Sheeeeeeit… Netflix has gotten Isiah Whitlock. Jr. together with Nicolas Cage, Sarah Silverman, and numerous other interesting, funny folks to dive into the etymology & cultural histories of forbidden language. I haven’t yet seen it, but it looks fun:

Photoshop artistry FTW this Christmas!

Given our family’s love of irony & wordplay, my wife Margot had the inspired idea of commissioning a portrait of our dog (a.k.a. “doge,” per the meme) as a Venetian doge. George at FavoritePaws did an amazing job, our son Finn’s mind was fully blown, and now the noble Seamus hangs in honor as the real pup slumbers below. 😌

Well gang, Imma say about this year what Dave Chapelle said at the Playa Haters Ball:

What can I say about that suit that hasn’t already been said about Afghanistan? It looks bombed out and depleted.

I’ll leave it to John Oliver to take it from here:

Here’s to a brighter, stronger, healthier year together, friends. God bless & stay strong.

Wherever you are & whatever you may celebrate, I hope you and yours are well this Christmas. I’ve been amusing the fam by dialing up some old Chieftains Christmas tracks (which transport me back to my relatives’ cozy homes in Chicago growing up), including this absolute banger. 😌 Enjoy.

7:30pm Pacific time, streaming free via YouTube:

In this talk, we’ll discuss the current state of AI-generated imagery, including Deepfakes and GANs: how they work, their capabilities, and what the future may hold. We’ll try to separate the hype from reality, and examine the social consequences of these technologies with a special focus on the effect that the idea of Deepfakes has had on the public. We’ll consider the visual misinformation landscape more broadly, including so-called “shallowfakes” and “cheapfakes” like Photoshop. Finally, we’ll review the challenges and promise of the global research community that has emerged around detecting visual misinformation.

I don’t know how one encapsulates the paradoxical “glacial/speed-run” feeling of these last 12 months, but the Goog gamely tries in these heartfelt three minutes. For more about the questions that preoccupied the world, check out The Year in Search site.

I mean, AR is cool and all, but have we considered a trash bin with some duct tape on it as a helmet? 😂

[Via]

…or about the year, at any rate. This is <chef’s kiss>:

Excellent follow-up in a reply:

Researchers at Google, Facebook, and the University of Washington have devised “a fully automatic method for converting a still image into a realistic animated looping video.”

We target scenes with continuous fluid motion, such as flowing water and billowing smoke. Our method relies on the observation that this type of natural motion can be convincingly reproduced from a static Eulerian motion description… We propose a novel video looping technique that flows features both forward and backward in time and then blends the results.

The results are rather amazing.

Lobe, the startup Microsoft acquired from UI star Mike Matas & co., offers a way to feed training data into an ML system via one’s browser. I have no idea how precise and/or general the applications could be, but regardless it makes for a fun & interesting demo.