Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Ghost Font: A font that humans can read but AI cannot

mixfont.com

Post reply on HN
Print view View original

181–188 of 188 posts

Re: Ghost Font: A font that humans can read but AI cannot

#181

Post by hedora »

picofarad wrote: post #179
solidasparagus wrote: post #20

When I gave Fable a screenshot it found the GHOST portion of GHOST FONT. Based on pixel density via some python code apparently - https://imgur.com/a/m3c801F

Hackernews is very good at finding the decoy message. This is as funny as thedailywtf posters who post "code snippets" to fix some other code snippet, and every single code snippet is wrong.

In fairness, on mobile, the decoy font is the only thing a human will be able to see unless they zoom in the right amount.

Is the LLM really wrong if most humans and it agree that the decoy message is the real message?

It is still at fault if it gets the “real” message when a human that can actually read it is instructing the LLM?

Re: Ghost Font: A font that humans can read but AI cannot

#182

Post by hedora »

tokai wrote: post #83

What is making it hard to read for so many people? My eyes aren't young or healthy, but it is as clear as day for me. Wonder with screens play are role.

Zoom level, at least on an iPhone mini.

Default: Pure static.

Zoom in: Written in ghost font.

Zoom in more: Now you can read it.

Re: Ghost Font: A font that humans can read but AI cannot

#184

Post by nextaccountic »

stabbles wrote: post #40
nextaccountic wrote: post #23

Earlier quoted context omitted.

> a screenshot The text is a video. Every frame contain random dots, so an individual frame by itself doesn't contain the intended message This "font" exploits the fact that current-gen frontier models will process video one frame at time, but each frame is noise, so by looking at frames in isolation doesn't reveal anything Then, they add a hidden message to each frame just so that the agent report something and stop…

If you take a frame you see it's neither random nor dots: https://i.imgur.com/CgtyGjl.png From a single frame you can definitely identify boundaries because the dots are sliding and get truncated.

This idea could be done with purely random frames. But they also need each frame to show a decoy to the agent (so that the agent stop looking - if they are persistent enough they could figure out the trick)

So each frame can't be 100% random and it must show some outline - but my guess is that it's the outline of the decoy, and unrelated to the outline of the actual message

And per what was reported, it's already pretty hard for the agent to figure out the decoy. After they finally crack it, they consider the problem solved

I think it's genius. The only problem is that it's trivially defeated by some tool written specifically to read it. So it defeats current-gen agents but if it becomes popular (eg. used by captcha services), future LLMs will just write a small Python script to read it

Re: Ghost Font: A font that humans can read but AI cannot

#186

Post by solidasparagus »

picofarad wrote: post #179
solidasparagus wrote: post #20

When I gave Fable a screenshot it found the GHOST portion of GHOST FONT. Based on pixel density via some python code apparently - https://imgur.com/a/m3c801F

Hackernews is very good at finding the decoy message. This is as funny as thedailywtf posters who post "code snippets" to fix some other code snippet, and every single code snippet is wrong.

The default real text was "GHOST FONT" and the "ghost" portion of that is what fable found. It wasn't a decoy message.
Post reply on HN