Hacker News new | ask | show | jobs
by p-e-w 16 days ago
It’s absolutely incredible that the model can deduce what the human needs to do in order to more clearly see the text.
1 comments

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.