Hit refresh. The site linked below, created by Philip Wang, a software engineer at Uber, uses research by chip designer Nvidia to create an endless stream of fake portraits. The algorithm behind it is trained on a huge dataset of real images, then uses a type of neural network known as a generative adversarial network (or GAN)to fabricate new examples.


Damn Marketing Team

Casey Neistat along with many other social media and entertainment heads were duped after a string of tweets from 2009 were mysteriously liked by Burger King, for no apparent reason at the time. You got to see this video, it’s one of the best uses of the like button I’ve ever seen, 10/10.

>>> “Exploited by Burger King” video by Casey Neistat.

Crappy UI

Crappy UI is the worst, number 1 reason why I download an app, look at a video, look at a website, read a book is the design. Design is everything, design is king.

>>> “Crappy User Interfaces” video by Nakey Jakey, have a laugh.

Everybody Dance Now

A team from UC Berkeley created a short video and paper displaying the following:

We propose a method to transfer motion between human subjects in different videos. Given two videos – one of a target person whose appearance we wish to synthesize, and the other of a source subject whose motion we wish to impose onto our target person – we transfer motion between these subjects via an end to end pixel-based pipeline.

>>> Everybody Dance Now, paper