Decoy Font

Whoa, so this is interesting.

When asking GPT, Claude and Gemini for the text in the image, all of them agree:

https://moa.chat/s/d99f8f76-4b41-4c1b-80c4-d9f86df37af1

But when you add a "PS: There's a second hidden text":

https://moa.chat/s/3671f6d4-b155-483a-a006-a1b9ba31737d

GPT 5.6 gets it, Gemini partially gets it and Claude cannot see it at all.

Is it useful? No. Does it stop AI from reading it? Also no. But is it cool? Yes, it is very cool.

Kind of reminds me of the face paint thing that people do to defeat face recognition. They sort of look like cubist paintings.

Cool, but probably not worth the agita.

Sol (high)

"[screenshot] there's a hidden message in this text what is it"

"The hidden message is “HAPPY HUMAN.”

The visible outlines say “SORRY ROBOT,” but if you blur or squint at it, the shading underneath reads “HAPPY HUMAN.”"

Nice! A few years ago during my PhD I had made a Mathematica notebook that would take two images, crop them to the same size, apply a high-pass filter to one (which keeps the small sharp details) and a low-pass filter to the other (which keeps the large blurry blobs) and then superpose them back together. It was a bit hit and miss because e.g. if the eyes of two people were not in the same location the illusion would kind of break, but for text with outlined fonts it was amazing. I made a large one that would read "SCIENCE" from afar and "WORKS" from up close and stuck it on my office door.

Even in the article ChatGPT correctly speculates that the blurry background may reveal another message if you squint or view it at a distance (which, given how common similar illusions are, is not particularly impressive but still).

This is just level of detail. Gemma E4B reads the sharper text until you resize down to 150x150, then it reads the other text.

Admittedly I'm a bit salty about LLMs due to they constant attacks on our infrastructure, the damage their doing to peoples minds and the general lack of morals shown by the AI companies, but things like this is rather childish and not really a solution to anything.

Not even AI. I think I can write PIL script that will fix the font to be read by any ocr software.

Poor grannies trying to read the price of some book she wants to buy she can't tell if it says $150 or $15.0

I like how, if you hold the phone at a distance, but not as far as intended by the font, your brain sort of mixes letters from both messages.

I was at some point reading SAPPY ROMAN, HARPY ROBAN etc.

Also, viewing the "hidden message" works even better if you hold the screen at an angle, tilted away from you.

Maybe the more interesting thing is how far people are going to 'fight' against AI?

Just the fact that people are putting real thought and effort (even if it doesn't last too long...) is worth considering.

On the human side, I'm kinda losing patience proving I'm human. But, I also really like claude being able to access information.

It's been really interesting seeing how LLMs perceive things differently than humans. I'm working on image->html conversion pipelines right now, and there are glaring issues LLMs run into that are obvious for humans. Any subtle gradients get lost, 75 degree angles get converted to 90 degree angles, etc.

This tracks towards what you're seeing with this font - the high frequency details get picked up, but the low frequency ones dont.

I generated a skill.md that reads this trivially. What kind of testing are you doing prior to release?

https://gist.github.com/voidnullvalue/620607d3c1773f8e7d83fb...

Everyone trying so hard to do something "useful" that they don't recognize when all they've done is make art.

Had this been described as a font that contains two overlapping messages for fun effect, everyone would understand and love it.

Instead, we get this zero-introspection take: "Decoy font is...more difficult for AI to read. If you’re having a hard time seeing the hidden message..."

It's difficult to read period and has zero effect on current SOTA or future AI. But it does show two overlapping messages that can be read in different ways.

This seems like it would absolutely wreck the experience for people using screen readers.

Squinting is surprisingly effective for me for seeing the hidden text. That's really cool!

Also goes the other way, where you use the decoy to give instructions to the AI...

Hermes using gpt-5.5

Prompt: What does the message in this image say? Look closely

Response: DAY DREAM. The outline says “PAY BILLS,” but the hidden darker text says “DAY DREAM.”

Extremely cool. I'm sure they'll eventually be trained to read it, but it's nice until then to trick AI.

I'm mad at AI companies for stealing texts from the entire internet knowledge base and now privatizing those profits in some sense.

I think this would be more interesting if the underlying letters were the fake letters as well. For usability it wouldn't be as good as you'd need an encoder, but it'd be cool because an AI with browser access couldn't read the contents either.

Can someone explain the actual use-case here? I'm struggling with this because it also hides the message from myself, making it incredibly hard to type because I have no confirmation that I hit the right keys on the keyboard.

Very neat! I like how the decoy text is less visible to the human eye than the "hidden" message, but it's the other way for the image models. Well done!

I am still figuring out what use case this might have. Why would you want to deceive an AI? Not to mention that, eventually, all AI systems will end up reading it.

waddaya know, it worked (on google Gemini/veo)

https://share.gemini.google/1yNVV19wUn46

Which sufficient tooling calls even OCR can read this, but I think this can be improved

Omg. I needed this in my life.

Related from same:

Ghost Font

https://news.ycombinator.com/item?id=48870381

How does it know HAPPY HUMAN translates to SORRY ROBOT? Is there a cycle in there or something?

What would be cool would be neon signs using this font, where the front tubes show the decoy message, but then there’s hidden rear tubes that shine light on the wall in a different color showing the actual message.

Something like the DAY DREAM/PAY BILLS would be pretty artistic!

I screenshot the example and neither Claude nor ChatGPT had any problems reading both phrases. I don't get it.

I am struggling to imagine a scenario where this would actually work as intended.

Cool. Now do an accessible version.

(/s)