Inside the Alexa Prize

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.

AI Glossary

Chatbot:

A computer ­program designed to converse with humans.

Socialbot:

An especially schmoozy chatbot—one that can engage in extended small talk, not just cue up music and take down grocery lists.

Handcrafting:

A ­labor-intensive technique for ­programming chatbots that involves writing explicit rules and templates.

Machine learning:

A type of AI that learns to perform a task by analyzing patterns in data, rather than by relying on rules written by people.

Seq2seq:

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.

Amazon’s control room during the Alexa Prize judging.

Courtesy of Amazon

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.

The University of ­Washington’s team: (from left) Hao Cheng, Maarten Sap, Ari Holtzman, Elizabeth Clark, Hao Fang.

Ian Allen

"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.

LEARN MORE

The WIRED Guide to Artificial Intelligence

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?”

“Sure.”

“Super. Did you watch this movie? It was released this year.”

“I did.”

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.”

George guffaws.

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.

The University of ­Washington’s team advisers, professors Noah A. Smith and Mari Ostendorf.

Ian Allen

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.


Inside Amazon


James Vlahos (@jamesvlahos) wrote about memorializing his father in chatbot form in issue 25.08.

This article appears in the March issue. Subscribe now.

Listen to this story, and other WIRED features, on the Audm app.

Read more: https://www.wired.com/story/inside-amazon-alexa-prize/

Charles Manson, Imprisoned Mass-Murdering Cult Leader, Dies

Charles Manson, the imprisoned wild-eyed cult leader who masterminded the 1969 murders of actress Sharon Tate and six other people in Los Angeles, has died. He was 83.

Manson died of natural causes at 8:13pm Pacific time on Nov. 19 at Kern County Hospital, according to a statement from the California Department of Corrections and Rehabilitation. He was serving a life sentence at a state prison in California.

A career criminal, Manson persuaded a drug-induced flock of followers — the so-called Manson family — that he was the reincarnation of Jesus Christ and that they would survive and rule the world after a racial apocalypse he called “Helter Skelter.” The name came from a Beatles song he viewed as prophetic.

Manson’s followers may have killed more than two dozen people by some reports, but criminal trials against him and his group focused on the savage killing spree that became known as the Tate-LaBianca murders.

With a focus on killing Hollywood celebrities, Manson ordered followers Charles “Tex” Watson, Susan Atkins, Patricia “Katie” Krenwinkel and Linda Kasabian to invade a Los Angeles home on Aug. 9, 1969, and kill its occupants.

Death Toll

In addition to Tate, the 26-year-old pregnant wife of film director Roman Polanski, those killed from multiple stabbings and gunshots were writer and actor Wojciech “Voytek” Frykowski and his partner, the coffee bean heiress Abigail Folger; celebrity hairstylist Jay Sebring and Steven Parent, a friend of Tate’s gardener. Polanski was in London working on a film.

Kasabian acted as the lookout and became the star witness against Manson, whose role in the killings was discovered by police while investigating other crimes. She was offered immunity for her testimony.

The killing of Tate, who starred in films such as “Valley of the Dolls,” was particularly gruesome. She was stabbed in the stomach by Atkins despite pleas to spare her unborn child, whose delivery date was near. Atkins used Tate’s blood to write the word “pig” on the front door.

The next night, Manson took Watson, Krenwinkel and Leslie Van Houten to the home of supermarket executive Leno LaBianca and his wife, Rosemary, who were also murdered.

The trio stayed in the house for a while, eating food from the LaBianca’s refrigerator and playing with the couple’s dogs.

Intended Victims

Atkins told fellow prisoners that the Manson family planned to kill other Hollywood stars to help trigger the racial apocalypse Manson predicted. She died in a women’s prison in 2009.

Manson’s trial began in June 1970. After a trial characterized by the giggling and grimaces of the defendants, Manson was convicted of first-degree murder in January 1971.

He was sentenced to death. California’s supreme court later ruled capital punishment illegal, and he was re-sentenced to life imprisonment. Manson, who carved a swastika into his forehead while in prison, was denied parole more than a dozen times.

“There’s no murder in a holy war,” he told Charlie Rose in a 1986 interview on “CBS News Nightwatch,” referring to Tate’s slaying.

Charles Maddox, whose crazed deeds would spawn a series of books, movies and documentaries, was born Nov. 12, 1934, in Cincinnati, Ohio, to Kathleen Maddox, a 16-year-old alcoholic prostitute and Walker Scott. After her marriage to William Manson, Charles was given his step-father’s last name.

Career Criminal

He made a living through crime, spending half of the first 32 years of his life behind bars. Manson was put in jail for armed robbery, arson, burglary, assault, mail theft, drug possession, forgery, credit-card fraud, receiving stolen property, pimping, grand theft auto and numerous parole violations.

After his release from prison in 1967, he became a cult guru in the San Francisco area as a prophet of the apocalypse and tried to pursue a career in music.

He was befriended by Dennis Wilson, the drummer in the Beach Boys band. Through this association, Manson got an opportunity to audition for record producer Terry Melcher, the son of singer and actress Doris Day. Melcher, who had rejected Manson’s bid to make a record, was the previous occupant of the Los Angeles house Polanski and Tate had rented, which was the site of the first murders.

In 1955, Manson married Rosalie Willis and had a son Charles Manson, Jr., who committed suicide in 1993. After their divorce, he married Leona Stevens and had a second son, Charles Luther Manson. He had a third son, Valentine Manson, with Manson family member Mary Brunner.

“The name Manson has become a metaphor for evil, and evil has its allure,” the prosecutor of the Tate-La Bianca case, Vincent Bugliosi, co-wrote in the best-selling book on the Manson case, “Helter Skelter: The True Story of the Manson Murders.” “Some people have the same fascination for Jack the Ripper and Hitler.”

    Read more: http://www.bloomberg.com/news/articles/2017-11-20/charles-manson-jailed-mass-murdering-cult-leader-dies-at-83

    Naomi Klein: how power profits from disaster

    The long read: After a crisis, private contractors move in and suck up funding for work done badly, if at all then those billions get cut from government budgets. Like Grenfell Tower, Hurricane Katrina revealed a disdain for the poor

    There have been times in my reporting from disaster zones when I have had the unsettling feeling that I was seeing not just a crisis in the here and now, but getting a glimpse of the future a preview of where the road we are all on is headed, unless we somehow grab the wheel and swerve. When I listen to Donald Trump speak, with his obvious relish in creating an atmosphere of chaos and destabilisation, I often think: Ive seen this before, in those strange moments when portals seemed to open up into our collective future.

    One of those moments arrived in New Orleans after Hurricane Katrina, as I watched hordes of private military contractors descend on the flooded city to find ways to profit from the disaster, even as thousands of the citys residents, abandoned by their government, were treated like dangerous criminals just for trying to survive.

    I started to notice the same tactics in disaster zones around the world. I used the term shock doctrine to describe the brutal tactic of using the publics disorientation following a collective shock wars, coups, terrorist attacks, market crashes or natural disasters to push through radical pro-corporate measures, often called shock therapy. Though Trump breaks the mould in some ways, his shock tactics do follow a script, and one that is familiar from other countries that have had rapid changes imposed under the cover of crisis.

    This strategy has been a silent partner to the imposition of neoliberalism for more than 40 years. Shock tactics follow a clear pattern: wait for a crisis (or even, in some instances, as in Chile or Russia, help foment one), declare a moment of what is sometimes called extraordinary politics, suspend some or all democratic norms and then ram the corporate wishlist through as quickly as possible. The research showed that virtually any tumultuous situation, if framed with sufficient hysteria by political leaders, could serve this softening-up function. It could be an event as radical as a military coup, but the economic shock of a market or budget crisis would also do the trick. Amid hyperinflation or a banking collapse, for instance, the countrys governing elites were frequently able to sell a panicked population on the necessity for attacks on social protections, or enormous bailouts to prop up the financial private sector because the alternative, they claimed, was outright economic apocalypse.

    The Republicans under Donald Trump are already seizing the atmosphere of constant crisis that surrounds this presidency to push through as many unpopular, pro-corporate policies. And we know they would move much further and faster given an even bigger external shock. We know this because senior members of Trumps team have been at the heart of some of the most egregious examples of the shock doctrine in recent memory.

    Rex Tillerson, the US secretary of state, has built his career in large part around taking advantage of the profitability of war and instability. ExxonMobil profited more than any oil major from the increase in the price of oil that was the result of the 2003 invasion of Iraq. It also directly exploited the Iraq war to defy US state department advice and make an exploration deal in Iraqi Kurdistan, a move that, because it sidelined Iraqs central government, could well have sparked a full-blown civil war, and certainly did contribute to internal conflict.

    Rex
    Rex Tillerson, now US secretary of state, is a former CEO of ExxonMobil. Photograph: Mike Stone/Reuters

    As CEO of ExxonMobil, Tillerson profited from disaster in other ways as well. As an executive at the fossil fuel giant, he spent his career working for a company that, despite its own scientists research into the reality of human-caused climate change, decided to fund and spread misinformation and junk climate science. All the while, according to an LA Times investigation, ExxonMobil (both before and after Exxon and Mobil merged) worked diligently to figure out how to further profit from and protect itself against the very crisis on which it was casting doubt. It did so by exploring drilling in the Arctic (which was melting, thanks to climate change), redesigning a natural gas pipeline in the North Sea to accommodate rising sea levels and supercharged storms, and doing the same for a new rig off the coast of Nova Scotia.

    At a public event in 2012, Tillerson acknowledged that climate change was happening but what he said next was revealing: as a species, humans have always adapted. So we will adapt to this. Changes to weather patterns that move crop production areas around well adapt to that.

    Hes quite right: humans do adapt when their land ceases to produce food. The way humans adapt is by moving. They leave their homes and look for places to live where they can feed themselves and their families. But, as Tillerson well knows, we do not live at a time when countries gladly open their borders to hungry and desperate people. In fact, he now works for a president who has painted refugees from Syria a country where drought was an accelerant of the tensions that led to civil war as Trojan horses for terrorism. A president who introduced a travel ban that has gone a long way towards barring Syrian migrants from entering the United States.

    A president who has said about Syrian children seeking asylum, I can look in their faces and say: You cant come. A president who has not budged from that position even after he ordered missile strikes on Syria, supposedly moved by the horrifying impacts of a chemical weapon attack on Syrian children and beautiful babies. (But not moved enough to welcome them and their parents.) A president who has announced plans to turn the tracking, surveillance, incarceration and deportation of immigrants into a defining feature of his administration.

    Waiting in the wings, biding their time, are plenty of other members of the Trump team who have deep skills in profiting from all of that.


    Between election day and the end of Trumps first month in office, the stocks of the two largest private prison companies in the US, CoreCivic (formerly the Corrections Corporation of America) and the Geo Group, doubled, soaring by 140% and 98%, respectively. And why not? Just as Exxon learned to profit from climate change, these companies are part of the sprawling industry of private prisons, private security and private surveillance that sees wars and migration both very often linked to climate stresses as exciting and expanding market opportunities. In the US, the Immigration and Customs Enforcement agency (Ice) incarcerates up to 34,000 immigrants thought to be in the country illegally on any given day, and 73% of them are held in private prisons. Little wonder, then, that these companies stocks soared on Trumps election. And soon they had even more reasons to celebrate: one of the first things Trumps new attorney general, Jeff Sessions, did was rescind the Obama administrations decision to move away from for-profit jails for the general prison population.

    Trump appointed as deputy defence secretary Patrick Shanahan, a top executive at Boeing who, at one point, was responsible for selling costly hardware to the US military, including Apache and Chinook helicopters. He also oversaw Boeings ballistic missile defence programme a part of the operation that stands to profit enormously if international tensions continue to escalate under Trump.

    And this is part of a much larger trend. As Lee Fang reported in the Intercept in March 2017, President Donald Trump has weaponised the revolving door by appointing defence contractors and lobbyists to key government positions as he seeks to rapidly expand the military budget and homeland security programmes At least 15 officials with financial ties to defence contractors have been either nominated or appointed so far.

    The revolving door is nothing new, of course. Retired military brass reliably take up jobs and contracts with weapons companies. Whats new is the number of generals with lucrative ties to military contractors whom Trump has appointed to cabinet posts with the power to allocate funds including those stemming from his plan to increase spending on the military, the Pentagon and the Department of Homeland Security by more than $80bn in just one year.

    Contractors
    Contractors for the US-based Blackwater private security firm in Iraq in 2005. Photograph: Marwan Naamani/AFP/Getty Images

    The other thing that has changed is the size of the Homeland Security and surveillance industry. This sector grew exponentially after the September 11 attacks, when the Bush administration announced it was embarking on a never-ending war on terror, and that everything that could be outsourced would be. New firms with tinted windows sprouted up like malevolent mushrooms around suburban Virginia, outside Washington DC, and existing ones, such as Booz Allen Hamilton, expanded into brand new territories. Writing in Slate in 2005, Daniel Gross captured the mood of what many called the security bubble: Homeland security may have just reached the stage that internet investing hit in 1997. Back then, all you needed to do was put an e in front of your company name and your IPO would rocket. Now you can do the same with fortress.

    That means many of Trumps appointees come from firms that specialise in functions that, not so long ago, it would have been unthinkable to outsource. His National Security Council chief of staff, for instance, is retired Lt Gen Keith Kellogg. Among the many jobs Kellogg has had with security contractors since going private was one with Cubic Defense.

    According to the company, he led our ground combat training business and focus[ed] on expanding the companys worldwide customer base. If you think combat training is something armies used to do all on their own, youd be right.

    One noticeable thing about Trumps contractor appointees is how many of them come from firms that did not even exist before 9/11: L-1 Identity Solutions (specialising in biometrics), the Chertoff Group (founded by George W Bushs homeland security director Michael Chertoff), Palantir Technologies (a surveillance/big data firm cofounded by PayPal billionaire and Trump backer Peter Thiel), and many more. Security firms draw heavily on the military and intelligence wings of government for their staffing.

    Under Trump, lobbyists and staffers from these firms are now migrating back to government, where they will very likely push for even more opportunities to monetise the hunt for people Trump likes to call bad hombres.

    This creates a disastrous cocktail. Take a group of people who directly profit from ongoing war and then put those same people at the heart of government. Whos going to make the case for peace? Indeed, the idea that a war could ever definitively end seems a quaint relic of what during the Bush years was dismissed as preSeptember 11 thinking.


    And then theres vice-president Mike Pence, seen by many as the grownup in Trumps messy room. Yet it is Pence, the former governor of Indiana, who actually has the most disturbing track record when it comes to bloody-minded exploitation of human suffering.

    When Mike Pence was announced as Donald Trumps running mate, I thought to myself: I know that name, Ive seen it somewhere. And then I remembered. He was at the heart of one of the most shocking stories Ive ever covered: the disaster capitalism free-for-all that followed Katrina and the drowning of New Orleans. Mike Pences doings as a profiteer from human suffering are so appalling that they are worth exploring in a little more depth, since they tell us a great deal about what we can expect from this administration during times of heightened crisis.

    Before we delve into Pences role, whats important to remember about Hurricane Katrina is that, though it is usually described as a natural disaster, there was nothing natural about the way it affected the city of New Orleans. When Katrina hit the coast of Mississippi in August 2005, it had been downgraded from a category 5 to a still-devastating category 3 hurricane. But by the time it made its way to New Orleans, it had lost most of its strength and been downgraded again, to a tropical storm.

    Thats relevant, because a tropical storm should never have broken through New Orleanss flood defence. Katrina did break through, however, because the levees that protect the city did not hold. Why? We now know that despite repeated warnings about the risk, the army corps of engineers had allowed the levees to fall into a state of disrepair. That failure was the result of two main factors.

    One was a specific disregard for the lives of poor black people, whose homes in the Lower Ninth Ward were left most vulnerable by the failure to fix the levees. This was part of a wider neglect of public infrastructure, which is the direct result of decades of neoliberal policy. Because when you systematically wage war on the very idea of the public sphere and the public good, of course the publicly owned bones of society roads, bridges, levees, water systems are going to slip into a state of such disrepair that it takes little to push them beyond the breaking point. When you massively cut taxes so that you dont have money to spend on much of anything besides the police and the military, this is what happens.

    Mike
    Vice-president Mike Pence with Donald Trump. Photograph: Evan Vucci/AP

    It wasnt just the physical infrastructure that failed the city, and particularly its poorest residents, who are, as in so many US cities, overwhelmingly African American. The human systems of disaster response also failed the second great fracturing. The arm of the federal government that is tasked with responding to moments of national crisis such as this is the Federal Emergency Management Agency (Fema), with state and municipal governments also playing key roles in evacuation planning and response. All levels of government failed.

    It took Fema five days to get water and food to people in New Orleans who had sought emergency shelter in the Superdome. The most harrowing images from that time were of people stranded on rooftops of homes and hospitals holding up signs that said HELP, watching the helicopters pass them by. People helped each other as best they could. They rescued each other in canoes and rowboats. They fed each other. They displayed that beautiful human capacity for solidarity that moments of crisis so often intensify. But at the official level, it was the complete opposite. Ill always remember the words of Curtis Muhammad, a longtime New Orleans civil rights organiser, who said this experience convinced us that we had no caretakers.

    The way this abandonment played out was deeply unequal, and the divisions cleaved along lines of race and class. Many people were able to leave the city on their own they got into their cars, drove to a dry hotel, called their insurance brokers. Some people stayed because they believed the storm defences would hold. But a great many others stayed because they had no choice they didnt have a car, or were too infirm to drive, or simply didnt know what to do. Those are the people who needed a functioning system of evacuation and relief and they were out of luck.

    Abandoned in the city without food or water, those in need did what anyone would do in those circumstances: they took provisions from local stores. Fox News and other media outlets seized on this to paint New Orleanss black residents as dangerous looters who would soon be coming to invade the dry, white parts of the city and surrounding suburbs and towns. Buildings were spray-painted with messages: Looters will be shot.

    Checkpoints were set up to trap people in the flooded parts of town. On Danziger Bridge, police officers shot black residents on sight (five of the officers involved ultimately pleaded guilty, and the city came to a $13.3m settlement with the families in that case and two other similar post-Katrina cases). Meanwhile, gangs of armed white vigilantes prowled the streets looking, as one resident later put it in an expos by investigative journalist AC Thompson, for the opportunity to hunt black people.


    I was in New Orleans during the flooding and I saw for myself how amped up the police and military were not to mention private security guards from companies such as Blackwater who were showing up fresh from Iraq. It felt very much like a war zone, with poor and black people in the crosshairs people whose only crime was trying to survive. By the time the National Guard arrived to organise a full evacuation of the city, it was done with a level of aggression and ruthlessness that was hard to fathom. Soldiers pointed machine guns at residents as they boarded buses, providing no information about where they were being taken. Children were often separated from their parents.

    What I saw during the flooding shocked me. But what I saw in the aftermath of Katrina shocked me even more. With the city reeling, and with its residents dispersed across the country and unable to protect their own interests, a plan emerged to ram through a pro-corporate wishlist with maximum velocity. The famed free-market economist Milton Friedman, then 93 years old, wrote an article for the Wall Street Journal stating, Most New Orleans schools are in ruins, as are the homes of the children who have attended them. The children are now scattered all over the country. This is a tragedy. It is also an opportunity to radically reform the educational system.

    In a similar vein, Richard Baker, at that time a Republican congressman from Louisiana, declared, We finally cleaned up public housing in New Orleans. We couldnt do it, but God did. I was in an evacuation shelter near Baton Rouge when Baker made that statement. The people I spoke with were just floored by it. Imagine being forced to leave your home, having to sleep in a camping bed in some cavernous convention centre, and then finding out that the people who are supposed to represent you are claiming this was some sort of divine intervention God apparently really likes condo developments.

    Baker got his cleanup of public housing. In the months after the storm, with New Orleanss residents and all their inconvenient opinions, rich culture and deep attachments out of the way, thousands of public housing units, many of which had sustained minimal storm damage because they were on high ground, were demolished. They were replaced with condos and town houses priced far out of reach for most who had lived there.

    And this is where Mike Pence enters the story. At the time Katrina hit New Orleans, Pence was chairman of the powerful and highly ideological Republican Study Committee (RSC), a caucus of conservative lawmakers. On 13 September 2005 just 15 days after the levees were breached, and with parts of New Orleans still under water the RSC convened a fateful meeting at the offices of the Heritage Foundation in Washington DC. Under Pences leadership, the group came up with a list of Pro-Free-Market Ideas for Responding to Hurricane Katrina and High Gas Prices 32 pseudo-relief policies in all, each one straight out of the disaster capitalism playbook.

    New
    New Orleans residents wait on a rooftop to be rescued after Hurricane Katrina in 2005. Photograph: Reuters

    What stands out is the commitment to wage all-out war on labour standards and the public sphere which is bitterly ironic, because the failure of public infrastructure is what turned Katrina into a human catastrophe in the first place. Also notable is the determination to use any opportunity to strengthen the hand of the oil and gas industry. The list includes recommendations to suspend the obligation for federal contractors to pay a living wage; make the entire affected area a free-enterprise zone; and repeal or waive restrictive environmental regulations that hamper rebuilding. In other words, a war on the kind of red tape designed to keep communities safe from harm.

    President Bush adopted many of the recommendations within the week, although, under pressure, he was eventually forced to reinstate the labour standards. Another recommendation called for giving parents vouchers to use at private and charter schools (for-profit schools subsidised with tax dollars), a move perfectly in line with the vision held by Trumps pick for education secretary, Betsy DeVos. Within the year, the New Orleans school system became the most privatised in the US.

    And there was more. Though climate scientists have directly linked the increased intensity of hurricanes to warming ocean temperatures, that didnt stop Pence and his committee from calling on Congress to repeal environmental regulations on the Gulf coast, give permission for new oil refineries in the US, and green-light drilling in the Arctic National Wildlife Refuge.

    Its a kind of madness. After all, these very measures are a surefire way to drive up greenhouse gas emissions, the major human contributor to climate change, which leads to fiercer storms. Yet they were immediately championed by Pence, and later adopted by Bush, under the guise of responding to a devastating hurricane.

    Its worth pausing to tease out the implications of all of this. Hurricane Katrina turned into a catastrophe in New Orleans because of a combination of extremely heavy weather possibly linked to climate change and weak and neglected public infrastructure. The so-called solutions proposed by the group Pence headed at the time were the very things that would inevitably exacerbate climate change and weaken public infrastructure even further. He and his fellow free-market travellers were determined, it seems, to do the very things that are guaranteed to lead to more Katrinas in the future.

    And now Mike Pence is in a position to bring this vision to the entire United States.


    The oil industry wasnt the only one to profit from Hurricane Katrina. Immediately after the storm, the whole gang of contractors who had descended on Baghdad when war broke out Bechtel, Fluor, Halliburton, Blackwater, CH2M Hill and Parsons, infamous for its sloppy Iraq work now arrived in New Orleans. They had a singular vision: to prove that the kinds of privatised services they had been providing in Iraq and Afghanistan also had an ongoing domestic market and to collect no-bid contracts totalling $3.4bn.

    The controversies were legion. Relevant experience often appeared to have nothing to do with how contracts were allocated. Take, for example, the company that Fema paid $5.2m to perform the crucial role of building a base camp for emergency workers in St Bernard Parish, a suburb of New Orleans. The camp construction fell behind schedule and was never completed. Under investigation, it emerged that the contractor, Lighthouse Disaster Relief, was in fact a religious group. About the closest thing I have done to this is just organise a youth camp with my church, confessed Lighthouses director, Pastor Gary Heldreth.

    After all the layers of subcontractors had taken their cut, there was next to nothing left for the people doing the work. Author Mike Davis tracked the way Fema paid Shaw $175 per sq ft to install blue tarps on damaged roofs, even though the tarps themselves were provided by the government. Once all the subcontractors took their share, the workers who actually hammered in the tarps were paid as little as $2 per sq ft.

    Every level of the contracting food chain, in other words, is grotesquely overfed except the bottom rung, Davis wrote, where the actual work is carried out. These supposed contractors were really like the Trump Organization hollow brands, sucking out profit and then slapping their name on cheap or non-existent services.

    In order to offset the tens of billions going to private companies in contracts and tax breaks, in November 2005 the Republican-controlled Congress announced that it needed to cut $40bn from the federal budget. Among the programmes that were slashed: student loans, Medicaid and food stamps.

    So, the poorest people in the US subsidised the contractor bonanza twice: first, when Katrina relief morphed into unregulated corporate handouts, providing neither decent jobs nor functional public services; and second, when the few programmes that assist the unemployed and working poor nationwide were gutted to pay those bloated bills.

    New Orleans is the disaster capitalism blueprint designed by the current vice-president and by the Heritage Foundation, the hard-right think tank to which Trump has outsourced much of his administrations budgeting. Ultimately, the response to Katrina sparked an approval ratings freefall for George W Bush, a plunge that eventually lost the Republicans the presidency in 2008. Nine years later, with Republicans now in control of Congress and the White House, its not hard to imagine this test case for privatised disaster response being adopted on a national scale.

    The presence of highly militarised police and armed private soldiers in New Orleans came as a surprise to many. Since then, the phenomenon has expanded exponentially, with local police forces across the country outfitted to the gills with military-grade gear, including tanks and drones, and private security companies frequently providing training and support. Given the array of private military and security contractors occupying key positions in the Trump administration, we can expect all of this to expand further with each new shock.

    The Katrina experience also stands as a stark warning to those who are holding out hope for Trumps promised $1tn in infrastructure spending. That spending will fix some roads and bridges, and it will create jobs. Crucially, Trump has indicated that he plans to do as much as possible not through the public sector but through public-private partnerships which have a terrible track record for corruption, and may result in far lower wages than true public-works projects would. Given Trumps business record, and Pences role in the administration, there is every reason to fear that his big-ticket infrastructure spending could become a Katrina-like kleptocracy, a government of thieves, with the Mar-a-Lago set helping themselves to vast sums of taxpayer money.

    New Orleans provides a harrowing picture of what we can expect when the next shock hits. But sadly, it is far from complete: there is much more that this administration might try to push through under cover of crisis. To become shock-resistant, we need to prepare for that, too.

    Main photograph: AP Photo/Palm Beach Post/Gary Coronado.

    This is an edited extract from No Is Not Enough: Defeating the New Shock Politics by Naomi Klein, published by Allen Lane at 12.99. To order a copy for 11.04, go to bookshop.theguardian.com or call 0330 333 6846. Free UK p&p over 10, online orders only. Phone orders min p&p of 1.99.

    Follow the Long Read on Twitter at @gdnlongread, or sign up to the long read weekly email here.

    Read more: https://www.theguardian.com/us-news/2017/jul/06/naomi-klein-how-power-profits-from-disaster