analysis, ChatGPT 5.5 Pro hallucinated a message that doesn’t exist. 经过 19 分钟的分析，ChatGPT 5.5 Pro 产生幻觉，编造出了一条根本不存在的信息。
However, simply hiding a message in a video isn’t a perfect solution. While an online model environment might not be able to get it from individual frames, a dedicated agent that has a local code execution environment can still analyze the motion of the dots and decode the message. Ghost Font solves this in another layered way: a decoy message is included in every video generation. 然而，仅仅将信息隐藏在视频中并非完美的解决方案。虽然在线模型环境可能无法从单帧中获取信息，但具备本地代码执行环境的专用智能体仍然可以分析点的运动并解码信息。Ghost Font 通过另一种分层方式解决了这个问题：在每次视频生成中都包含了一条“诱饵信息”。
The decoy message serves as a final trick for a determined agent. When looking for a hidden message, it might first find the decoy message and think that that is the real embedded message in the video. That’s how Ghost Font is able to hide a message even from the strongest thinking models like Fable and GPT Sol 5.6 Ultra. 诱饵信息是针对执着智能体的最后一道防线。当 AI 寻找隐藏信息时，它可能会先发现诱饵信息，并误以为那就是视频中嵌入的真实信息。这就是 Ghost Font 即使面对 Fable 和 GPT Sol 5.6 Ultra 等最强推理模型也能隐藏信息的原因。
Ultimately, the way to truly hide a message is to use encryption, or some sort of key. No AI will be able to read a message that requires a specific password to unlock that only humans know. However, this project explores whether it’s possible to create a shareable file containing a visual message that can’t be easily read by AI models. 归根结底，真正隐藏信息的办法是使用加密或某种密钥。没有任何 AI 能读取需要只有人类才知道的特定密码才能解锁的信息。然而，本项目旨在探索是否有可能创建一种包含视觉信息且 AI 模型难以轻易读取的可分享文件。
We created this experiment as a way to explore the limits of AI perception while also preserving something human. As AI takes over font generation, our hope is that humans will continue to have a unique creative voice. 我们创建这个实验是为了探索 AI 感知的极限，同时保留一些人类特有的东西。随着 AI 接管字体生成，我们希望人类能够继续保持独特的创造性声音。
What’s next? There are certain implications for Ghost Font that I think would be interesting to continue to explore. For example, it would be interesting to incorporate Ghost Font into CAPTCHA systems, as most systems are easily solved by AI today. Using motion in a video would be a way to make it much more difficult for an automated bot to decipher but still relatively easy for a human to read. 接下来是什么？我认为 Ghost Font 的某些应用方向值得继续探索。例如，将其整合到验证码（CAPTCHA）系统中会很有趣，因为如今大多数验证码系统都能被 AI 轻松破解。利用视频中的运动，可以使自动化机器人更难破译，但人类依然相对容易阅读。
Ghost Font might also be an interesting way to benchmark AI progress when it comes to visual perception. Right now, multimodal models are image-based, and even when passed a video, they usually split the video into frames and analyze individual frames. In the near future, I assume there will be a video-native model that will be able to read the text directly. Ghost Font 也可能成为衡量 AI 视觉感知进展的一种有趣方式。目前，多模态模型基于图像，即使处理视频时，它们通常也是将视频拆分为帧并逐帧分析。我预计在不久的将来，会出现能够直接读取视频文本的视频原生模型。
A final lesson is that AI is certainly getting really good. While Ghost Font is hard for AI to read, it’s also pretty hard for humans to read! The gap continues to close. It will be interesting to see what the future holds when it comes to AI perception and multimodal models. 最后的一点启示是，AI 确实变得越来越强大了。虽然 Ghost Font 对 AI 来说很难读取，但对人类来说也相当吃力！两者之间的差距正在不断缩小。未来 AI 感知和多模态模型的发展将非常值得期待。
As a next step, I plan to release the code for the video generation as an open-source project—stay tuned for that! I also hope to expand the size and handle longer text strings. I hope you enjoyed this experiment and I would love to hear your thoughts. You can find me on X at @ericlu. 下一步，我计划将视频生成的代码作为开源项目发布——敬请期待！我也希望扩展其尺寸并支持更长的文本字符串。希望你喜欢这个实验，我很乐意听到你的想法。你可以在 X 上通过 @ericlu 找到我。