When I was a boy, I had a friend who loved inventing new sports. And as I found myself, say, rollerblading while trying to strike a football with a hockey stick into a basketball hoop, I always remembered a bit too late how terrible these ideas were. For the most part, people have figured out the good sports already: Baseball. Basketball. Football. Soccer. But where humans may have peaked, computers might just be getting started.
Speedgate is the first sport designed from the ground up by artificial intelligence. A pet project of the creative agency AKQA for Design Week Portland, the team trained a neural network on short written descriptions and rules from roughly 400 different sports. And the words that the AI spit out in response were slowly refined–with a bit of interpretation by the people–into the game known as “Speedgate.”
“Our creative team spent a lot of time looking at a large spreadsheet (which is not the glamorized AI collaboration that most people may think of),” writes Kathryn Webb, AI Practice Lead at AKQA. “It took a number of iterations to get to a place where the outputs where both comprehensible and creatively interesting.”
For instance, if the system suggested descriptions like “a sport and volleyball, rink grappling,” the team would interpret that as “Volleyball game in a small room where you are attached to the floor.” In another case, the AI suggested “a sport event major participants of on leaps ball saw also a pommel , types ) two parallel , quickest played supine heights,” which the team translated to the hilarious sport of pommel horse sawing, in which “two people sit on pommel horses on opposite sides of a giant log, they rock back and forth with a saw.”
These new sports would certainly be spectacles to behold, but they weren’t the ideal new sports AKQA imagined them. In fact, AKQA set a high bar for itself: It wanted to create a game that was easy to learn, fun, accessible to many, and would make a great workout for those who wanted to move.
After parsing over 1,000 ideas, AKQA came across a description of an intriguing sport that would eventually be known as Speedgate–with its rules filled in by even more AI text generation and at least a few creative liberties. Speedgate is a game played by teams of six, in which you can throw or kick a ball around a field to your teammates, but you cannot run. The objective is to pass/kick the ball through the center gate, which gives you the ability to score. Then you have to pass/kick the ball through a second gate (kind of like a soccer goal) to actually score.
But as a bit of a fun bonus, the gates are just poles with no net–meaning you can score the standard two points in either direction. And if you pass the ball through a gate to a teammate, and they pass the ball back through the gate to you, you score three points instead of two.
What’s legitimately neat about Speedgate is that, by design, you can’t play it as a soloist, taking the ball on a breakaway from one end of the field to another. You have to play as a team. And the AI contributed some fairly clever rules to that effect.
“My personal favorite: If a team says they scored a goal, but they didn’t, goal is given to the other team,” says Whitney Jenkins, Creative Director at AKQA. “Apparently, our AI wants to emphasis sportsmanship and honesty.”
AKQA says it didn’t stop at just the rules of the game–it used AI to help generate the game’s logo and even its chant. I can’t help but see the work of a proud parent, pointing at a child’s crayon scribbles and explaining their genius. But that is not to say the AI didn’t do its job. Speedgate actually sounds pretty fun to play, and creative liberties aside, it was based on and inspired by the work of the neural net.
As for AKQA, the agency has been playing Speedgate every Saturday morning for the past four weeks–and now they’ve uploaded the rules so that anyone can set up their own field and start their own ad hoc league. “We’ve played with intramural college athletes, kids, and kids with adults,” says Jenkins. “Everyone loves Speedgate.”