For all the scary talk about what nefarious deeds AI will be capable of one day, a geeky fight that tends to spark debate about whether the technology is a net positive or could eventually bring about the destruction of humanity, there’s at least one observable skill that AI is increasingly mastering right now — a skill that AI is starting to actually get so good at it may even shock you.
Play the video at the top of this post, and you’ll see.
What the video above depicts is a collection of humans that an AI-generated algorithm — courtesy of DataGrid, a startup based at Japan’s Kyoto University — designed. The poses, the clothes, the different hairstyles, stances, everything — the AI just came up with it all, in a stunning bit of understanding about the humans who occupy the world around it.
According to a translation of the text that accompanies the video, the researchers used what’s called a Generative Adversarial Network, or GAN, to generate the high-resolution (1024×1024) images of nonexistent humans. It goes on to suggest that this kind of thing could be useful in a variety of ways, such as by creating virtual models for industries like advertising and fashion.
The GAN involves one artificial neural network essentially trying to keep “fooling” another one, until the second one can no longer distinguish between (in this case) real human images versus computer-generated ones. Seeing this kind of thing for yourself, it’s a reminder that we’re definitely in for some strange times as deepfakes and the like begin to proliferate, with a video like this underscoring how adept AI is becoming at creating images of fake humans.
To see a different version of this same thing in action, check out the website ThisPersonDoesNotExist.com, which we’ve reported on previously. It’s the same concept as the video above, except in the case of that website, you just keep hitting refresh and you’ll be greeted by the image of an insanely real looking human that was in fact created by an AI and doesn’t exist.
This technology is impressive, but at the same time it also seems to herald something that humanity still has not fully come to grips with yet. It’s only a matter of time before AI masters the creation of fake human speech and other things that, along with the images, can be integrated into a full package and really give us a hard time with separating fact from fiction. Maybe someone will develop an AI one day that masters the art of fighting disinfo and ferreting out fake news. We can only hope.