Hacker News Reader

It’s absolutely incredible that the model can deduce what the human needs to do in order to more clearly see the text.

Counterpoint: this is the same instructions provided for a wide class of printed optical illusions, likely well represented in the training set.

But the model recognized that they apply here. That’s absolutely non-trivial. It could have easily mistaken the line pattern for an autostereogram and told the user to cross their eyes instead.

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

Oh Nice, I wasn't able to really read the hidden text before reading your squinting part, that's interesting!

It took me defocusing my eyes to read the hidden text with normal ease. When I tried it, squinting only made it focus in on the thin lines instead of the background.

I find it works a lot better at smaller sizes.