Hacker News Reader

Comment by ethana | Hacker News Reader

Someone still has to come up with new art styles for the machine to mix.

Before that becomes the main problem, that other problem must be solved where you give it your picture and the Mona Lisa whose style is to be copied and the way it copies the style is it paints her eyebrow atop your mouth. 'Cause it's not like this thing can really distinguish between "style" and "content". What it does is it pastes patches from the "style" image onto the "content" image. Sometimes the result is interesting, much of the time it's between boring and terrifying. It's cool and all, but it's not much more intelligent than your favorite Photoshop filter.

"Going the way of the dodo..."

If the rating is more important than the creation, perhaps they should create a neural network with an image as input, and a single signal as output, that indicates on a scale of 0 to 1 how interesting that image is, from an artistic point of view.

Alternatively, equip a human with an EEG headset, let them look at images, and take the rating from the output of the scanner.

Interesting is not a value on a one dimensional scale, because the art isn't one dimensional.

> Cause it's not like this thing can really distinguish between "style" and "content

So it's going to be perfect for modern art? :D

No, it can't distinguish because it doesn't know either.

Build a database, randomly assemble.

Recurse.

Use whatever language generator deemed appropriate* to assign proper titles for the newly-evolved art movement.

*this may be delegated to a meat-computer, in pity.

Reply on news.ycombinator.com