[jonplackett]

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)

[goodmythical]

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!

[hnlmorg]

Is that reading the image? Or just identifying the source of the image and returning the authors write up on their website?

You’d have to use new images with different messages using that font to be sure Gemini isn’t “cheating” here

[andypants]

You've told it that there are 2 messages.

[Lio]

Now it would be interesting to give it some text on blurry nonsense to see what affect that has.

Probably that it just reports it can't find the second message or that one is not present but I wonder if it would flag it up and if that could be spammed?

(Not that I'm suggesting anyone do that you understand).

[xnickb]

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.

[kps]

That was 7 hours ago. Now, Google Images not only reads the text but links to that web site.

[fitsumbelay]

... wherein it's made known the author can't lose. good for the author