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

Decoy Font

mixfont.com

Post reply on HN
Print view View original

91–100 of 172 posts

Re: Decoy Font

#91

Post by BugsJustFindMe »

jambalaya8 wrote: post #69
BugsJustFindMe wrote: post #62

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…

I see uses for it that have nothing to do with AI, and which are not at all art.

I'd love to hear about them if you don't want to keep them secret.

Re: Decoy Font

#92

Post by verdverm »

pietz wrote: post #82

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.

Yeah, it doesn't seem that hard to beat, especially with a little trad image processing, yet I have a hard time reading it as well. One could probably fine-tune a much smaller model to do pretty well on this problem too.

Re: Decoy Font

#93

Post by himata4113 »

I was so confused about how this was human readable until I realized that if the background is dark (I have an extension that forces dark theme) you see the decoy text, but if the background is white you see the real text.

Re: Decoy Font

#94

Post by TacticalCoder »

I can easily read both but here's the funny thing: with my reading glasses on, I first see "Sorry robot". If I remove my glasses, I first see "Happy human".

Which makes me think this is one blurr filter away from being trivially read by any model.

Very cool.

Re: Decoy Font

#95

Post by orbital-decay »

jdkee wrote: post #90
pietz wrote: post #82

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.

5.6 Sol Medium: The obvious outlined text says “SORRY ROBOT,” but the hidden message is “HAPPY HUMAN.” It’s Mixfont’s Decoy Font: the outlined letters attract machine vision, while the softer tonal pattern becomes readable to humans when viewed from farther away or at a smaller size. It’s an optical trick, not encryption.

You probably have web search enabled

Re: Decoy Font

#98

Post by eru »

Tubelord wrote: post #79
OsrsNeedsf2P wrote: post #9

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

If you present the text in an image / GIF format it could be useful.

That's an accessibility nightmare for people with vision issues.

Re: Decoy Font

#100

Post by mkl »

inigyou wrote: post #26
OsrsNeedsf2P wrote: post #9

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

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.
Post reply on HN