104 comments

[ 3.5 ms ] story [ 50.6 ms ] thread
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.
First thought is in memes so automatic censoring doesn't catch it.
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.
I was thinking this too. Then it might as well look like a normal font. But copy-paste and you get a garbled mess. Screen readers though.
I screenshot the example and neither Claude nor ChatGPT had any problems reading both phrases. I don't get it.
Someone had an idea, neat idea, but solved 10 years ago already.

Edit: GPT-5.5 says: "The hidden text is “HAPPY HUMAN.”

The outlined decoy text is “SORRY ROBOT.” Blurring or viewing it from farther away reveals the hidden message."

1) Make an ambiguous text 2) Feed it to AI and see which of the 2 it picks 3) If it detects both repeat step 2 using minor adjustments or different AI model until AI responds with one of 2 message 4) Make a blog post claiming that AI chose dummy and other message was the real one
This seems like it would absolutely wreck the experience for people using screen readers.
It only works as a decoy when you give it to the LLM as an image. As html it appears like normal human friendly text, which is what screen readers use to interpret the text.
Which means that this font is entirely useless unless it is implemented in a way that breaks screen readers.
How? AFAIK screen readers don’t do OCR.
Forget about screen readers: I'm looking at it on a monitor and I just see the robot version!
Is it useful? No. Does it stop AI from reading it? Also no. But is it cool? Yes, it is very cool.
The demonstration shows that it does stop AI
I made an image and it fooled GPT. I asked it to look for a hidden message and it found the blurred word.

Still cool+fun though.

The demonstration might, and it may work for certain models with certain prompts, but I just asked gemini if it could see both and it both did see both and gave me a tutorial on how I could see both as if it were a simple magic eye poster.
I mean, I've worked for companies where their curated sales demonstrations showed the speed of light is easily breakable... Do your own testing with some thinking applied.

https://m.xkcd.com/1217/

I mean, I can defeat AI by putting white text on a white background and turning to a picture. Also means it's worthless for actual humans to read too. Try to actually use it on a site and chances are you'll get an ADA complaint.

It would be trivial to train future models to detect and read it though (and some already can, based on other comments in this thread). It only works as much as it does because it's new and reading it hasn't been a goal.
sometimes in life there is no reason to kick a rock around besides having fun ;)
> Is it useful? No

Seems like it might have some use thwarting Ring/Flock/etc cameras within a specific proximity.

It's giving major "They Live" vibes.

Is it useful? No. Does it stop AI from reading it? Also no. But is it cool? Also no. Does it give me nausea? Yes yes yes.
I just gave the day dream / pay bills image to ChatGPT and Gemini pro and they both could only tell me the pay bills text (shown with the thin lines)
Sure, but this is only as useful as useless it is.

Meaning the moment this gets wide adoption AI will have 0 issues dealing with it. LLMs are very good at translating one language to another.

Gemini flash responds to "can you read both messages here?" with:

Yes, this is a clever optical illusion! Depending on which layers your eyes focus on, you can read two entirely different messages in this image:

    Message 1 (The sharp outline layer):

        PAY BILLS

        How to see it: Focus on the sharp, concentric black outline contours of the letters.

    Message 2 (The soft, blurry shadow layer):

        DAY DREAMS

        How to see it: Let your eyes relax/defocus slightly, or step back from the screen to focus on the soft, heavy grey drop shadows. The blurred shadows transform the "P" into a D, the "B" into a D, the "I" into an R, the "L"s into an M, and the "S" is shared!
That was 7 hours ago. Now, Google Images not only reads the text but links to that web site.
... wherein it's made known the author can't lose. good for the author
I think this illustrates that you can just do stuff without claiming it is useful. Like couldn't you just make this font and call it something like double-entendre or something?
It's similar to any anti face detection art. Probably useless but cool.
Ehh. Probably not many people will be using this particular thing to thwart ai BUT I think it may be a stop on a path towards something very useful someday.
If you present the text in an image / GIF format is could be useful.
That's an accessibility nightmare for people with vision issues.
This is just level of detail. Gemma E4B reads the sharper text until you resize down to 150x150, then it reads the other text.
As do I. The hero image clearly says "SORRY ROBOT" to me, which is the message supposedly intended for AI... kind of a fail.

It's only when I squint hard that I can see "HAPPY HUMAN".

Downsizing is effectively low pass filtering, so that's expected. Any scheme that transmits different messages in different frequency bands is going to be susceptible to a similar attack.
Not even AI. I think I can write PIL script that will fix the font to be read by any ocr software.
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.
Have you no whimsy?
As a project they are kind of fun.

The problem is we see stuff like this try to get turned into actual products by people with questionable motivations and ethics.

Looking at you PhotoGuard/Nightshade.

How does it know HAPPY HUMAN translates to SORRY ROBOT? Is there a cycle in there or something?
I don't think the font can actually do that - I think it is a hand-crafted example of the idea. The later examples all have random letters for the decoy text.
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 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.
(comment deleted)
Cool. Now do an accessible version.

(/s)

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!

(comment deleted)
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!
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.”"

wow that's kind of crazy impressive that it can do that honestly, VLMs have gone so far, can't imagine the crazy amount of annotations they had to create to get to that level
(comment deleted)
Oh Nice, I wasn't able to really read the hidden text before reading your squinting part, that's interesting!
It’s absolutely incredible that the model can deduce what the human needs to do in order to more clearly see the text.
Which sufficient tooling calls even OCR can read this, but I think this can be improved
I'm surprised the AI reads the outline version, since I thought most scaled the image down, which is basically a low-pass filter on those single-pixel lines.
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.

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

All ”AI resistance” I’ve seen is not against the tech, but against human bad actors behind AI: unethical procurement of training data, reckless application, low effort high volyme spam, replacing humans, centralization of power, dependency on megacorps etc. I think a lot of people have become less tech-positive after the ad-tech era that brought us social media, unprecedented levels of surveillance, freemium rug pulls etc. It’s much easier to understand the resistance if you place it in that context, rather than imagining millions of sleeper agent luddites suddenly coming out of the woodworks.

BLIND PEOPLE HATE THIS ONE TRICK
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.

Also works if you scale/zoom the image. The crisp lines disappear entirely at a certain point.
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.”