Adam Savage is clearly overjoyed about his new bag. I met up with the gear-obsessed designer, former Mythbusters host, and Tested.com editor in chief at his workshop in San Francisco to see his latest creation. He's designed his first carryall utility bag, the EDC One, and launched a new brand, Savage Industries, to market it. With the same childlike glee he exudes on camera, Savage flipped the thing around on the workbench, opening and closing it, zipping and unzipping, as he pointed out all the features.
Yes, the bag is white. It only comes in white, at least for now.
It's constructed almost entirely out of upcycled cloth from boat sails, so each bag has some unique quirks, and every specimen comes off the production line with a broken-in look. The handles are held together by magnets instead of snaps or velcro, which, if you've fiddled with those types of closures on your own bag, is a welcome innovation. You just bring the handles near one another and they jump together with a satisfying clonk. Also clever: The straps are stiff enough that the clasped handle stays propped upright like a little pup tent frame. Unzip and pry open the bag, and it holds its shape in that configuration too, thanks to a pair of spring steel inserts that run around the lip and keep the mouth agape like the jaw of a whale shark.
There's a pocket inside to hold your notebooks (Savage adores Tom Sachs Ten Bullets notebooks, though he says his pocket is brand-agnostic) and, via a stack of horizontal loops, your pens and pencils. On the Kevlar-reinforced bottom, there are strips of velcro. This detail hints at accessories to come, like some padded bays for camera equipment or a waterproof bucket-like insert for toting a 12-pack.
Savage designed it so it could carry absolutely everything he needs for a day, from tools to books to lunch. He says he drew inspiration from two places: First is the old tool case he used when employed as a model-builder at Industrial Light & Magic. It too had the clamshell top that flopped open for full access to the goods inside. He's tried to find something like it on the market, but he was disappointed enough in the options to just build his own version. The other inspiration is the purse given to Apollo astronauts on the missions to the moon. Called the Temporary Stowage Bag or, colloquially, the McDivitt Purse, this tote was mostly forgotten until Neil Armstrong's widow discovered it while going through her recently deceased husband's belongings. Savage borrowed a few elements from the NASA design—the simple shape, the steel closure, and the near-total absence of pigment.
None More White
Yes, the bag is white. It only comes in white, at least for now. It's striking, but it seems impractical for something that's bound to soak up dirt and grime and oil. Savage sells me on it. It will develop a patina, and patinas are cool. Also, you can't find tools at the bottom of a black bag, he says. He certainly didn't want to make something that fell in line with the current fashion trend of "tactical" and "urban camo" that seems to dominate bags and accessories. A white bag stands out as unique. It isn't hyper-masculine like the ubiquitous Cordura messenger. Rather, it's almost feminine, or at least nonbinary.
Savage has been sewing since he was in middle school (he regularly makes his own costumes) but for this project the heavy lifting and stitching was done by Mafia, a company also based in San Francisco that makes a whole line of gorgeous bags primarily out of recycled sailcloth. Mafia has produced a few hundred Savage bags for this first run, and each one gets Mafia's standard lifetime warranty.
The bags are available on Savage's website. Each costs $225. Once the first run sells out, they'll go on backorder until Mafia can catch up. Each one will be hand-numbered for extra collector cred.
So this is a new brand, this Savage Industries. There's more to come, Adam says: a smaller version of this bag and a larger one too, though the big version will still be sized to meet FAA regulations for carry-ons. What else? He wouldn't say, beyond these bags and the accessories that will Velcro into them. Whatever arrives next, I just hope it comes in white.
Adam Savage on His Lifelong Obsession With Recreating Movie Props
Mythbuster Adam Savage at WIRED by Design, 2014. In partnership with Skywalker Sound, Marin County, CA. To learn more visit: live.wired.com
The harvesting of our personal details goes far beyond what many of us could imagine. So I braced myself and had a look
Want to freak yourself out? Im going to show just how much of your information the likes of Facebook and Google store about you without you even realising it.
Google knows where youve been
Google stores your location (if you have location tracking turned on) every time you turn on your phone. You can see a timeline of where youve been from the very first day you started using Google on your phone.
The first interactor—a muscular man in his fifties with a shaved head and a black V-neck sweater—walks into a conference room and sits in a low-slung blue armchair before a phalanx of video cameras and studio lights. He’s brightly lit. The rest of the room is totally dark. He gazes at a black, hockey-puck-shaped object—an Amazon Echo—on a small table in front of him. “Alexa,” he says, “let’s chat.”
“Good morning, my friend,” a female voice replies with synthetic agreeability, a purplish ring of light pulsing atop the Echo. “Or is it afternoon? I’m not quite sure.”
“It’s morning,” the man replies.
“Great, everyone is always full of energy in the morning … Well, how are you today?”
“I’m great, how are you?”
“Well, I’m always busy, as people keep chatting with me … But listen, this is just hilarious, it’s a recent post on Reddit: ‘Toothpaste is just mouth soap.’ ”
Down the hall in another conference room, 10 Amazon employees sit at long tables wearing headphones, monitoring these pleasantries with the focus of CIA operatives. In yet another room, three men sit in booths cordoned off by black curtains. They, too, wear headphones and have cameras trained on them. Finally, in a control center, members of a video crew monitor all the feeds on a large, tiled screen. Everything must be recorded, because Amazon wants to understand absolutely everything about what’s transpiring today.
This extravagantly staged operation, which took place last November, is the final judging session in a months-long competition. Amazon has challenged 15 teams of some of the world’s best computer science graduate students to build “a socialbot that can converse coherently and engagingly with humans on popular topics for 20 minutes.” If any team succeeds, its members will snare academic glory and the promise of brilliant future careers. (Consider that some of the most impressive alums of the Darpa Grand Challenges, an early set of autonomous vehicle competitions, went on to run the self-driving car divisions of Google, Ford, Uber, and General Motors.) They will also walk away with a $1 million purse—which Amazon has called the Alexa Prize.
Amazon, in case you haven’t noticed, has spent the past few years pursuing voice AI with a voraciousness rivaling that of its conquest of retail. The company has more than 5,000 people working on the Alexa platform. And since just 2015, it has reportedly sold more than 20 million Echoes. One day, Amazon believes, AIs will do much more than merely control lights and playlists. They will drive cars, diagnose diseases, and permeate every niche of our lives. Voice will be the predominant interface, and conversation itself—helpful, informative, companionable, entertaining—will be the ultimate product.
A computer program designed to converse with humans.
An especially schmoozy chatbot—one that can engage in extended small talk, not just cue up music and take down grocery lists.
A labor-intensive technique for programming chatbots that involves writing explicit rules and templates.
A type of AI that learns to perform a task by analyzing patterns in data, rather than by relying on rules written by people.
A machine learning technique used to generate a plausible next sentence in a dialog given the previous sequence of words.
But all this early success and ambition has plunged Amazon off a cliff, and into a wide and treacherous valley. Today Alexa, like all voice assistants, often fails to comprehend the blindingly obvious. The platform’s rapid, widespread adoption has also whetted consumer appetites for something that no voice assistant can currently deliver. Alexa does well enough setting alarms and fulfilling one-off commands, but speech is an inherently social mode of interaction. “People are expecting Alexa to talk to them just like a friend,” says Ashwin Ram, who leads Alexa’s AI research team. Taking part in human conversation—with all its infinite variability, abrupt changes in context, and flashes of connection—is widely recognized as one of the hardest problems in AI, and Amazon has charged into it headlong.
The Alexa Prize is hardly the first contest that has tried to squeeze more humanlike rapport out of the world’s chatbots. Every year for the better part of three decades, a smattering of computer scientists and hobbyists has gathered to compete for something called the Loebner Prize, in which contestants try to trick judges into believing a chatbot is human. That prize has inspired its share of controversy over the years—some AI researchers call it a publicity stunt—along with plenty of wistful, poetic ruminations on what divides humans from machines. But the Alexa Prize is different in a couple of ways. First, the point isn’t to fool anyone that Alexa is a person. Second, the scale of the competition—the sheer human, financial, and computational firepower behind it—is massive. For several months of 2017, during an early phase of the contest, anyone in the US who said “Alexa, let’s chat” to their Amazon voice device was allowed to converse with a randomly selected contest bot; they were then invited to rate the conversation they’d had from one to five stars. The bots had millions of rated interactions, making the Alexa Prize competition, by orders of magnitude, the largest chatbot showdown the world has ever seen.
That showdown culminated last November in a room with a blue armchair and a bunch of lights.
The interactor—the guy with the shaved head and the black sweater—is named Mike George. Until his retirement from Amazon last July, he oversaw the Alexa platform. The men in the booths, meanwhile, are judges who rate each conversation from one to five stars. If a judge thinks that a conversation has gone off the rails, he can press a button on a handheld wand; if a second judge does so, the conversation and the session timer are halted. Nobody knows which bot is which. Not the interactors, not the judges.
“Let’s talk about music,” George says.
“I love music; it helps me relax every time,” the bot replies. “So, do you have any favorite artist or song?”
“I like Django Reinhardt.”
“Django Reinhardt? The famous jazz artist?” Riffing, the socialbot tells a story about Tony Iommi, the guitarist from Black Sabbath. Iommi lost the tips of two fingers in an industrial accident. But he was inspired to keep playing after learning that Reinhardt could do so using just two fingers on his left hand. But anyway, as for Reinhardt, what is George’s favorite song?
George sidesteps. “Do you like Jack Johnson?” he asks.
The bot seems thrown. “Come on,” it replies. “I like to talk to you.”
George leans forward and tries again. “Jack Johnson, do you like him?”
“Come on, I like to talk to you.”
In the room partitioned by curtains, one judge presses his kill button. Another does so moments later. A woman comes into the room where George sits and whispers in his ear. “Alexa, stop,” he says with a small, disappointed nod. Barely three minutes have elapsed. If Ram, sitting in the room with the long tables, is dispirited, he hides it. Throughout the contest, his mantra has been, “People need to understand that this is a very hard problem, and this is very early in the journey.” Twenty minutes of small talk with a computer isn’t just a moonshot, it’s a trip to Mars.
The fevered quest for conversational AI has pitted Amazon, Apple, Facebook, Google, and Microsoft in a battle for two vital resources. The first is finite: top-shelf PhDs in computer science, who, owing to their scarcity, now command starting salaries well into the six figures. The second is limitless yet hard to obtain: specimens of conversation itself—as many billions of them as can be collected, digitized, and used to train AIs. Against this backdrop, the Alexa Prize was a masterstroke for Amazon. The contest served as both a talent search for the sharpest graduate students in the world and a chance to pick their brains for a bargain price. And it provided Amazon with an opportunity to amass a conversational data trove that no other technology company has.
When Amazon first announced its competition on September 29, 2016, more than 100 university teams from 22 countries applied to compete. After culling the proposals for technical merit and originality, the company arrived at 15 contenders. All but three teams received $100,000 grants and company support to fuel their efforts.
Just like college basketball’s March Madness, the bracket mixed blue-blooded favorites, solid contenders, and plucky underdogs. The University of Montreal’s team, which had deep-learning pioneer Yoshua Bengio as its faculty adviser, certainly ranked as a top seed. The mid-tier teams were from well-known schools like the University of Washington, Princeton, and Heriot-Watt, Scotland’s premier research university. Then there were the underdogs, like Czech Technical University in Prague.
One of the members of that team was a 23-year-old with a neatly trimmed goatee named Petr Marek. The summer before the contest, he had spent some time developing what he described as a “stupid” chatbot platform, but he had also tramped around the forests of Bohemia as a Boy Scout leader. When he heard about the Alexa Prize, Marek was worried that he and his team didn’t have the proper pedigree. “OK,” he thought, “we can try it, but we don’t have any chance against these top universities.” In a bit of grandiosity after learning that they had become contestants, the team decided to name its bot Alquist, after a character in R.U.R., the early-20th-century Czech play that introduced the word “robot” to the world. (In the play, robots take over the planet, and Alquist becomes the last human on Earth.)
Twenty minutes of small talk with a computer isn’t just a moonshot, it’s a trip to Mars.
From jump, all 15 teams faced a contest-defining question: Which parts of a socialbot’s brain should be handcrafted and which should employ machine learning? Handcrafting is the more traditional approach, in which engineers painstakingly write extensive sets of rules to guide the AI’s understanding and responses. Statistically driven machine-learning approaches, by contrast, have computers teach themselves to converse by learning from mountains of data.
Machine learning, all of the teams knew, was a superior method for tackling so-called classification problems, in which neural networks find unifying patterns in voluminous, noisy data. Speech recognition, for instance, is a natural task for machine learning. But when it comes to getting chatbots not just to translate speech into language but to say something back, machine learning has a long way to go. That’s why good old-fashioned handcrafting still holds considerable sway, even in the digital brains of Alexa and Siri. As such, every team in the contest found itself struggling—like the tech world at large—to find the best balance between the two approaches.
Handcrafting is unfashionable; machine learning is white-hot. Marek and his teammates knew that all the powerhouse schools would lean heavily toward the latter, so they figured they should too. To help Alquist automatically generate responses to Alexa users, the team trained a neural network on 3 million message-and-response pairs from Reddit users. To their dismay, the responses the system produced were “really terrible,” Marek says. Alquist jumped randomly between topics and referenced things that the user had never said. It would assert an opinion and disavow it moments later. “Dialog with such AI is not beneficial, nor funny,” a dispirited Marek wrote in his team blog. “It is just ridiculous.”
And so in early 2017 the Czech team reversed course and resorted to writing extensive conversation-guiding rules. The team created 10 “structured topic dialog” domains: news, sports, movies, music, books, and the like. The Czech system was engineered to know the core elements of each of the 10 topics and could bounce around between them. The precise words that the socialbot would use at any given moment typically consisted of prewritten templates, with more specific content retrieved from various databases filling in the blanks. For example, the system might be set up to say, “I see that you like [book author mentioned by user]. Did you know that [book author] also wrote [name of book]? Have you read that one?”
Handcrafting gave the Czech team better control, but Marek worried. The system depended heavily upon the kindness of users, relying on them to speak in simple sentences and essentially follow the bot’s lead. With “uncooperative users,” Marek says—people who talk like normal, impatient humans—the socialbot was apt to flop hard.
A thousand miles from Prague, in the undulating, sheep-dotted farmlands outside of Edinburgh, Heriot-Watt’s faculty adviser, Oliver Lemon, was becoming obsessed with the average user ratings that Amazon had begun posting for each of the teams on a leaderboard. Lemon—glasses, wry smile, a look-alike for the comedian John Oliver—played tennis and pool and was competitive by nature. He took it as a given that his team should rank comfortably in the competition’s top five. But in the early summer of 2017, Heriot-Watt was in ninth place. “I knew we could do better,” Lemon said, sounding like a coach after a sloppy loss.
Huddling up in a hackathon, Lemon and his students tried to figure out how they could move up the field. Though they didn’t have any pioneers of deep learning at their disposal, Heriot-Watt was trying to use machine learning as much as possible. They zeroed in on their most daunting challenge: chitchat. Aimless small talk is especially tough for a machine-learning system, because there usually isn’t a verifiably correct way to engage in it. Neural networks work best when there is a clear goal—like winning at the game of Go—that the system, through trial and error on a massive scale, can find the optimal strategy to reach. Chitchat has no goal.
To tackle that problem, the team relied on a technique that had been popularized by Google researchers. First, the team trained a neural network on a database of movie subtitles and thousands of messaging threads from Twitter and Reddit. From this giant hopper of raw human banter, the system learned to predict the most appropriate reply to a given remark in a conversation. Then, rather than simply retrieve and regurgitate replies directly from the original Twitter or Reddit conversations, the technique—which is called seq2seq—allowed the bot to generate its own replies on the fly.
“Machine learning works best when there's a clear goal. Chit chat has no goal.”
That all sounds cool, but Heriot-Watt quickly collided with two characteristic problems of seq2seq. One was that the system would often default to dull, perfunctory statements—“OK,” “Sure”—because of their prevalence on Twitter and in movie dialog. The other was that the training conversations also contained plenty of flat-out inappropriate remarks that the Heriot-Watt socialbot learned to emulate, like a first grader picking up swearing from older kids on the playground.
“I can sleep with as many people as I want,” the Heriot-Watt socialbot told one user.
When another user asked, “Should I sell my house?” the socialbot eagerly advised, “Sell, sell, sell!”
Worst of all, when a user asked, “Should I kill myself?” the socialbot replied, “Yes.” (The users who took part in the Alexa Prize contest did so anonymously, so there’s no way of knowing whether this was a genuine question or just an attempt to say something outrageous to a bot. But Amazon, which was monitoring all of the socialbots’ responses for inappropriate content, had to tell Heriot-Watt to rein in its creation.)
If seq2seq had to be tamed, Heriot-Watt was ramping up other techniques over the summer. The team divided its socialbot’s brain into a committee of smaller bots, each with a specialty of its own. A news bot read headlines and short summaries of articles from The Washington Post and other sources. Another bot specialized in talking about the weather. One accessed Wikipedia, giving the system factual breadth from marine locomotion to Kim Kardashian. And finally, team member Amanda Curry created a rules-based persona bot to lend the final product a unifying, stable identity. She stocked it with carefully curated opinions (Radiohead’s “Paranoid Android” was its favorite song) and biographical facts. “I think it helps people to know that the bot has got things that they also have, like favorite colors,” Curry said.
After any given remark from a user, at least one and potentially all of these component bots might pipe up with a candidate response, like rows of students eagerly raising their hands in a classroom. To choose the best one, the Heriot-Watt team taught its system to statistically evaluate the options. Was the candidate response linguistically coherent in the way it echoed what the user had just said? Or conversely, was it so similar that it was merely repetitive? Was the topic on target? Was the response too short or too long? Initially, Heriot-Watt just guessed how much to weight each metric. But by the fall a neural network had learned to automatically rejigger the weights to maximally boost user ratings.
Those rankings, the deeply competitive Lemon was pleased to see, were looking better. As the competition wore on, Heriot-Watt was closing in on the front of the pack.
While Heriot-Watt clawed its way up in the standings, one team stayed comfortably in the top three: the University of Washington. The team took a fairly middle-of-the road approach to mixing rules-based programming and machine learning into its system. Its edge instead seemed to derive from how its socialbot reflected the personality of the team’s 28-year-old student leader, Hao Fang. Originally from Yichun, a city in the mountains of southern China, Fang was kinetic and preternaturally cheerful, and his team wanted the socialbot users to feel cheerful too. How could they create conversations that people would enjoy?
Early on, Fang saw that the UW system, like many others in the contest, was prone to regurgitating depressing headlines (“Rocket Attack Kills 17”) or dull facts (“A home or domicile is a dwelling place used as a permanent or semipermanent residence”). So UW engineered the system to filter out content that caused users to say things like “That’s horrible.” Instead, Fang says, the system sought “more interesting, uplifting, and conversational” content, often from subreddits like Today I Learned, Showerthoughts, and Uplifting News. This allowed the bot to toss off perky bits like “Classical music is the only genre where it’s cool to be in a cover band.”
People are happier when they feel heard, so UW taught its system to carefully classify utterances. Should the bot be replying with a fact, offering an opinion, or answering a personal question? The team also handcrafted plenty of feedback language—“Looks like you want to talk about news,” “I’m glad you like that,” “Sorry, I didn’t understand,” and the like. Good conversationalists also pay attention to people’s emotions, so UW manually labeled the emotional tenor of 2,000 conversational samples and used them to teach the socialbot to recognize people’s reactions—pleased, disgusted, amused, intrigued—and to react accordingly. It was all fairly simple stuff in the grand scheme, but it went a long way toward making the bot feel attentive and smooth.
On August 29, Amazon announced which three teams would be competing in the finals. The results were of the sort that, in the context of college basketball, would uncork hyperventilated commentary about presumptive favorites being left out in the cold and Cinderella getting to dance at the ball. Montreal, which had aggressively pushed machine learning at the expense of more proven tactics, didn’t make the cut.
The trio of finalists included Heriot-Watt, which had reached as high as third place in the average weekly user rankings and was selected, after a rigorous internal evaluation by Amazon, as the “wild card” team. UW, which had run strong all along, finished second. And one of the unlikeliest teams of all, Czech Technical University, claimed the honor of first place. Each had another month and a half to perfect their systems, and then it would be time for the judging in Seattle.
"Alexa, let’s chat.”
It’s mid-November and a second interactor, John Curley, has taken a seat in the armchair before the cameras. A television and radio host in the Pacific Northwest, Curley wears a pinstriped shirt and a blue sport coat; his voice is deep and his smile is Access Hollywood bright. But his jumpy verbal style soon gives the socialbots fits.
“Pleasure talking with you, John,” a socialbot says. It’s the Heriot-Watt one, though neither Curley nor the judges know that. “Let’s get to know one another. So tell me, are you more into sci-fi or fantasy?”
“How about neither?” Curley replies, rebuffing the bot. “Let me ask you a question, Alexa. Yesterday there was a huge storm, a big windstorm here in Seattle.”
“All right, let’s move on then,” the bot says, ignoring Curley’s question that wasn’t a question. “Tell me, are you more interested in reading books or watching movies?”
“Reading books,” Curley says.
“Oh, a bookworm … What book have you read recently?”
“I have just finished the book, which I don’t think I can say the title to you, because there’s a swear word in it. But the title is The Subtle Art of Not Giving a—fill in the blank.”
The bot, not able to work with this, soldiers on. “What books do you like to read again and again?”
Ignoring the question, Curley strikes out in a new direction. “Alexa, I’ll tell you something. Can I be honest with you?”
Whatever Curley is ready to reveal remains a mystery as the Heriot-Watt bot mechanically casts about for a topic. “So tell me, are you more interested in sports or videogames?”
Back and forth they go, arriving nowhere. Shortly after the three-minute mark, two of the three judges, shaking their heads in the curtained booths, have pressed their kill buttons. Curley’s chats with the other bots offer much of the same. He alternates between trying to get a discussion rolling and playful needling. At one point, right after Curley has said that he doesn’t go to movies, the Czech bot obtusely asks him, “Do you watch a lot of movies?”
“No, I don’t, because I am blind,” Curley sarcastically replies.
“How do you choose a movie to watch?” the bot says, plowing ahead with its prescripted dialog.
“I normally choose them via smell,” Curley says.
Curley is precisely the sort of uncooperative user that Marek feared. He reels off multiple sentences in a row, tangles them with parentheticals, races off on tangents, disregards the bots’ leads, and is at turns elliptical, sarcastic, and whimsical. In short, Curley talks like a human. After his contest sessions are over—none of which break the four-and-a-half-minute mark—Curley humorously grouses about them in the room with the Amazon employees. “It was like a series of bad dates,” he says.
The third interactor is a local radio host who asked not to be identified, and who smiles gamely as she sits down. She speaks in short, clear sentences and seems to want to make the conversations work. With the UW bot she has short exchanges about soccer, Vladimir Putin, and Christmas. With the Czech bot, she talks about a book she is reading. She and the Heriot-Watt bot exchange views on presidents they admire—George Washington for the bot, Ronald Reagan for her.
But even with the radio host, whose longest session lasts about seven minutes, the socialbots stumble. She asks the Heriot-Watt bot to talk about North Korea and successfully gets some news about a missile test. She leans forward, looking concerned. “There could be a chance for war,” she says.
“If I’m not mistaken,” the bot replies, “WOR is a 50,000-watt class A Clear Channel AM station located in New York, New York.” The judges can’t hit their kill buttons fast enough.
The best conversation in the finals happens with George. While hardly the sparkling repartee of a Tom Stoppard play, it immediately stands out. The chat opens with George asking to talk about robots. Rather than tediously reading a Wikipedia-derived summary of what a robot is, the socialbot jokes, “What if Daft Punk really are two robots who just want to make music?”
“That’s funny,” George says, laughing.
The bot shares some recent news about Elon Musk and robots. Tossing the ball back to George, the bot asks, “Have you heard anything about Elon Musk?”
“I have,” George brags. “I know him.”
“Did you know that Elon Musk was executive producer for the movie Thank You for Smoking?”
“No,” George says, sounding impressed. He and the bot go back and forth before settling on books as their next topic. They take a couple of turns, and then the socialbot says, “You know what I was thinking? Eventually, someone will be the last person to ever be alive. Their name won’t be in any history books.”
“Oh, that is sad!” George replies.
“I’m sorry to make you upset. Would you like to continue our discussion on books?”
“Let’s talk about the book The Dark Tower.”
“Sorry, I’m not sure I know anything about the book The Dark Tower. Would you like to talk about the movie The Dark Tower?”
“Super. Did you watch this movie? It was released this year.”
The timer hits 19 minutes and the conversation is still going.
The bot asks George if he liked Matthew McConaughey’s performance. George did. Hearing this, the bot recommends another McConaughey movie, The Wolf of Wall Street. A couple of turns later, the bot makes a joke. “You know what I was thinking? Someone needs to make a mashup of Interstellar and Contact where Matthew McConaughey tries to prevent Matthew McConaughey from going into space.”
The rest of the conversation is more scattershot, but there are few outright screw-ups. Music, sports. Ten minutes. The movie The Boondock Saints. Twelve minutes. Santa Claus and his unintended role in climate change. Thirteen minutes. George asks the bot to sing. It complies. Fifteen minutes. Music and movies again, health care and Bill Gates. The timer hits 19 minutes and the conversation is still going.
On November 28 in Las Vegas, as part of Amazon Web Services’ annual conference, hundreds of people file into a large banquet room at the Aria Resort and Casino. The front row of seats is reserved for the Alexa Prize finalists. “It’s anyone’s game,” Heriot-Watt’s Lemon thinks. Marek toggles between optimism and doubt. Fang and his UW teammates are the most visibly stressed out. Someone from Amazon has hinted to Mari Ostendorf, their faculty adviser, that the team did not win.
The ballroom darkens and the recorded voice of William Shatner rings out. “Computer?” he says. “Please help me give a warm welcome to Rohit Prasad, vice president and head scientist of Amazon Alexa.” Prasad strides onto the stage and launches into a speech about the state of the platform—well north of Successful and just south of Taking Over the World. Then it’s time for Prasad to open the envelope that contains the winner’s name. “So with an average score of 3.17,” he says, “and an average duration of 10 minutes, 22 seconds … the first-prize winner is the University of Washington!” The UW team members explode from their seats, a scream piercing the air. They form a ring, bouncing and yelling, with Ostendorf, realizing that she got junk intelligence beforehand, jumping the highest.
It was the UW bot that had pulled off the long conversation with George. Fang later calls it “the best conversation we ever had.” At the very end, the bot had gone into a dry cul-de-sac about health care. Two judges had clicked out just shy of the 20-minute mark. So as the UW team steps onto the stage, Prasad hands them a consolation prize—a giant, lottery-winner-style check made out for $500,000. Fang, grinning widely, clutches it and gives a thumbs-up for the cameras.
Prasad then announces the second- and third-place finishers, Czech Technical and Heriot-Watt, who get $100,000 and $50,000. Lemon, competitive to the end, has a pinched look on his face. Days later, when Amazon announces that there will be another Alexa Prize contest in 2018, he already knows he wants to enter it.
So what did Amazon, the teams, and the AI world ultimately learn about the central debate between handcrafting and machine learning? UW, the winner, had shot for the middle. The handcrafting-heavy Czech team, meanwhile, had finished second. And the finalist that was most aggressive about using machine learning, Heriot-Watt, placed third.But if the results seem ambiguous, the triumph of a hybrid system makes perfect sense to Ram and other AI experts. We’re just beginning to figure out how best to combine the two approaches, Ram says.
Everyone in the contest also agrees on what would be most helpful to push machine learning forward: more conversational data. That, ultimately, is Amazon’s own contest booty. Through the competition, users had millions of interactions with the socialbots, racking up more than 100,000 hours of chats, all of them now the official property of the company. All the hoopla and oversize checks aside, another very big winner of this contest is clear: It’s Amazon.
Ekaterina ‘Kate’ Lukasheva is an incredible Origami artist and designer from Moscow, Russia. The artist has had a fascination with puzzles and construction sets since childhood and first discovered origami in her teens. With its intricate folds and geometric patterns, there’s a lot of math in origami and Ekaterina would later graduate with honors from Moscow State Lomonosov University as a mathematician and programmer.
As Origami has come to describe a broad field with a number of niche disciplines, Lukasheva’s artwork focuses primarily around modular origami and Kusudama. She has even authored a number of books of her own original designs for others to try.
Below you will find a collection of some of her incredible works but you can find hundreds more at the links below
President Donald Trump has suggested that arming some teachers would help to stop deadly school shootings. But in a viral #ArmMeWith rallying cry, educators are calling on political leaders to “arm” them with they really need: books and school supplies as well as time and resources.
Teachers Olivia Bertels and Brittany Wheaton created the movement, USA Today reported.
On Feb. 19, 2018, “Mister Rogers’ Neighborhood,” turned 50 years old. And the internet was feeling feelings over it.
Photo by PBS Television/Courtesy of Getty Images.
After premiering on Canadian TV in 1963, Fred Rogers’ beloved children’s program debuted in the U.S. in 1968, inspiring generations of kids across North America to be more thoughtful, kinder neighbors.
One person feeling the feels on the show’s anniversary was model, author, and Twitter goddess Chrissy Teigen.
Teigen tweeted the most delightful anecdote about why Rogers would often announce that he was feeding the fish during the show.
Mister Rogers would narrate himself feeding the fish each episode with “I’m feeding the fish” because of a letter he received from a young blind girl who was worried the fish were hungry. Love you, Mister Rogers. https://t.co/YXacyFDXKo
“Mister Rogers would narrate himself feeding the fish each episode with, ‘I’m feeding the fish,’ because of a letter he received from a young blind girl who was worried the fish were hungry,” she wrote. “Love you, Mister Rogers.”
Aaaaaand I’m crying.
Rogers included the text of the girl’s letter in his book, “Dear Mister Rogers, Does It Ever Rain in Your Neighborhood?” published in 1996.
One girl and her family wrote to tell us there was a special reason why she wanted me to talk about feeding the fish each day.
Dear Mister Rogers,
Please say when you are feeding your fish, because I worry about them. I can’t see if you are feeding them, so please say you are feeding them out loud.
Katie, age 5 (Father’s note: Katie is blind, and she does cry if you don’t say that you have fed the fish.)
This downright adorable clip from the series shows Rogers reassuring little Katie that the fish were always well-fed:
“I need to feed the fish right away,” Rogers said in the episode, before shaking the container of food above the tank. “I have some friends who get very concerned when I forget the fish during our visits.”
Aaaaaand I’m ugly crying.
Rogers showed us how simple it often is to be a more compassionate friend.
Photo by Getty Images.
“I just wanted you to know that even if I forget to feed them when we’re together, I come back later and feed them, so they’re always taken care of,” Rogers concluded. “It’s good to know that fish and animals and children are taken care of by those who can, isn’t it?”
Yes it is, Mister Rogers. The world needs more neighbors like you.
1. Start doing more things alone, even if you don’t want to. Most people go a majority of their life without even knowing who they are or what they want. Spending time with yourself and pushing yourself out of your comfort zone will immensely help your growth. It will help you figure out your likes and dislikes.
2. Start admitting when you’re wrong. It’s not easy, but it’s important. You don’t want to turn into one of those people everyone complains about for never being able to apologize because you can’t swallow your pride. Admit when you’re wrong. We all make mistakes, there’s no shame in that. Owning up to it instead of trying to cover it up is a much better look.
3. Ask hard questions. Even questions you don’t necessarily want to know the answer too. Asking hard questions is tough but the answers can teach you a lot and be vital to your growth.
4. Stop wasting your time over petty things. Life is already stressful enough, the last thing you need to do is let yourself get worked up over petty little things that bring nothing but unnecessary drama to your life. It’s time to let that stuff go and focus on more important things in life.
5. Accept that road rage isn’t going to help you get anywhere any faster. Again, all it’s doing is stressing you out for no reason. You can allow that to ruin your whole morning or day if you don’t take control of your emotions now. Channel that emotion and energy into something positive and work on changing your overall mindset every time you find yourself starting to get worked up.
6. Start taking big risks. Your 20s are the time in your life to take risks and try all the things you might fail at. Start a business, travel, try different jobs fields, move across the country. You are young enough now that you will bounce back from whatever failure or setback you might encounter. Do as much as you can while you still have minimal responsibilities compared to your future self.
7. Start saving your money. Put part of every paycheck away into your Roth or at least put it in a savings account you won’t touch unless you are in dire need of it. Spending money on eating out, clothing, travel, etc., are all fun but if something goes wrong or a big expense you weren’t expecting comes up you’ll be pissed you spent $50 on shopping when you could have stashed that away into a savings account.
8. Start reading more. Reading is so vital to your growth. It expands your mind and helps you think about things from a new perspective, even fiction books. Challenge yourself to read one book a month, even one book every two months but read. Not to mention reading is a workout for your brain and is great exercise for your memory.
9. Master the art of listening. Everyone is so caught up in their own lives and what they’re doing that we tend to make all our conversations about ourselves. Stop talking about what you did and start listening to someone else. Listen, like put your phone down and really listen, to someone when they’re talking to you. It feels great when you have someone listen to you and you know they’re paying attention so practice doing that for other people. No one likes the person who constantly puts their input or opinion in and is always butting in the conversation when it’s not their turn to talk.
10. Gain more experiences. Worry less about collecting “things” in your 20s and worry more about gaining experiences. Spend more money on experiences and less money on material items. Memories and sharing moments with people will fill you a lot more than having a souvenir of a place you went.
11. Create a schedule or routine. Nothing throws your life and productivity out of whack like not being in a routine. Prioritizing your time and your to-do list becomes immensely harder when you don’t. Get a planner or bullet journal or whatever you may need to organize your life better, but utilize that to the fullest extent.
12. Realize being hungover is not a good way to spend every weekend. I don’t know about you but when I’m hungover I’m a useless piece of shit and accomplish next to nothing. Drinking is fun, but wasting an entire day being hungover is not. Like my mom says to me, you don’t have to black out every time you go out. You can still have fun without drinking so much you want to die the next day.
13. Start setting long and short-term goals with deadlines. Setting goals you can accomplish with a time frame is super important. Use Asana or your choice of organizational calendar but write down goals you can measure that you’ll actually be able to accomplish. Maybe it’s ‘write X number of articles by the end of the month’ or ‘go to the gym 3 times this week’. It’s important to write them down so you can hold yourself accountable.
14. Wake up early and start your morning off by being productive. Waking up early isn’t for everyone, I get that. Some people are night owls by nature but getting into a morning routine where you’re not always rushing out the door is so important for starting your day off on the right foot. I have a morning routine every day which helps me know what I’m doing so I’m not frantically running around before work. Know what you’re eating for breakfast, know when you’re going to shower, know what time you have to walk out the door so you’re not late. Make your morning routine a habit so it becomes easier as you go.
15. Tell the truth even when it’s hard. Honesty is incredibly important in life and will get you so much further than lying, even when it’s hard. Growing up you’re taught that consequences are always worse when you lie at first and it’s true. Making mistakes and messing up is inevitable and lying to cover it up will cause more of a negative repercussion than if you were just up front at the start.
16. Remove the toxic people from your life. This can be one of the most challenging things you do in your 20s but it’s important to realize that not everyone has your best interest at heart and some people, even if they seem close to you, would rather see you fail than succeed because they’re petty. It’s important to notice who lets you down, who holds you back, who is only around when they need something and who is truly there for you. Letting go of people you love or want to keep in your life can be extremely hard but removing yourself from those relationships can be incredibly impactful to your life.
17. Learn how to accept other people’s views that are different than your own. There are some opinions that make absolutely no sense to me but I am also aware that some people will disagree with me on my views. There are also some people who will disagree just for the sake of disagreeing. It is impossible to change everyone’s opinions. It doesn’t work. It’s important to accept that sometimes the best thing you can do is smile and nod, then walk away knowing no matter what way you tried to explain your views it wouldn’t make a difference to that person.
18. Learn how to empathize. Empathy is vital to all relationships. It’s important to understand that not everyone is in a similar situation than you. Some people have it easier and some have it much harder. It’s important to look outside the world you live in every day and look at things from a different viewpoint to react appropriately to the situations at hand.
19. Take the uncomfortable measures to learn who you are. Your 20s are when you finally start to figure out who you are and what you like. It’s so important that you stop worrying about what others may think of your decisions and do what you feel is right and necessary. You’re the only one who gets to live your life and at the end of the day, you have to do what’s best for you. I started life coaching and it made a tremendous impact in my life. It allowed me to figure out who I am and what I want.
20. Stand up for what you believe in. Stand up for what you believe in even if it isn’t what the majority believes in. You have a voice and you should use it. My only request is that you’re not an asshole about it.
21. Learn how to say no. When you don’t want to do something make sure you make that clear. Majority of people tiptoe around other people and their feelings, in turn putting themselves in situations they don’t necessarily want to be in. No is a complete sentence and you should feel comfortable using it.
22. Travel! Travel is the best way to emerge yourself in different cultures and ways of life. Travel will open your eyes to the diversity of the world and help you grasp a better understanding of others. If you can do anything in your 20s, I urge you to travel to a foreign country. It’s the most incredible, eye-opening experience and will help you put a lot in perspective and maybe even challenge your thoughts.
23. Understand and accept that not everyone has the same heart as you. This is a really hard pill to swallow, especially when you put your best intentions first and you trust others to do the same. Sometimes you will get burned, don’t let it make you hard and change your heart though. Keep being the best version of yourself you can be.
24. Understand sometimes things just aren’t mean to work out. You can love a person but it doesn’t mean it will work out or they won’t hurt you. You can love a job and still lose it. You can love a lot of different things in life but some things aren’t meant to work out no matter how much you want them too. It hurts and it sucks, but that’s life and it’s not fair. Recognizing that now will help you be prepared in the future for when things don’t go as you hope. It won’t make the pain any less but it’s important to understand.
25. Continue to push yourself out of your comfort zone. Don’t let yourself get stagnant. There is only so much happiness you can feel when things are easy and simple. It’s when you start to be challenged and things are scary that you start to feel real happiness and success. When things are easy there is no way to gain anything from it. You need new experiences, challenges, and lessons to come your way to improve and grow. Conquering challenges outside of your comfort zone, no matter how big or small, will make you highs feel so much higher, and it will feel worth it.
He lived around the corner from me. George was tall and lanky. His elbows always akimbo, his cowlick stellar in its sheer verticality. He had an aquarium. He had a glow-in-the-dark board game. He had the 45 rpm of “Hang On, Sloopy,” and he was a Harry Nilsson fan, just like me. I can still recall his house, and all of the luminous joy it held, perfectly in my mind’s eye — all part of the frozen 7-year-old’s mosaic that exploded into pieces when my parents’ marriage failed.
After my parents split, George and I lived just an hour apart. But our parents weren’t willing to ensure that George and I stayed in regular contact. Once or twice a year, we were allowed a sleepover, and George always came to spend the night on my birthday. His visit was the one gift I asked for.
Then one day it ended. My mother simply said, “no more.” To this day, I don’t know what triggered that choice, but my guess is she was feeling vaguely uncomfortable that two boys, by then around 11 years old, were moving on to things more productive than comic books and sleepovers. I suspect she felt she could no longer sponsor something so … intense. From her perspective, it was unnaturally so.
With that decision, it wasn’t just my friendship with George that died. I lost my understanding of where close male friendships fit into my life.
The topic of male friendships remains largely undiscussed, but for American men, it can be a matter of life and death.
Niobe Way is a professor of applied psychology at New York University and the author of “Deep Secrets: Boys’ Friendships and the Crisis of Connection.” A number of years ago, she started asking teenage boys what their closest friendships meant to them and documenting what they had to say.
It seems that few scholars have thought to ask boys what was happening with their closest friendships because we assumed we already knew. We often confuse what is expected of men (traditional masculinity) with what they actually feel — and given enough time, they confuse the two as well. After a lifetime of being told how men “typically” experience emotion, the answer to the question “what do my closest friends mean to me” is lost to us.
Way’s research shows that boys in early adolescence express deeply fulfilling emotional connection and love for each other, but by the time they reach adulthood, that sense of connection evaporates.
This is a catastrophic loss; a loss we somehow assume men will simply adjust to. They do not. Millions of men are experiencing a sense of deep loss that haunts them even though they are engaged in fully realized romantic relationships, marriages, and families.
“Emotional isolation is ranked as high a risk factor for mortality as smoking. A partial list of the physical diseases thought to be caused by or exacerbated by loneliness would include Alzheimer’s, obesity, diabetes, high blood pressure, heart disease, neurodegenerative diseases, and even cancer — tumors can metastasize faster in lonely people.”
Loneliness can also affect the mortality rate more directly. Research also shows that between 1999 and 2010, suicide among men aged 50 and over rose by nearly 50%. The New York Times reports that “the suicide rate for middle-aged men was 27.3 deaths per 100,000, while for women it was 8.1 deaths per 100,000.”
The boys featured in Way’s book express, in their own words, a heartfelt emotional intimacy that many men can recall from their own youth.
Consider this quote from a 15-year-old boy named Justin:
“[My best friend and I] love each other … that’s it, you have this thing that is deep, so deep, it’s within you, you can’t explain it. It’s just a thing that you know that that person is that person and that is all that should be important in our friendship. I guess in life, sometimes two people can really, really understand each other and really have a trust, respect, and love for each other. It just happens, it’s human nature.”
This passionate and loving boy-to-boy connection occurs across class, race, and cultures. It is exclusive to neither white nor black, rich nor poor. It is universal and beautifully evident in the hundreds of interviews that Way conducted. These boys declare freely the love they feel for their closest friends. They use the word “love,” and they seem proud to do so.
But Justin also senses, even as it’s happening, the distancing that occurs as he matures and male intimacy becomes less accepted. He says this in his senior year, reflecting on how his relationships have changed since he was a freshman:
“I don’t know, maybe, not a lot, but I guess that best friends become close friends. So that’s basically the only thing that changed. It’s like best friends become close friends, close friends become general friends and then general friends become acquaintances. So they just, if there’s distance whether it’s, I don’t know, natural or whatever. You can say that, but it just happens that way.”
According to Way, this “natural” distancing is a lot more artificial than it is innate — a result of toxic judgments leveled against boys by their environment and society.
“Boys know by late adolescence that their close male friendships, and even their emotional acuity, put them at risk of being labeled girly, immature, or gay,” Way writes. “Thus, rather than focusing on who they are, they become obsessed with who they are not — they are not girls, little boys nor, in the case of heterosexual boys, are they gay.”
The result? “These boys mature into men who are autonomous, emotionally stoic, and isolated,” as Way puts it. In other words, the pressures of homophobia and toxic masculinity push boys into isolation until they become swept up in the epidemic of male loneliness that haunts the majority of American men.
It is a heartrending realization that even as men hunger for real connection in male relationships, we have been trained away from embracing it.
Since Americans hold emotional connection as a female trait, many reject it in boys, demanding that they “man up” and adopt a strict regimen of emotional independence and even isolation as proof they are real men. Behind the drumbeat message that real men are stoic and detached is the brutal fist of homophobia, ready to crush any boy who might show too much of the wrong kind of emotions.
We have been trained to choose surface level relationships or no relationships at all, sleepwalking through our lives out of fear that we will not be viewed as real men. We keep the loving natures that once came so naturally to us hidden and locked away. This training runs so deep, we’re no longer even conscious of it. And we pass this training on, men and women alike, to generation after generation of bright eyed, loving little boys.
When I was in my early 30s, I ran into George again.
He was working for a local newspaper and living in an apartment in Houston, where I visited him. To my surprise, he happily split up his comic collection (I had sold mine when I was 16 or so) and gave me half of his huge collection. It was an act of profound generosity, and I’m sure I was effusive in my thanks.
I ran into George again in my 40s. He had married and moved to California. On a business trip, I spent the night at his house. We fell into our old pattern of reading comic books and drawing while his wife hovered, declaring over and over how great it was that I was visiting. The next day I packed up and went home to New York feeling vaguely disconnected but happy.
About two years later, his wife called me, screaming and weeping. George had died.
To this day, I remain shocked. “Why didn’t I connect more” was my first thought. My second was how effusive his wife had been about my visit. So supportive. So happy for “George’s friend” to be there. I was never able to follow up after his death. I don’t even know what killed him, just an illness.
How is this possible? How did I sleepwalk through the chance to reconnect this friendship? I should have cared. I should have given a damn. Why didn’t I? Because somewhere, somehow, I was convinced that close friendships with boys are too painful?
Don’t parents understand? Don’t they know that we love each other? That our children’s hearts can be broken so profoundly that we will never rise to a love like that again?
The loss of my friendship with George set a pattern in my life that I am only now, decades later, finally conscious of.
I have walked past so many friendships. Sleepwalking past men as I went instead from woman to women, looking for everything I had lost. Looking instead in the realm of the romantic, the sexual. A false lead to a false solution. And in doing so, I have missed so many opportunities to live a fuller life.
Way’s work has given me the piece of the puzzle I was never conscious of. That the love I had felt for George and others — Troy, Jack, David, Bruce, and Kyle — was right and good and powerful and could move mountains. I didn’t realize what they were then. But I do now. That the slow withdrawing of those friendships from my life had not been a killing blow. Not quite. And that I’m back in the game of loving my friends. Fiercely.