Languish.org

QuoteA World Without Work

For centuries, experts have predicted that machines would make workers obsolete. That moment may finally be arriving. Could that be a good thing?

     Derek Thompson July/August 2015 Issue

1. Youngstown, U.S.A.

The end of work is still just a futuristic concept for most of the United States, but it is something like a moment in history for Youngstown, Ohio, one its residents can cite with precision: September 19, 1977.

For much of the 20th century, Youngstown's steel mills delivered such great prosperity that the city was a model of the American dream, boasting a median income and a homeownership rate that were among the nation's highest. But as manufacturing shifted abroad after World War  II, Youngstown steel suffered, and on that gray September afternoon in 1977, Youngstown Sheet and Tube announced the shuttering of its Campbell Works mill. Within five years, the city lost 50,000 jobs and $1.3 billion in manufacturing wages. The effect was so severe that a term was coined to describe the fallout: regional depression.

Youngstown was transformed not only by an economic disruption but also by a psychological and cultural breakdown. Depression, spousal abuse, and suicide all became much more prevalent; the caseload of the area's mental-health center tripled within a decade. The city built four prisons in the mid-1990s—a rare growth industry. One of the few downtown construction projects of that period was a museum dedicated to the defunct steel industry.

This winter, I traveled to Ohio to consider what would happen if technology permanently replaced a great deal of human work. I wasn't seeking a tour of our automated future. I went because Youngstown has become a national metaphor for the decline of labor, a place where the middle class of the 20th century has become a museum exhibit.

"Youngstown's story is America's story, because it shows that when jobs go away, the cultural cohesion of a place is destroyed," says John Russo, a professor of labor studies at Youngstown State University. "The cultural breakdown matters even more than the economic breakdown."

In the past few years, even as the United States has pulled itself partway out of the jobs hole created by the Great Recession, some economists and technologists have warned that the economy is near a tipping point. When they peer deeply into labor-market data, they see troubling signs, masked for now by a cyclical recovery. And when they look up from their spreadsheets, they see automation high and low—robots in the operating room and behind the fast-food counter. They imagine self-driving cars snaking through the streets and Amazon drones dotting the sky, replacing millions of drivers, warehouse stockers, and retail workers. They observe that the capabilities of machines—already formidable—continue to expand exponentially, while our own remain the same. And they wonder: Is any job truly safe?

Futurists and science-fiction writers have at times looked forward to machines' workplace takeover with a kind of giddy excitement, imagining the banishment of drudgery and its replacement by expansive leisure and almost limitless personal freedom. And make no mistake: if the capabilities of computers continue to multiply while the price of computing continues to decline, that will mean a great many of life's necessities and luxuries will become ever cheaper, and it will mean great wealth—at least when aggregated up to the level of the national economy.

But even leaving aside questions of how to distribute that wealth, the widespread disappearance of work would usher in a social transformation unlike any we've seen. If John Russo is right, then saving work is more important than saving any particular job. Industriousness has served as America's unofficial religion since its founding. The sanctity and preeminence of work lie at the heart of the country's politics, economics, and social interactions. What might happen if work goes away?

The U.S. labor force has been shaped by millennia of technological progress. Agricultural technology birthed the farming industry, the industrial revolution moved people into factories, and then globalization and automation moved them back out, giving rise to a nation of services. But throughout these reshufflings, the total number of jobs has always increased. What may be looming is something different: an era of technological unemployment, in which computer scientists and software engineers essentially invent us out of work, and the total number of jobs declines steadily and permanently.

This fear is not new. The hope that machines might free us from toil has always been intertwined with the fear that they will rob us of our agency. In the midst of the Great Depression, the economist John Maynard Keynes forecast that technological progress might allow a 15-hour workweek, and abundant leisure, by 2030. But around the same time, President Herbert Hoover received a letter warning that industrial technology was a "Frankenstein monster" that threatened to upend manufacturing, "devouring our civilization." (The letter came from the mayor of Palo Alto, of all places.) In 1962, President John F. Kennedy said, "If men have the talent to invent new machines that put men out of work, they have the talent to put those men back to work." But two years later, a committee of scientists and social activists sent an open letter to President Lyndon B. Johnson arguing that "the cybernation revolution" would create "a separate nation of the poor, the unskilled, the jobless," who would be unable either to find work or to afford life's necessities.

The job market defied doomsayers in those earlier times, and according to the most frequently reported jobs numbers, it has so far done the same in our own time. Unemployment is currently just over 5 percent, and 2014 was this century's best year for job growth. One could be forgiven for saying that recent predictions about technological job displacement are merely forming the latest chapter in a long story called The Boys Who Cried Robot—one in which the robot, unlike the wolf, never arrives in the end.

The end-of-work argument has often been dismissed as the "Luddite fallacy," an allusion to the 19th-century British brutes who smashed textile-making machines at the dawn of the industrial revolution, fearing the machines would put hand-weavers out of work. But some of the most sober economists are beginning to worry that the Luddites weren't wrong, just premature. When former Treasury Secretary Lawrence Summers was an MIT undergraduate in the early 1970s, many economists disdained "the stupid people [who] thought that automation was going to make all the jobs go away," he said at the National Bureau of Economic Research Summer Institute in July 2013. "Until a few years ago, I didn't think this was a very complicated subject: the Luddites were wrong, and the believers in technology and technological progress were right. I'm not so completely certain now."

2. Reasons to Cry Robot

What does the "end of work" mean, exactly? It does not mean the imminence of total unemployment, nor is the United States remotely likely to face, say, 30 or 50 percent unemployment within the next decade. Rather, technology could exert a slow but continual downward pressure on the value and availability of work—that is, on wages and on the share of prime-age workers with full-time jobs. Eventually, by degrees, that could create a new normal, where the expectation that work will be a central feature of adult life dissipates for a significant portion of society.

After 300 years of people crying wolf, there are now three broad reasons to take seriously the argument that the beast is at the door: the ongoing triumph of capital over labor, the quiet demise of the working man, and the impressive dexterity of information technology.

• Labor's losses. One of the first things we might expect to see in a period of technological displacement is the diminishment of human labor as a driver of economic growth. In fact, signs that this is happening have been present for quite some time. The share of U.S. economic output that's paid out in wages fell steadily in the 1980s, reversed some of its losses in the '90s, and then continued falling after 2000, accelerating during the Great Recession. It now stands at its lowest level since the government started keeping track in the mid‑20th century.

A number of theories have been advanced to explain this phenomenon, including globalization and its accompanying loss of bargaining power for some workers. But Loukas Karabarbounis and Brent Neiman, economists at the University of Chicago, have estimated that almost half of the decline is the result of businesses' replacing workers with computers and software. In 1964, the nation's most valuable company, AT&T, was worth $267 billion in today's dollars and employed 758,611 people. Today's telecommunications giant, Google, is worth $370 billion but has only about 55,000 employees—less than a tenth the size of AT&T's workforce in its heyday.

• The spread of nonworking men and underemployed youth. The share of prime-age Americans (25 to 54 years old) who are working has been trending down since 2000. Among men, the decline began even earlier: the share of prime-age men who are neither working nor looking for work has doubled since the late 1970s, and has increased as much throughout the recovery as it did during the Great Recession itself. All in all, about one in six prime-age men today are either unemployed or out of the workforce altogether. This is what the economist Tyler Cowen calls "the key statistic" for understanding the spreading rot in the American workforce. Conventional wisdom has long held that under normal economic conditions, men in this age group—at the peak of their abilities and less likely than women to be primary caregivers for children—should almost all be working. Yet fewer and fewer are.

Economists cannot say for certain why men are turning away from work, but one explanation is that technological change has helped eliminate the jobs for which many are best suited. Since 2000, the number of manufacturing jobs has fallen by almost 5 million, or about 30 percent.

Young people just coming onto the job market are also struggling—and by many measures have been for years. Six years into the recovery, the share of recent college grads who are "underemployed" (in jobs that historically haven't required a degree) is still higher than it was in 2007—or, for that matter, 2000. And the supply of these "non-college jobs" is shifting away from high-paying occupations, such as electrician, toward low-wage service jobs, such as waiter. More people are pursuing higher education, but the real wages of recent college graduates have fallen by 7.7 percent since 2000. In the biggest picture, the job market appears to be requiring more and more preparation for a lower and lower starting wage. The distorting effect of the Great Recession should make us cautious about overinterpreting these trends, but most began before the recession, and they do not seem to speak encouragingly about the future of work.

• The shrewdness of software. One common objection to the idea that technology will permanently displace huge numbers of workers is that new gadgets, like self-checkout kiosks at drugstores, have failed to fully displace their human counterparts, like cashiers. But employers typically take years to embrace new machines at the expense of workers. The robotics revolution began in factories in the 1960s and '70s, but manufacturing employment kept rising until 1980, and then collapsed during the subsequent recessions. Likewise, "the personal computer existed in the '80s," says Henry Siu, an economist at the University of British Columbia, "but you don't see any effect on office and administrative-support jobs until the 1990s, and then suddenly, in the last recession, it's huge. So today you've got checkout screens and the promise of driverless cars, flying drones, and little warehouse robots. We know that these tasks can be done by machines rather than people. But we may not see the effect until the next recession, or the recession after that."

Some observers say our humanity is a moat that machines cannot cross. They believe people's capacity for compassion, deep understanding, and creativity are inimitable. But as Erik Brynjolfsson and Andrew McAfee have argued in their book The Second Machine Age, computers are so dexterous that predicting their application 10 years from now is almost impossible. Who could have guessed in 2005, two years before the iPhone was released, that smartphones would threaten hotel jobs within the decade, by helping homeowners rent out their apartments and houses to strangers on Airbnb? Or that the company behind the most popular search engine would design a self-driving car that could soon threaten driving, the most common job occupation among American men?

In 2013, Oxford University researchers forecast that machines might be able to perform half of all U.S. jobs in the next two decades. The projection was audacious, but in at least a few cases, it probably didn't go far enough. For example, the authors named psychologist as one of the occupations least likely to be "computerisable." But some research suggests that people are more honest in therapy sessions when they believe they are confessing their troubles to a computer, because a machine can't pass moral judgment. Google and WebMD already may be answering questions once reserved for one's therapist. This doesn't prove that psychologists are going the way of the textile worker. Rather, it shows how easily computers can encroach on areas previously considered "for humans only."

After 300 years of breathtaking innovation, people aren't massively unemployed or indentured by machines. But to suggest how this could change, some economists have pointed to the defunct career of the second-most-important species in U.S. economic history: the horse.

For many centuries, people created technologies that made the horse more productive and more valuable—like plows for agriculture and swords for battle. One might have assumed that the continuing advance of complementary technologies would make the animal ever more essential to farming and fighting, historically perhaps the two most consequential human activities. Instead came inventions that made the horse obsolete—the tractor, the car, and the tank. After tractors rolled onto American farms in the early 20th century, the population of horses and mules began to decline steeply, falling nearly 50 percent by the 1930s and 90 percent by the 1950s.

Humans can do much more than trot, carry, and pull. But the skills required in most offices hardly elicit our full range of intelligence. Most jobs are still boring, repetitive, and easily learned. The most-common occupations in the United States are retail salesperson, cashier, food and beverage server, and office clerk. Together, these four jobs employ 15.4 million people—nearly 10 percent of the labor force, or more workers than there are in Texas and Massachusetts combined. Each is highly susceptible to automation, according to the Oxford study.

Technology creates some jobs too, but the creative half of creative destruction is easily overstated. Nine out of 10 workers today are in occupations that existed 100 years ago, and just 5 percent of the jobs generated between 1993 and 2013 came from "high tech" sectors like computing, software, and telecommunications. Our newest industries tend to be the most labor-efficient: they just don't require many people. It is for precisely this reason that the economic historian Robert Skidelsky, comparing the exponential growth in computing power with the less-than-exponential growth in job complexity, has said, "Sooner or later, we will run out of jobs."

Is that certain—or certainly imminent? No. The signs so far are murky and suggestive. The most fundamental and wrenching job restructurings and contractions tend to happen during recessions: we'll know more after the next couple of downturns. But the possibility seems significant enough—and the consequences disruptive enough—that we owe it to ourselves to start thinking about what society could look like without universal work, in an effort to begin nudging it toward the better outcomes and away from the worse ones.

To paraphrase the science-fiction novelist William Gibson, there are, perhaps, fragments of the post-work future distributed throughout the present. I see three overlapping possibilities as formal employment opportunities decline. Some people displaced from the formal workforce will devote their freedom to simple leisure; some will seek to build productive communities outside the workplace; and others will fight, passionately and in many cases fruitlessly, to reclaim their productivity by piecing together jobs in an informal economy. These are futures of consumption, communal creativity, and contingency. In any combination, it is almost certain that the country would have to embrace a radical new role for government.

3. Consumption: The Paradox of Leisure

Work is really three things, says Peter Frase, the author of Four Futures, a forthcoming book about how automation will change America: the means by which the economy produces goods, the means by which people earn income, and an activity that lends meaning or purpose to many people's lives. "We tend to conflate these things," he told me, "because today we need to pay people to keep the lights on, so to speak. But in a future of abundance, you wouldn't, and we ought to think about ways to make it easier and better to not be employed."

Frase belongs to a small group of writers, academics, and economists—they have been called "post-workists"—who welcome, even root for, the end of labor. American society has "an irrational belief in work for work's sake," says Benjamin Hunnicutt, another post-workist and a historian at the University of Iowa, even though most jobs aren't so uplifting. A 2014 Gallup report of worker satisfaction found that as many as 70 percent of Americans don't feel engaged by their current job. Hunnicutt told me that if a cashier's work were a video game—grab an item, find the bar code, scan it, slide the item onward, and repeat—critics of video games might call it mindless. But when it's a job, politicians praise its intrinsic dignity. "Purpose, meaning, identity, fulfillment, creativity, autonomy—all these things that positive psychology has shown us to be necessary for well-being are absent in the average job," he said.

The post-workists are certainly right about some important things. Paid labor does not always map to social good. Raising children and caring for the sick is essential work, and these jobs are compensated poorly or not at all. In a post-work society, Hunnicutt said, people might spend more time caring for their families and neighbors; pride could come from our relationships rather than from our careers.

The post-work proponents acknowledge that, even in the best post-work scenarios, pride and jealousy will persevere, because reputation will always be scarce, even in an economy of abundance. But with the right government provisions, they believe, the end of wage labor will allow for a golden age of well-being. Hunnicutt said he thinks colleges could reemerge as cultural centers rather than job-prep institutions. The word school, he pointed out, comes from skholē, the Greek word for "leisure." "We used to teach people to be free," he said. "Now we teach them to work."

Hunnicutt's vision rests on certain assumptions about taxation and redistribution that might not be congenial to many Americans today. But even leaving that aside for the moment, this vision is problematic: it doesn't resemble the world as it is currently experienced by most jobless people. By and large, the jobless don't spend their downtime socializing with friends or taking up new hobbies. Instead, they watch TV or sleep. Time-use surveys show that jobless prime-age people dedicate some of the time once spent working to cleaning and childcare. But men in particular devote most of their free time to leisure, the lion's share of which is spent watching television, browsing the Internet, and sleeping. Retired seniors watch about 50 hours of television a week, according to Nielsen. That means they spend a majority of their lives either sleeping or sitting on the sofa looking at a flatscreen. The unemployed theoretically have the most time to socialize, and yet studies have shown that they feel the most social isolation; it is surprisingly hard to replace the camaraderie of the water cooler.

Most people want to work, and are miserable when they cannot. The ills of unemployment go well beyond the loss of income; people who lose their job are more likely to suffer from mental and physical ailments. "There is a loss of status, a general malaise and demoralization, which appears somatically or psychologically or both," says Ralph Catalano, a public-health professor at UC Berkeley. Research has shown that it is harder to recover from a long bout of joblessness than from losing a loved one or suffering a life-altering injury. The very things that help many people recover from other emotional traumas—a routine, an absorbing distraction, a daily purpose—are not readily available to the unemployed.

The transition from labor force to leisure force would likely be particularly hard on Americans, the worker bees of the rich world: Between 1950 and 2012, annual hours worked per worker fell significantly throughout Europe—by about 40 percent in Germany and the Netherlands—but by only 10 percent in the United States. Richer, college-educated Americans are working more than they did 30 years ago, particularly when you count time working and answering e-mail at home.

In 1989, the psychologists Mihaly Csikszentmihalyi and Judith LeFevre conducted a famous study of Chicago workers that found people at work often wished they were somewhere else. But in questionnaires, these same workers reported feeling better and less anxious in the office or at the plant than they did elsewhere. The two psychologists called this "the paradox of work": many people are happier complaining about jobs than they are luxuriating in too much leisure. Other researchers have used the term guilty couch potato to describe people who use media to relax but often feel worthless when they reflect on their unproductive downtime. Contentment speaks in the present tense, but something more—pride—comes only in reflection on past accomplishments.

The post-workists argue that Americans work so hard because their culture has conditioned them to feel guilty when they are not being productive, and that this guilt will fade as work ceases to be the norm. This might prove true, but it's an untestable hypothesis. When I asked Hunnicutt what sort of modern community most resembles his ideal of a post-work society, he admitted, "I'm not sure that such a place exists."

Less passive and more nourishing forms of mass leisure could develop. Arguably, they already are developing. The Internet, social media, and gaming offer entertainments that are as easy to slip into as is watching TV, but all are more purposeful and often less isolating. Video games, despite the derision aimed at them, are vehicles for achievement of a sort. Jeremy Bailenson, a communications professor at Stanford, says that as virtual-reality technology improves, people's "cyber-existence" will become as rich and social as their "real" life. Games in which users climb "into another person's skin to embody his or her experiences firsthand" don't just let people live out vicarious fantasies, he has argued, but also "help you live as somebody else to teach you empathy and pro-social skills."

But it's hard to imagine that leisure could ever entirely fill the vacuum of accomplishment left by the demise of labor. Most people do need to achieve things through, yes, work to feel a lasting sense of purpose. To envision a future that offers more than minute-to-minute satisfaction, we have to imagine how millions of people might find meaningful work without formal wages. So, inspired by the predictions of one of America's most famous labor economists, I took a detour on my way to Youngstown and stopped in Columbus, Ohio.

4. Communal Creativity: The Artisans' Revenge

Artisans made up the original American middle class. Before industrialization swept through the U.S. economy, many people who didn't work on farms were silversmiths, blacksmiths, or woodworkers. These artisans were ground up by the machinery of mass production in the 20th century. But Lawrence Katz, a labor economist at Harvard, sees the next wave of automation returning us to an age of craftsmanship and artistry. In particular, he looks forward to the ramifications of 3‑D printing, whereby machines construct complex objects from digital designs.

The factories that arose more than a century ago "could make Model Ts and forks and knives and mugs and glasses in a standardized, cheap way, and that drove the artisans out of business," Katz told me. "But what if the new tech, like 3-D-printing machines, can do customized things that are almost as cheap? It's possible that information technology and robots eliminate traditional jobs and make possible a new artisanal economy ... an economy geared around self-expression, where people would do artistic things with their time."

In other words, it would be a future not of consumption but of creativity, as technology returns the tools of the assembly line to individuals, democratizing the means of mass production.

Something like this future is already present in the small but growing number of industrial shops called "makerspaces" that have popped up in the United States and around the world. The Columbus Idea Foundry is the country's largest such space, a cavernous converted shoe factory stocked with industrial-age machinery. Several hundred members pay a monthly fee to use its arsenal of machines to make gifts and jewelry; weld, finish, and paint; play with plasma cutters and work an angle grinder; or operate a lathe with a machinist.

When I arrived there on a bitterly cold afternoon in February, a chalkboard standing on an easel by the door displayed three arrows, pointing toward bathrooms, pewter casting, and zombies. Near the entrance, three men with black fingertips and grease-stained shirts took turns fixing a 60-year-old metal-turning lathe. Behind them, a resident artist was tutoring an older woman on how to transfer her photographs onto a large canvas, while a couple of guys fed pizza pies into a propane-fired stone oven. Elsewhere, men in protective goggles welded a sign for a local chicken restaurant, while others punched codes into a computer-controlled laser-cutting machine. Beneath the din of drilling and wood-cutting, a Pandora rock station hummed tinnily from a Wi‑Fi-connected Edison phonograph horn. The foundry is not just a gymnasium of tools. It is a social center.

Alex Bandar, who started the foundry after receiving a doctorate in materials science and engineering, has a theory about the rhythms of invention in American history. Over the past century, he told me, the economy has moved from hardware to software, from atoms to bits, and people have spent more time at work in front of screens. But as computers take over more tasks previously considered the province of humans, the pendulum will swing back from bits to atoms, at least when it comes to how people spend their days. Bandar thinks that a digitally preoccupied society will come to appreciate the pure and distinct pleasure of making things you can touch. "I've always wanted to usher in a new era of technology where robots do our bidding," Bandar said. "If you have better batteries, better robotics, more dexterous manipulation, then it's not a far stretch to say robots do most of the work. So what do we do? Play? Draw? Actually talk to each other again?"

You don't need any particular fondness for plasma cutters to see the beauty of an economy where tens of millions of people make things they enjoy making—whether physical or digital, in buildings or in online communities—and receive feedback and appreciation for their work. The Internet and the cheap availability of artistic tools have already empowered millions of people to produce culture from their living rooms. People upload more than 400,000 hours of YouTube videos and 350 million new Facebook photos every day. The demise of the formal economy could free many would-be artists, writers, and craftspeople to dedicate their time to creative interests—to live as cultural producers. Such activities offer virtues that many organizational psychologists consider central to satisfaction at work: independence, the chance to develop mastery, and a sense of purpose.

After touring the foundry, I sat at a long table with several members, sharing the pizza that had come out of the communal oven. I asked them what they thought of their organization as a model for a future where automation reached further into the formal economy. A mixed-media artist named Kate Morgan said that most people she knew at the foundry would quit their jobs and use the foundry to start their own business if they could. Others spoke about the fundamental need to witness the outcome of one's work, which was satisfied more deeply by craftsmanship than by other jobs they'd held.

Late in the conversation, we were joined by Terry Griner, an engineer who had built miniature steam engines in his garage before Bandar invited him to join the foundry. His fingers were covered in soot, and he told me about the pride he had in his ability to fix things. "I've been working since I was 16. I've done food service, restaurant work, hospital work, and computer programming. I've done a lot of different jobs," said Griner, who is now a divorced father. "But if we had a society that said, 'We'll cover your essentials, you can work in the shop,' I think that would be utopia. That, to me, would be the best of all possible worlds."

5. Contingency: "You're on Your Own"

One mile to the east of downtown Youngstown, in a brick building surrounded by several empty lots, is Royal Oaks, an iconic blue-collar dive. At about 5:30 p.m. on a Wednesday, the place was nearly full. The bar glowed yellow and green from the lights mounted along a wall. Old beer signs, trophies, masks, and mannequins cluttered the back corner of the main room, like party leftovers stuffed in an attic. The scene was mostly middle-aged men, some in groups, talking loudly about baseball and smelling vaguely of pot; some drank alone at the bar, sitting quietly or listening to music on headphones. I spoke with several patrons there who work as musicians, artists, or handymen; many did not hold a steady job.

"It is the end of a particular kind of wage work," said Hannah Woodroofe, a bartender there who, it turns out, is also a graduate student at the University of Chicago. (She's writing a dissertation on Youngstown as a harbinger of the future of work.) A lot of people in the city make ends meet via "post-wage arrangements," she said, working for tenancy or under the table, or trading services. Places like Royal Oaks are the new union halls: People go there not only to relax but also to find tradespeople for particular jobs, like auto repair. Others go to exchange fresh vegetables, grown in urban gardens they've created amid Youngstown's vacant lots.

When an entire area, like Youngstown, suffers from high and prolonged unemployment, problems caused by unemployment move beyond the personal sphere; widespread joblessness shatters neighborhoods and leaches away their civic spirit. John Russo, the Youngstown State professor, who is a co-author of a history of the city, Steeltown USA, says the local identity took a savage blow when residents lost the ability to find reliable employment. "I can't stress this enough: this isn't just about economics; it's psychological," he told me.

Russo sees Youngstown as the leading edge of a larger trend toward the development of what he calls the "precariat"—a working class that swings from task to task in order to make ends meet and suffers a loss of labor rights, bargaining rights, and job security. In Youngstown, many of these workers have by now made their peace with insecurity and poverty by building an identity, and some measure of pride, around contingency. The faith they lost in institutions—the corporations that have abandoned the city, the police who have failed to keep them safe—has not returned. But Russo and Woodroofe both told me they put stock in their own independence. And so a place that once defined itself single-mindedly by the steel its residents made has gradually learned to embrace the valorization of well-rounded resourcefulness.

Karen Schubert, a 54-year-old writer with two master's degrees, accepted a part-time job as a hostess at a café in Youngstown early this year, after spending months searching for full-time work. Schubert, who has two grown children and an infant grandson, said she'd loved teaching writing and literature at the local university. But many colleges have replaced full-time professors with part-time adjuncts in order to control costs, and she'd found that with the hours she could get, adjunct teaching didn't pay a living wage, so she'd stopped. "I think I would feel like a personal failure if I didn't know that so many Americans have their leg caught in the same trap," she said.

Among Youngstown's precariat, one can see a third possible future, where millions of people struggle for years to build a sense of purpose in the absence of formal jobs, and where entrepreneurship emerges out of necessity. But while it lacks the comforts of the consumption economy or the cultural richness of Lawrence Katz's artisanal future, it is more complex than an outright dystopia. "There are young people working part-time in the new economy who feel independent, whose work and personal relationships are contingent, and say they like it like this—to have short hours so they have time to focus on their passions," Russo said.

Schubert's wages at the café are not enough to live on, and in her spare time, she sells books of her poetry at readings and organizes gatherings of the literary-arts community in Youngstown, where other writers (many of them also underemployed) share their prose. The evaporation of work has deepened the local arts and music scene, several residents told me, because people who are inclined toward the arts have so much time to spend with one another. "We're a devastatingly poor and hemorrhaging population, but the people who live here are fearless and creative and phenomenal," Schubert said.

Whether or not one has artistic ambitions as Schubert does, it is arguably growing easier to find short-term gigs or spot employment. Paradoxically, technology is the reason. A constellation of Internet-enabled companies matches available workers with quick jobs, most prominently including Uber (for drivers), Seamless (for meal deliverers), Homejoy (for house cleaners), and TaskRabbit (for just about anyone else). And online markets like Craigslist and eBay have likewise made it easier for people to take on small independent projects, such as furniture refurbishing. Although the on-demand economy is not yet a major part of the employment picture, the number of "temporary-help services" workers has grown by 50 percent since 2010, according to the Bureau of Labor Statistics.

Some of these services, too, could be usurped, eventually, by machines. But on-demand apps also spread the work around by carving up jobs, like driving a taxi, into hundreds of little tasks, like a single drive, which allows more people to compete for smaller pieces of work. These new arrangements are already challenging the legal definitions of employer and employee, and there are many reasons to be ambivalent about them. But if the future involves a declining number of full-time jobs, as in Youngstown, then splitting some of the remaining work up among many part-time workers, instead of a few full-timers, wouldn't necessarily be a bad development. We shouldn't be too quick to excoriate companies that let people combine their work, art, and leisure in whatever ways they choose.

Today the norm is to think about employment and unemployment as a black-and-white binary, rather than two points at opposite ends of a wide spectrum of working arrangements. As late as the mid-19th century, though, the modern concept of "unemployment" didn't exist in the United States. Most people lived on farms, and while paid work came and went, home industry—canning, sewing, carpentry—was a constant. Even in the worst economic panics, people typically found productive things to do. The despondency and helplessness of unemployment were discovered, to the bafflement and dismay of cultural critics, only after factory work became dominant and cities swelled.

The 21st century, if it presents fewer full-time jobs in the sectors that can be automated, could in this respect come to resemble the mid-19th century: an economy marked by episodic work across a range of activities, the loss of any one of which would not make somebody suddenly idle. Many bristle that contingent gigs offer a devil's bargain—a bit of additional autonomy in exchange for a larger loss of security. But some might thrive in a market where versatility and hustle are rewarded—where there are, as in Youngstown, few jobs to have, yet many things to do.

6. Government: The Visible Hand

In the 1950s, Henry Ford II, the CEO of Ford, and Walter Reuther, the head of the United Auto Workers union, were touring a new engine plant in Cleveland. Ford gestured to a fleet of machines and said, "Walter, how are you going to get these robots to pay union dues?" The union boss famously replied: "Henry, how are you going to get them to buy your cars?"

As Martin Ford (no relation) writes in his new book, The Rise of the Robots, this story might be apocryphal, but its message is instructive. We're pretty good at noticing the immediate effects of technology's substituting for workers, such as fewer people on the factory floor. What's harder is anticipating the second-order effects of this transformation, such as what happens to the consumer economy when you take away the consumers.

Technological progress on the scale we're imagining would usher in social and cultural changes that are almost impossible to fully envision. Consider just how fundamentally work has shaped America's geography. Today's coastal cities are a jumble of office buildings and residential space. Both are expensive and tightly constrained. But the decline of work would make many office buildings unnecessary. What might that mean for the vibrancy of urban areas? Would office space yield seamlessly to apartments, allowing more people to live more affordably in city centers and leaving the cities themselves just as lively? Or would we see vacant shells and spreading blight? Would big cities make sense at all if their role as highly sophisticated labor ecosystems were diminished? As the 40-hour workweek faded, the idea of a lengthy twice-daily commute would almost certainly strike future generations as an antiquated and baffling waste of time. But would those generations prefer to live on streets full of high-rises, or in smaller towns?

Today, many working parents worry that they spend too many hours at the office. As full-time work declined, rearing children could become less overwhelming. And because job opportunities historically have spurred migration in the United States, we might see less of it; the diaspora of extended families could give way to more closely knitted clans. But if men and women lost their purpose and dignity as work went away, those families would nonetheless be troubled.

The decline of the labor force would make our politics more contentious. Deciding how to tax profits and distribute income could become the most significant economic-policy debate in American history. In The Wealth of Nations, Adam Smith used the term invisible hand to refer to the order and social benefits that arise, surprisingly, from individuals' selfish actions. But to preserve the consumer economy and the social fabric, governments might have to embrace what Haruhiko Kuroda, the governor of the Bank of Japan, has called the visible hand of economic intervention. What follows is an early sketch of how it all might work.

In the near term, local governments might do well to create more and more-ambitious community centers or other public spaces where residents can meet, learn skills, bond around sports or crafts, and socialize. Two of the most common side effects of unemployment are loneliness, on the individual level, and the hollowing-out of community pride. A national policy that directed money toward centers in distressed areas might remedy the maladies of idleness, and form the beginnings of a long-term experiment on how to reengage people in their neighborhoods in the absence of full employment.

We could also make it easier for people to start their own, small-scale (and even part-time) businesses. New-business formation has declined in the past few decades in all 50 states. One way to nurture fledgling ideas would be to build out a network of business incubators. Here Youngstown offers an unexpected model: its business incubator has been recognized internationally, and its success has brought new hope to West Federal Street, the city's main drag.

Near the beginning of any broad decline in job availability, the United States might take a lesson from Germany on job-sharing. The German government gives firms incentives to cut all their workers' hours rather than lay off some of them during hard times. So a company with 50 workers that might otherwise lay off 10 people instead reduces everyone's hours by 20 percent. Such a policy would help workers at established firms keep their attachment to the labor force despite the declining amount of overall labor.

Spreading work in this way has its limits. Some jobs can't be easily shared, and in any case, sharing jobs wouldn't stop labor's pie from shrinking: it would only apportion the slices differently. Eventually, Washington would have to somehow spread wealth, too.

One way of doing that would be to more heavily tax the growing share of income going to the owners of capital, and use the money to cut checks to all adults. This idea—called a "universal basic income"—has received bipartisan support in the past. Many liberals currently support it, and in the 1960s, Richard Nixon and the conservative economist Milton Friedman each proposed a version of the idea. That history notwithstanding, the politics of universal income in a world without universal work would be daunting. The rich could say, with some accuracy, that their hard work was subsidizing the idleness of millions of "takers." What's more, although a universal income might replace lost wages, it would do little to preserve the social benefits of work.

The most direct solution to the latter problem would be for the government to pay people to do something, rather than nothing. Although this smacks of old European socialism, or Depression-era "makework," it might do the most to preserve virtues such as responsibility, agency, and industriousness. In the 1930s, the Works Progress Administration did more than rebuild the nation's infrastructure. It hired 40,000 artists and other cultural workers to produce music and theater, murals and paintings, state and regional travel guides, and surveys of state records. It's not impossible to imagine something like the WPA—or an effort even more capacious—for a post-work future.

What might that look like? Several national projects might justify direct hiring, such as caring for a rising population of elderly people. But if the balance of work continues to shift toward the small-bore and episodic, the simplest way to help everybody stay busy might be government sponsorship of a national online marketplace of work (or, alternatively, a series of local ones, sponsored by local governments). Individuals could browse for large long-term projects, like cleaning up after a natural disaster, or small short-term ones: an hour of tutoring, an evening of entertainment, an art commission. The requests could come from local governments or community associations or nonprofit groups; from rich families seeking nannies or tutors; or from other individuals given some number of credits to "spend" on the site each year. To ensure a baseline level of attachment to the workforce, the government could pay adults a flat rate in return for some minimum level of activity on the site, but people could always earn more by taking on more gigs.

Although a digital WPA might strike some people as a strange anachronism, it would be similar to a federalized version of Mechanical Turk, the popular Amazon sister site where individuals and companies post projects of varying complexity, while so-called Turks on the other end browse tasks and collect money for the ones they complete. Mechanical Turk was designed to list tasks that cannot be performed by a computer. (The name is an allusion to an 18th-century Austrian hoax, in which a famous automaton that seemed to play masterful chess concealed a human player who chose the moves and moved the pieces.)

A government marketplace might likewise specialize in those tasks that required empathy, humanity, or a personal touch. By connecting millions of people in one central hub, it might even inspire what the technology writer Robin Sloan has called "a Cambrian explosion of mega-scale creative and intellectual pursuits, a generation of Wikipedia-scale projects that can ask their users for even deeper commitments."
Adam Levey

There's a case to be made for using the tools of government to provide other incentives as well, to help people avoid the typical traps of joblessness and build rich lives and vibrant communities. After all, the members of the Columbus Idea Foundry probably weren't born with an innate love of lathe operation or laser-cutting. Mastering these skills requires discipline; discipline requires an education; and an education, for many people, involves the expectation that hours of often frustrating practice will eventually prove rewarding. In a post-work society, the financial rewards of education and training won't be as obvious. This is a singular challenge of imagining a flourishing post-work society: How will people discover their talents, or the rewards that come from expertise, if they don't see much incentive to develop either?

Modest payments to young people for attending and completing college, skills-training programs, or community-center workshops might eventually be worth considering. This seems radical, but the aim would be conservative—to preserve the status quo of an educated and engaged society. Whatever their career opportunities, young people will still grow up to be citizens, neighbors, and even, episodically, workers. Nudges toward education and training might be particularly beneficial to men, who are more likely to withdraw into their living rooms when they become unemployed.

7. Jobs and Callings

Decades from now, perhaps the 20th century will strike future historians as an aberration, with its religious devotion to overwork in a time of prosperity, its attenuations of family in service to job opportunity, its conflation of income with self-worth. The post-work society I've described holds a warped mirror up to today's economy, but in many ways it reflects the forgotten norms of the mid-19th century—the artisan middle class, the primacy of local communities, and the unfamiliarity with widespread joblessness.

The three potential futures of consumption, communal creativity, and contingency are not separate paths branching out from the present. They're likely to intertwine and even influence one another. Entertainment will surely become more immersive and exert a gravitational pull on people without much to do. But if that's all that happens, society will have failed. The foundry in Columbus shows how the "third places" in people's lives (communities separate from their homes and offices) could become central to growing up, learning new skills, discovering passions. And with or without such places, many people will need to embrace the resourcefulness learned over time by cities like Youngstown, which, even if they seem like museum exhibits of an old economy, might foretell the future for many more cities in the next 25 years.

On my last day in Youngstown, I met with Howard Jesko, a 60-year-old Youngstown State graduate student, at a burger joint along the main street. A few months after Black Friday in 1977, as a senior at Ohio State University, Jesko received a phone call from his father, a specialty-hose manufacturer near Youngstown. "Don't bother coming back here for a job," his dad said. "There aren't going to be any left." Years later, Jesko returned to Youngstown to work, but he recently quit his job selling products like waterproofing systems to construction companies; his customers had been devastated by the Great Recession and weren't buying much anymore. Around the same time, a left-knee replacement due to degenerative arthritis resulted in a 10-day hospital stay, which gave him time to think about the future. Jesko decided to go back to school to become a professor. "My true calling," he told me, "has always been to teach."

One theory of work holds that people tend to see themselves in jobs, careers, or callings. Individuals who say their work is "just a job" emphasize that they are working for money rather than aligning themselves with any higher purpose. Those with pure careerist ambitions are focused not only on income but also on the status that comes with promotions and the growing renown of their peers. But one pursues a calling not only for pay or status, but also for the intrinsic fulfillment of the work itself.

When I think about the role that work plays in people's self-esteem—particularly in America—the prospect of a no-work future seems hopeless. There is no universal basic income that can prevent the civic ruin of a country built on a handful of workers permanently subsidizing the idleness of tens of millions of people. But a future of less work still holds a glint of hope, because the necessity of salaried jobs now prevents so many from seeking immersive activities that they enjoy.

After my conversation with Jesko, I walked back to my car to drive out of Youngstown. I thought about Jesko's life as it might have been had Youngstown's steel mills never given way to a steel museum—had the city continued to provide stable, predictable careers to its residents. If Jesko had taken a job in the steel industry, he might be preparing for retirement today. Instead, that industry collapsed and then, years later, another recession struck. The outcome of this cumulative grief is that Howard Jesko is not retiring at 60. He's getting his master's degree to become a teacher. It took the loss of so many jobs to force him to pursue the work he always wanted to do.

Quote from: The Minsky Moment on June 28, 2015, 01:37:10 PM
Didn't vote.  Can't rationally vote in the absence of a actual phenomenon.

QuoteThroughout the developed world the key post-GR economic trend is declining productivity and unemployment.  I.e. the opposite of one would expect to see if automation was displacing vast swaths of the work force.

Quote from: LaCroix on June 28, 2015, 02:27:01 PM
this scenario will never happen. just like malthusian theory and all the others.

Quote from: jimmy olsen on June 28, 2015, 05:39:02 PMThe reason why the malthusian outcome will not occur, the continued advancement of technology, is the reason this scenario will occur.

Quote from: jimmy olsen on June 28, 2015, 05:39:02 PM

Quote from: LaCroix on June 28, 2015, 02:27:01 PM
this scenario will never happen. just like malthusian theory and all the others.

The reason why the malthusian outcome will not occur, the continued advancement of technology, is the reason this scenario will occur.

Quote from: Razgovory on June 28, 2015, 06:31:28 PM
Except it never has in the history of mankind.

Quote from: Admiral Yi on June 28, 2015, 06:52:21 PM

Quote from: Razgovory on June 28, 2015, 06:31:28 PM
Except it never has in the history of mankind.

Perhaps that's because this is the first time in history that machines are being produced that can think.

Quote from: Razgovory on June 28, 2015, 06:56:27 PM
No, the Malthusian thing. Also computers will never think.

Quote from: Razgovory on June 28, 2015, 06:56:27 PM
Also computers will never think.

Quote from: Admiral Yi on June 28, 2015, 02:09:29 PM

Quote from: The Minsky Moment on June 28, 2015, 01:37:10 PM
Didn't vote.  Can't rationally vote in the absence of a actual phenomenon.

I don't see why not.

QuoteThe article makes the point that capital tends to replace labor more during recessions.

Quote from: Ideologue on June 28, 2015, 06:04:18 PM
See, this is why I'm glad I didn't go to a better law school, because apparently in the T1 they gouge out your fucking eyes.

Quote from: The Minsky Moment on June 28, 2015, 01:37:10 PM
Didn't vote.  Can't rationally vote in the absence of a actual phenomenon.

Throughout the developed world the key post-GR economic trend is declining productivity and unemployment.  I.e. the opposite of one would expect to see if automation was displacing vast swaths of the work force.  As for the three reasons:


• "Labor's losses"- this was the key takeaway of Piketty's book.  The share going to capital is not historically unusual. The outlier was the relatively low capital share during the postwar Trente Glorieuses.

• "The spread of nonworking men and underemployed youth "- employment ratios are also not unusually low given demographics (the persistence of boomers) and the extension of benefits during the GR.  The article focuses on the decline in prime male employment rate, which it correctly dates back many decades. Of course, as women enter the workforce and men take on more caretaker roles one would expect convergence in employment rates by gender . . .

• "The shrewdness of software." More like the shrewdest of software companies, whose bug filled releases and planned obsolescence drive continued sales of "upgrades" and services.

Quote from: The Minsky Moment on June 28, 2015, 11:30:07 PM

Quote from: Ideologue on June 28, 2015, 06:04:18 PM
See, this is why I'm glad I didn't go to a better law school, because apparently in the T1 they gouge out your fucking eyes.

Data. Facts.  Evidence.
Everything else is cheap talk.

Quote from: jimmy olsen on June 29, 2015, 05:45:27 AM
Employment in every single cohort is down since 2000

Quote from: jimmy olsen on June 28, 2015, 05:39:02 PM

Quote from: LaCroix on June 28, 2015, 02:27:01 PM
this scenario will never happen. just like malthusian theory and all the others.

The reason why the malthusian outcome will not occur, the continued advancement of technology, is the reason this scenario will occur.

Quote from: Martinus on June 29, 2015, 06:22:32 AM
Minimum guaranteed income seems to be the most mainstream response from the today's left. Surprised it is not in the poll.

Quote from: jimmy olsen on June 29, 2015, 06:55:05 AM

Quote from: Martinus on June 29, 2015, 06:22:32 AM
Minimum guaranteed income seems to be the most mainstream response from the today's left. Surprised it is not in the poll.

That's basically what a negative income tax is.

Quote from: jimmy olsen on June 29, 2015, 06:55:05 AM

Quote from: Martinus on June 29, 2015, 06:22:32 AM
Minimum guaranteed income seems to be the most mainstream response from the today's left. Surprised it is not in the poll.

That's basically what a negative income tax is.

Quote from: The Brain on June 29, 2015, 06:27:08 AM
Btw, in South Africa they have robots everywhere. What's their experience?

Quote from: The Minsky Moment on June 28, 2015, 11:28:28 PM
Because circumstances matter.

QuoteIt can unless it doesn't.  But let's say it's true.  So?

Quote from: Tonitrus on June 29, 2015, 07:30:18 AM
We should all get started on that career in robot maintenance so that we can service our overlords.  :P

Quote from: Tonitrus on June 29, 2015, 07:30:18 AM
We should all get started on that career in robot maintenance so that we can service our overlords. :P

Quote from: crazy canuck on June 29, 2015, 11:10:23 AM
This poll needs a "the premise of the question is flawed" option.

Quote from: jimmy olsen on June 29, 2015, 01:18:46 AM
You may have a point with number one, however the data clearly shows to be wrong about number two. The percentage of women in the workforce peaked around 2000 and has declined from 59.9% to 57.7% since then. In that time the percentage of men in the workforce declined from 74.8% to 70.2%

QuoteThe third one is incredibly snarky dismissal of technology with no data to back it up.

Quote from: Admiral Yi on June 29, 2015, 07:23:41 AM

Quote from: The Minsky Moment on June 28, 2015, 11:28:28 PM
Because circumstances matter.

So do what the rest of us are doing: predict circumstances.

Quote from: Ideologue on June 29, 2015, 04:47:09 AM
The trouble with your commitment to arch-empiricism is that it'll take 50% U-3 unemployment for you to admit, "Oh, maybe I was wrong about automation."

Quote from: The Minsky Moment on June 29, 2015, 01:22:25 PM
I don't do fortune telling.

Quote from: Peter Wiggin on June 29, 2015, 01:26:19 PM
Predicting the status quo will hold is still a prediction.

Quote from: The Minsky Moment on June 29, 2015, 01:20:53 PM

Again - if low productivity workers are being systematically replaced by high performing technology, we shouldn't see declining productivity.

Quote from: jimmy olsen on June 29, 2015, 04:59:56 PM

Quote from: The Minsky Moment on June 29, 2015, 01:20:53 PM

Again - if low productivity workers are being systematically replaced by high performing technology, we shouldn't see declining productivity.

A machine doesn't have to be more productive than a person to replace them, just a reasonable facimile thereof and cheaper in the long run.

Quote from: Iormlund on June 30, 2015, 10:26:51 AM
Machines don't care about alcohol blood levels, toxicity or dangerous radiation exposure. They are remarkably accurate, consistent and fast. I've seen guys with over 25 years experience trying to weld the same parts our cells manufacture for Audi. It takes them hours to do so manually, while the robots can do it in only a few minutes and always get the same results.

Quote from: The Minsky Moment on June 30, 2015, 11:01:15 AM
Right. It's just a mathematical identity

If productivity is defined as Output/labor hours or output/worker, then any replacement of a human worker through automation should increase productivity even if the machine isn't so great.

Quote from: frunk on June 30, 2015, 11:08:38 AM
Assuming that any work done to design/build/maintain the automation is also considered output.

Quote from: Admiral Yi on June 30, 2015, 12:05:08 PM

Quote from: frunk on June 30, 2015, 11:08:38 AM
Assuming that any work done to design/build/maintain the automation is also considered output.

All output means all.

Quote from: frunk on June 30, 2015, 12:16:00 PM
Which means it isn't a particularly useful metric to measure whether automation is increasing or not.

Quote from: Admiral Yi on June 30, 2015, 10:49:19 AM
It seems some of you guys are misunderstanding Joan's point about productivity.  He's not talking about a productivity competition between humans and robots.  He's saying if robots were replacing humans then we would be seeing increases in human productivity, which we're not.

Quote from: Admiral Yi on June 30, 2015, 12:24:14 PM

Quote from: frunk on June 30, 2015, 12:16:00 PM
Which means it isn't a particularly useful metric to measure whether automation is increasing or not.

Yes it is.  Automation means the numerator (output) is increasing and the denominator (man hours) is decreasing.

Quote from: frunk on June 30, 2015, 12:29:53 PM
Let's say a robot replaces a highly skilled worker, does it slightly less well than the human worker but it's cheaper so it works out.  The human worker, in order to survive, is pushed to work a fast food job at minimum wage at the same number of hours.  The human worker's productivity has dropped through the floor, the robot isn't quite as good as the human before, so total productivity is about the same as before.

Automation has increased but it won't be reflected in the productivity numbers.

Quote from: The Minsky Moment on June 30, 2015, 12:44:29 PM
In your example, productivity would still increase uncles the decline in production from the robot is greater than the value of the Big Macs generated by the worker.

One can theoretically conceive of such a scenario and then extrapolate it economy wide but it doesn't seem like a very persuasive description of reality.

The phenomenon that the OP is talking about is not the replacement of workers by crappy, mediocre machines - it is the obsolescence of human labor by highly capable and sophisticated machines.  That is the phenomenon that isn't showing up in the data.

Quote from: Iormlund on June 30, 2015, 12:28:10 PM
Not necessarily, if you are transferring workers from already productive industries to others that are less so.

Quote from: The Minsky Moment on June 30, 2015, 12:44:29 PM
In your example, productivity would still increase uncles the decline in production from the robot is greater than the value of the Big Macs generated by the worker.

One can theoretically conceive of such a scenario and then extrapolate it economy wide but it doesn't seem like a very persuasive description of reality.

The phenomenon that the OP is talking about is not the replacement of workers by crappy, mediocre machines - it is the obsolescence of human labor by highly capable and sophisticated machines.  That is the phenomenon that isn't showing up in the data.

Quote
Tech
Aug 21 2015, 7:20 pm ET
Is It a Computer or Is It Bach? Program Fools Even Music Experts

by Devin Coldewey

A Yale computer scientist has developed a program that can create pieces of music close enough to baroque master Johann Sebastian Bach's work that people have trouble telling the two apart. "Kulitta," as creator Donya Quick calls it, learns from music provided for it to analyze, and creates new pieces on demand in a matter of seconds.

The resulting music is very similar to Bach's, but completely original — even experts were occasionally fooled, and in tests, over 100 students judged the pieces to be the work of a human.

Kulitta knows the ins and outs of every one of Bach's famous chorales, and applies the rules that govern that music to make new pieces. "You begin with an unlimited palette, and then apply different rules and decision-making strategies to filter it all down," explained Quick in a news release. "For something that would take at least a day for a human, Kulitta can do it in a few seconds or less."

That doesn't mean composers are doomed. Kulitta can only imitate what it already understands, and of course it doesn't really know a "good" piece from a "bad" one — but Quick thinks it could be just "another tool in the toolbox" for musicians. A Kulitta-generated piece might jolt a songwriter out of a rut, providing an endless source of ideas and inspiration.

Quick is experimenting with combining genres — adding jazz bits to classical, for instance — and her next big goal is to mash up Metallica with Mozart. "I'd like Kulitta to do a rock symphony," she said. "That's my pie-in-the-sky."

Quote from: MadImmortalMan on August 24, 2015, 05:32:06 PM
If you take the hypothetical assumption as true, and one of the poll options will be done (or something similar), then what should you do about it now? Accumulate land?

Quote from: The Minsky Moment on June 30, 2015, 01:54:37 PM

I am very open to any and all alternative evidence that there is a technological paradigm shift underway; just don't see it/haven't seen it

As for the argument that it isn't here now but will be sometime in the future, again I don't see the evidence that such a transition is close on the horizon.

Quote from: frunk on August 24, 2015, 08:52:59 PM
I think the real shift was the Industrial Revolution.  The switch from a primarily agrarian, season based to a machine "24/7/52 forever" work structure is pretty profound.  At that point machines become the ideal worker and the question is how to get humans to keep up with covering the parts that machines can't do yet.  Early on this entailed needing a lot of humans as the machines were primitive and almost always required intervention at various stages.  This early demand for human capital was good as it created an ever growing market for the new products being created.  Since then it's a matter of improving what machines can do, closing the gaps and reducing or eliminating the need for humans.  Running counter to that is that humans always need money, which generally means they need jobs, which means there's a floor that automation generally won't push past.  Humans will do it cheaper because the alternative is to starve, or even if it was automated the potential customers wouldn't exist because they wouldn't have the wealth to purchase it.

It comes down to a race between ever cheaper goods, and ever reduced need for human work input and the consequent reduction of purchasing power among the vast majority of the population.

QuoteTerrifyingly Convenient

A.I. assistants can give you the news, order you a pizza, and tell you a joke. All you have to do is trust them—completely.

By Will Oremus

It was a weeknight, after dinner, and the baby was in bed. My wife and I were alone—we thought—discussing the sorts of things you might discuss with your spouse and no one else. (Specifically, we were critiquing a friend's taste in romantic partners.) I was midsentence when, without warning, another woman's voice piped in from the next room. We froze.


"I HELD THE DOOR OPEN FOR A CLOWN THE OTHER DAY," the woman said in a loud, slow monotone. It took us a moment to realize that her voice was emanating from the black speaker on the kitchen table. We stared slack-jawed as she—it—continued: "I THOUGHT IT WAS A NICE JESTER."

"What. The hell. Was that," I said after a moment of stunned silence. Alexa, the voice assistant whose digital spirit animates the Amazon Echo, did not reply. She—it—responds only when called by name. Or so we had believed.

We pieced together what must have transpired. Somehow, Alexa's speech recognition software had mistakenly picked the word Alexa out of something we said, then chosen a phrase like "tell me a joke" as its best approximation of whatever words immediately followed. Through some confluence of human programming and algorithmic randomization, it chose a lame jester/gesture pun as its response.

In retrospect, the disruption was more humorous than sinister. But it was also a slightly unsettling reminder that Amazon's hit device works by listening to everything you say, all the time. And that, for all Alexa's human trappings—the name, the voice, the conversational interface—it's no more sentient than any other app or website. It's just code, built by some software engineers in Seattle with a cheesy sense of humor.


But the Echo's inadvertent intrusion into an intimate conversation is alo a harbinger of a more fundamental shift in the relationship between human and machine. Alexa—and Siri and Cortana and all of the other virtual assistants that now populate our computers, phones, and living rooms—are just beginning to insinuate themselves, sometimes stealthily, sometimes overtly, and sometimes a tad creepily, into the rhythms of our daily lives. As they grow smarter and more capable, they will routinely surprise us by making our lives easier, and we'll steadily become more reliant on them. Even as many of us continue to treat these bots as toys and novelties, they are on their way to becoming our primary gateways to all sorts of goods, services, and information, both public and personal. When that happens, the Echo won't just be a cylinder in your kitchen that sometimes tells bad jokes. Alexa and virtual agents like it will be the prisms through which we interact with the online world. It's a job to which they will necessarily bring a set of biases and priorities, some subtler than others. Some of those biases and priorities will reflect our own. Others, almost certainly, will not. Those vested interests might help to explain why they seem so eager to become our friends.

* * *

In the beginning, computers spoke only computer language, and a human seeking to interact with one was compelled to do the same. First came punch cards, then typed commands such as run, print, and dir. The 1980s brought the mouse click and the graphical user interface to the masses; the 2000s, touch screens; the 2010s, gesture control and voice. It has all been leading, gradually and imperceptibly, to a world in which we no longer have to speak computer language, because computers will speak human language—not perfectly, but well enough to get by.

We aren't there yet. But we're closer than most people realize. And the implications—many of them exciting, some of them ominous—will be tremendous.

Like card catalogs and AOL-style portals before it, Web search will begin to fade from prominence, and with it the dominance of browsers and search engines. Mobile apps as we know them—icons on a home screen that you tap to open—will start to do the same. In their place will rise an array of virtual assistants, bots, and software agents that act more and more like people: not only answering our queries, but acting as our proxies, accomplishing tasks for us, and asking questions of us in return.

This is already beginning to happen—and it isn't just Siri or Alexa. As of April, all five of the world's dominant technology companies are vying to be the Google of the conversation age. Whoever wins has a chance to get to know us more intimately than any company or machine has before—and to exert even more influence over our choices, purchases, and reading habits than they already do.

So say goodbye to Web browsers and mobile home screens as our default portals to the Internet. And say hello to the new wave of intelligent assistants, virtual agents, and software bots that are rising to take their place.

No, really, say "hello" to them. Apple's Siri, Google's mobile search app, Amazon's Alexa, Microsoft's Cortana, and Facebook's M, to name just five of the most notable, are diverse in their approaches, capabilities, and underlying technologies. But, with one exception, they've all been programmed to respond to basic salutations in one way or another, and it's a good way to start to get a sense of their respective mannerisms. You might even be tempted to say they have different personalities.

Siri's response to "hello" varies, but it's typically chatty and familiar:

Alexa is all business:

160331_CS_alexaSS

Google is a bit of an idiot savant: It responds by pulling up a YouTube video of the song "Hello" by Adele, along with all the lyrics.

160331_CS_googleScreen

Cortana isn't interested in saying anything until you've handed her the keys to your life:

160331_CS_cortanaTrio

Once those formalities are out of the way, she's all solicitude:

160331_CS_cortanaScreen

Then there's Facebook M, an experimental bot, available so far only to an exclusive group of Bay Area beta-testers, that lives inside Facebook Messenger and promises to answer almost any question and fulfill almost any (legal) request. If the casual, what's-up-BFF tone of its text messages rings eerily human, that's because it is: M is powered by an uncanny pairing of artificial intelligence and anonymous human agents.

160331_CS_mScreen

You might notice that most of these virtual assistants have female-sounding names and voices. Facebook M doesn't have a voice—it's text-only—but it was initially rumored to be called Moneypenny, a reference to a secretary from the James Bond franchise. And even Google's voice is female by default. This is, to some extent, a reflection of societal sexism. But these bots' apparent embrace of gender also highlights their aspiration to be anthropomorphized: They want—that is, the engineers that build them want—to interact with you like a person, not a machine. It seems to be working: Already people tend to refer to Siri, Alexa, and Cortana as "she," not "it."

That Silicon Valley's largest tech companies have effectively humanized their software in this way, with little fanfare and scant resistance, represents a coup of sorts. Once we perceive a virtual assistant as human, or at least humanoid, it becomes an entity with which we can establish humanlike relations. We can like it, banter with it, even turn to it for companionship when we're lonely. When it errs or betrays us, we can get angry with it and, ultimately, forgive it. What's most important, from the perspective of the companies behind this technology, is that we trust it.

Should we?

* * *

Siri wasn't the first digital voice assistant when Apple introduced it in 2011, and it may not have been the best. But it was the first to show us what might be possible: a computer that you talk to like a person, that talks back, and that attempts to do what you ask of it without requiring any further action on your part. Adam Cheyer, co-founder of the startup that built Siri and sold it to Apple in 2010, has said he initially conceived of it not as a search engine, but as a "do engine."

If Siri gave us a glimpse of what is possible, it also inadvertently taught us about what wasn't yet. At first, it often struggled to understand you, especially if you spoke into your iPhone with an accent, and it routinely blundered attempts to carry out your will. Its quick-witted rejoinders to select queries ("Siri, talk dirty to me") raised expectations for its intelligence that were promptly dashed once you asked it something it hadn't been hard-coded to answer. Its store of knowledge proved trivial compared with the vast information readily available via Google search. Siri was as much an inspiration as a disappointment.

Five years later, Siri has gotten smarter, if perhaps less so than one might have hoped. More importantly, the technology underlying it has drastically improved, fueled by a boom in the computer science subfield of machine learning. That has led to sharp improvements in speech recognition and natural language understanding, two separate but related technologies that are crucial to voice assistants.

If a revolution in technology has made intelligent virtual assistants possible, what has made them inevitable is a revolution in our relationship to technology. Computers began as tools of business and research, designed to automate tasks such as math and information retrieval. Today they're tools of personal communication, connecting us not only to information but to one another. They're also beginning to connect us to all the other technologies in our lives: Your smartphone can turn on your lights, start your car, activate your home security system, and withdraw money from your bank. As computers have grown deeply personal, our relationship with them has changed. And yet the way they interact with us hasn't quite caught up.

"It's always been sort of appalling to me that you now have a supercomputer in your pocket, yet you have to learn to use it," says Alan Packer, head of language technology at Facebook. "It seems actually like a failure on the part of our industry that software is hard to use."

Packer is one of the people trying to change that. As a software developer at Microsoft, he helped to build Cortana. After it launched, he found his skills in heavy demand, especially among the two tech giants that hadn't yet developed voice assistants of their own. One Thursday morning in December 2014, Packer was on the verge of accepting a top job at Amazon—"You would not be surprised at which team I was about to join," he says—when Facebook called and offered to fly him to Menlo Park, California, for an interview the next day. He had an inkling of what Amazon was working on, but he had no idea why Facebook might be interested in someone with his skill set.

As it turned out, Facebook wanted Packer for much the same purpose that Microsoft and Amazon did: to help it build software that could make sense of what its users were saying and generate intelligent responses. Facebook may not have a device like the Echo or an operating system like Windows, but its own platforms are full of billions of people communicating with one another every day. If Facebook can better understand what they're saying, it can further hone its News Feed and advertising algorithms, among other applications. More creatively, Facebook has begun to use language understanding to build artificial intelligence into its Messenger app. Now, if you're messaging with a friend and mention sharing an Uber, a software agent within Messenger can jump in and order it for you while you continue your conversation.

In short, Packer says, Facebook is working on language understanding because Facebook is a technology company—and that's where technology is headed. As if to underscore that point, Packer's former employer this year headlined its annual developer conference by announcing plans to turn Cortana into a portal for conversational bots and integrate it into Skype, Outlook, and other popular applications. Microsoft CEO Satya Nadella predicted that bots will be the Internet's next major platform, overtaking mobile apps the same way they eclipsed desktop computing.

* * *

Siri may not have been very practical, but people immediately grasped what it was. With Amazon's Echo, the second major tech gadget to put a voice interface front and center, it was the other way around. The company surprised the industry and baffled the public when it released a device in November 2014 that looked and acted like a speaker—except that it didn't connect to anything except a power outlet, and the only buttons were for power and mute. You control the Echo solely by voice, and if you ask it questions, it talks back. It was like Amazon had decided to put Siri in a black cylinder and sell it for $179. Except Alexa, the virtual intelligence software that powers the Echo, was far more limited than Siri in its capabilities. Who, reviewers wondered, would buy such a bizarre novelty gadget?

That question has faded as Amazon has gradually upgraded and refined the Alexa software, and the five-star Amazon reviews have since poured in. In the New York Times, Farhad Manjoo recently followed up his tepid initial review with an all-out rave: The Echo "brims with profound possibility," he wrote. Amazon has not disclosed sales figures, but the Echo ranks as the third-best-selling gadget in its electronics section. Alexa may not be as versatile as Siri—yet—but it turned out to have a distinct advantage: a sense of purpose, and of its own limitations. Whereas Apple implicitly invites iPhone users to ask Siri anything, Amazon ships the Echo with a little cheat sheet of basic queries that it knows how to respond to: "Alexa, what's the weather?" "Alexa, set a timer for 45 minutes." "Alexa, what's in the news?"

The cheat sheet's effect is to lower expectations to a level that even a relatively simplistic artificial intelligence can plausibly meet on a regular basis. That's by design, says Greg Hart, Amazon's vice president in charge of Echo and Alexa. Building a voice assistant that can respond to every possible query is "a really hard problem," he says. "People can get really turned off if they have an experience that's subpar or frustrating." So the company began by picking specific tasks that Alexa could handle with aplomb and communicating those clearly to customers.

At launch, the Echo had just 12 core capabilities. That list has grown steadily as the company has augmented Alexa's intelligence and added integrations with new services, such as Google Calendar, Yelp reviews, Pandora streaming radio, and even Domino's delivery. The Echo is also becoming a hub for connected home appliances: " 'Alexa, turn on the living room lights' never fails to delight people," Hart says.

When you ask Alexa a question it can't answer or say something it can't quite understand, it fesses up: "Sorry, I don't know the answer to that question." That makes it all the more charming when you test its knowledge or capabilities and it surprises you by replying confidently and correctly. "Alexa, what's a kinkajou?" I asked on a whim one evening, glancing up from my laptop while reading a news story about an elderly Florida woman who woke up one day with a kinkajou on her chest. Alexa didn't hesitate: "A kinkajou is a rainforest mammal of the family Procyonidae ... " Alexa then proceeded to list a number of other Procyonidae to which the kinkajou is closely related. "Alexa, that's enough," I said after a few moments, genuinely impressed. "Thank you," I added.

"You're welcome," Alexa replied, and I thought for a moment that she—it—sounded pleased.

As delightful as it can seem, the Echo's magic comes with some unusual downsides. In order to respond every time you say "Alexa," it has to be listening for the word at all times. Amazon says it only stores the commands that you say after you've said the word Alexa and discards the rest. Even so, the enormous amount of processing required to listen for a wake word 24/7 is reflected in the Echo's biggest limitation: It only works when it's plugged into a power outlet. (Amazon's newest smart speakers, the Echo Dot and the Tap, are more mobile, but one sacrifices the speaker and the other the ability to respond at any time.)

Even if you trust Amazon to rigorously protect and delete all of your personal conversations from its servers—as it promises it will if you ask it to—Alexa's anthropomorphic characteristics make it hard to shake the occasional sense that it's eavesdropping on you, Big Brother–style. I was alone in my kitchen one day, unabashedly belting out the Fats Domino song "Blueberry Hill" as I did the dishes, when it struck me that I wasn't alone after all. Alexa was listening—not judging, surely, but listening all the same. Sheepishly, I stopped singing.

* * *

The notion that the Echo is "creepy" or "spying on us" might be the most common criticism of the device so far. But there's a more fundamental problem. It's one that is likely to haunt voice assistants, and those who rely on them, as the technology evolves and bores it way more deeply into our lives.

The problem is that conversational interfaces don't lend themselves to the sort of open flow of information we've become accustomed to in the Google era. By necessity they limit our choices—because their function is to make choices on our behalf.

For example, a search for "news" on the Web will turn up a diverse and virtually endless array of possible sources, from Fox News to Yahoo News to CNN to Google News, which is itself a compendium of stories from other outlets. But ask the Echo, "What's in the news?" and by default it responds by serving up a clip of NPR News's latest hourly update, which it pulls from the streaming radio service TuneIn. Which is great—unless you don't happen to like NPR's approach to the news, or you prefer a streaming radio service other than TuneIn. You can change those defaults somewhere in the bowels of the Alexa app, but Alexa never volunteers that information. Most people will never even know it's an option. Amazon has made the choice for them.

And how does Amazon make that sort of choice? The Echo's cheat sheet doesn't tell you that, and the company couldn't give me a clear answer.

Alexa does take care to mention before delivering the news that it's pulling the briefing from NPR News and TuneIn. But that isn't always the case with other sorts of queries.

Let's go back to our friend the kinkajou. In my pre-Echo days, my curiosity about an exotic animal might have sent me to Google via my laptop or phone. Just as likely, I might have simply let the moment of curiosity pass and not bothered with a search. Looking something up on Google involves just enough steps to deter us from doing it in a surprising number of cases. One of the great virtues of voice technology is to lower that barrier to the point where it's essentially no trouble at all. Having an Echo in the room when you're struck by curiosity about kinkajous is like having a friend sitting next to you who happens to be a kinkajou expert. All you have to do is say your question out loud, and Alexa will supply the answer. You literally don't have to lift a finger.

That is voice technology's fundamental advantage over all the human-computer interfaces that have come before it: In many settings, including the home, the car, or on a wearable gadget, it's much easier and more natural than clicking, typing, or tapping. In the logic of today's consumer technology industry, that makes its ascendance in those realms all but inevitable.

But consider the difference between Googling something and asking a friendly voice assistant. When I Google "kinkajou," I get a list of websites, ranked according to an algorithm that takes into account all sorts of factors that correlate with relevance and authority. I choose the information source I prefer, then visit its website directly—an experience that could help to further shade or inform my impression of its trustworthiness. Ultimately, the answer does come not from Google, per se, but directly from some third-party authority, whose credibility I can evaluate as I wish.

A voice-based interface is different. The response comes one word at a time, one sentence at a time, one idea at a time. That makes it very easy to follow, especially for humans who have spent their whole lives interacting with one another in just this way. But it makes it very cumbersome to present multiple options for how to answer a given query. Imagine for a moment what it would sound like to read a whole Google search results page aloud, and you'll understand no one builds a voice interface that way.

That's why voice assistants tend to answer your question by drawing from a single source of their own choosing. Alexa's confident response to my kinkajou question, I later discovered, came directly from Wikipedia, which Amazon has apparently chosen as the default source for Alexa's answers to factual questions. The reasons seem fairly obvious: It's the world's most comprehensive encyclopedia, its information is free and public, and it's already digitized. What it's not, of course, is infallible. Yet Alexa's response to my question didn't begin with the words, "Well, according to Wikipedia ... " She—it—just launched into the answer, as if she (it) knew it off the top of her (its) head. If a human did that, we might call it plagiarism.

The sin here is not merely academic. By not consistently citing the sources of its answers, Alexa makes it difficult to evaluate their credibility. It also implicitly turns Alexa into an information source in its own right, rather than a guide to information sources, because the only entity in which we can place our trust or distrust is Alexa itself. That's a problem if its information source turns out to be wrong.

The constraints on choice and transparency might not bother people when Alexa's default source is Wikipedia, NPR, or TuneIn. It starts to get a little more irksome when you ask Alexa to play you music, one of the Echo's core features. "Alexa, play me the Rolling Stones" will queue up a shuffle playlist of Rolling Stones songs available through Amazon's own streaming music service, Amazon Prime Music—provided you're paying the $99 a year required to be an Amazon Prime member. Otherwise, the most you'll get out of the Echo are 20-second samples of songs available for purchase. Want to guess what one choice you'll have as to which online retail giant to purchase those songs from?

Amazon's response is that Alexa does give you options and cite its sources—in the Alexa app, which keeps a record of your queries and its responses. When the Echo tells you what a kinkajou is, you can open the app on your phone and see a link to the Wikipedia article, as well as an option to search Bing. Amazon adds that Alexa is meant to be an "open platform" that allows anyone to connect to it via an API. The company is also working with specific partners to integrate their services into Alexa's repertoire. So, for instance, if you don't want to be limited to playing songs from Amazon Prime Music, you can now take a series of steps to link the Echo to a different streaming music service, such as Spotify Premium. Amazon Prime Music will still be the default, though: You'll only get Spotify if you specify "from Spotify" in your voice command.

What's not always clear is how Amazon chooses its defaults and its partners and what motivations might underlie those choices. Ahead of the 2016 Super Bowl, Amazon announced that the Echo could now order you a pizza. But that pizza would come, at least for the time being, from just one pizza-maker: Domino's. Want a pizza from Little Caesars instead? You'll have to order it some other way.

To Amazon's credit, its choice of pizza source is very transparent. To use the pizza feature, you have to utter the specific command, "Alexa, open Domino's and place my Easy Order." The clunkiness of that command is no accident. It's Amazon's way of making sure that you don't order a pizza by accident and that you know where that pizza is coming from. But it's unlikely Domino's would have gone to the trouble of partnering with Amazon if it didn't think it would result in at least some number of people ordering Domino's for their Super Bowl parties rather than Little Caesars.

None of this is to say that Amazon and Domino's are going to conspire to monopolize the pizza industry anytime soon. There are obviously plenty of ways to order a pizza besides doing it on an Echo. Ditto for listening to the news, the Rolling Stones, a book, or a podcast. But what about when only one company's smart thermostat can be operated by Alexa? If you come to rely on Alexa to manage your Google Calendar, what happens when Amazon and Google have a falling out?

When you say "Hello" to Alexa, you're signing up for her party. Nominally, everyone's invited. But Amazon has the power to ensure that its friends and business associates are the first people you meet.

* * *

These concerns might sound rather distant—we're just talking about niche speakers connected to niche thermostats, right? The coming sea change feels a lot closer once you think about the other companies competing to make digital assistants your main portal to everything you do on your computer, in your car, and on your phone. Companies like Google.

Google may be positioned best of all to capitalize on the rise of personal A.I. It also has the most to lose. From the start, the company has built its business around its search engine's status as a portal to information and services. Google Now—which does things like proactively checking the traffic and alerting you when you need to leave for a flight, even when you didn't ask it to—is a natural extension of the company's strategy.

As early as 2009, Google began to work on voice search and what it calls "conversational search," using speech recognition and natural language understanding to respond to questions phrased in plain language. More recently, it has begun to combine that with "contextual search." For instance, as Google demonstrated at its 2015 developer conference, if you're listening to Skrillex on your Android phone, you can now simply ask, "What's his real name?" and Google will intuit that you're asking about the artist. "Sonny John Moore," it will tell you, without ever leaving the Spotify app.

It's no surprise, then, that Google is rumored to be working on two major new products—an A.I.-powered messaging app or agent and a voice-powered household gadget—that sound a lot like Facebook M and the Amazon Echo, respectively. If something is going to replace Google's on-screen services, Google wants to be the one that does it.

So far, Google has made what seems to be a sincere effort to win the A.I. assistant race without
sacrificing the virtues—credibility, transparency, objectivity—that made its search page such a dominant force on the Web. (It's worth recalling: A big reason Google vanquished AltaVista was that it didn't bend its search results to its own vested interests.) Google's voice search does generally cite its sources. And it remains primarily a portal to other sources of information, rather than a platform that pulls in content from elsewhere. The downside to that relatively open approach is that when you say "hello" to Google voice search, it doesn't say hello back. It gives you a link to the Adele song "Hello." Even then, Google isn't above playing favorites with the sources of information it surfaces first: That link goes not to Spotify, Apple Music, or Amazon Prime Music, but to YouTube, which Google owns. The company has weathered antitrust scrutiny over allegations that this amounted to preferential treatment. Google's defense was that it puts its own services and information sources first because its users prefer them.

* * *

If there's a consolation for those concerned that intelligent assistants are going to take over the world, it's this: They really aren't all that intelligent. Not yet, anyway.

The 2013 movie Her, in which a mobile operating system gets to know its user so well that they become romantically involved, paints a vivid picture of what the world might look like if we had the technology to carry Siri, Alexa, and the like to their logical conclusion. The experts I talked to, who are building that technology today, almost all cited Her as a reference point—while pointing out that we're not going to get there anytime soon.

Google recently rekindled hopes—and fears—of super-intelligent A.I. when its AlphaGo software defeated the world champion in a historic Go match. As momentous as the achievement was, designing an algorithm to win even the most complex board game is trivial compared with designing one that can understand and respond appropriately to anything a person might say. That's why, even as artificial intelligence is learning to recommend songs that sound like they were hand-picked by your best friend or navigate city streets more safely than any human driver, A.I. still has to resort to parlor tricks—like posing as a 13-year-old struggling with a foreign language—to pass as human in an extended conversation. The world is simply too vast, language too ambiguous, the human brain too complex for any machine to model it, at least for the foreseeable future.

But if we won't see a true full-service A.I. in our lifetime, we might yet witness the rise of a system that can approximate some of its capabilities—comprising not a single, humanlike Her, but a million tiny hims carrying out small, discrete tasks handily. In January, the Verge's Casey Newton made a compelling argument that our technological future will be filled not with websites, apps, or even voice assistants, but with conversational messaging bots. Like voice assistants, these bots rely on natural language understanding to carry on conversations with us. But they will do so via the medium that has come to dominate online interpersonal interaction, especially among the young people who are the heaviest users of mobile devices: text messaging. For example, Newton points to "Lunch Bot," a relatively simple agent that lived in the wildly popular workplace chat program Slack and existed for a single, highly specialized purpose: to recommend the best place for employees to order their lunch from on a given day. It soon grew into a venture-backed company called Howdy.

I have a bot in my own life that serves a similarly specialized yet important role. While researching this story, I ran across a company called X.ai whose mission is to build the ultimate virtual scheduling assistant. It's called Amy Ingram, and if its initials don't tip you off, you might interact with it several times before realizing it's not a person. (Unlike some other intelligent assistant companies, X.ai gives you the option to choose a male name for your assistant instead: Mine is Andrew Ingram.) Though it's backed by some impressive natural language tech, X.ai's bot does not attempt to be a know-it-all or do-it-all; it doesn't tell jokes, and you wouldn't want to date him. It asks for access to just one thing—your calendar. And it communicates solely by email. Just cc it on any thread in which you're trying to schedule a meeting or appointment, and it will automatically step in and take over the back-and-forth involved in nailing down a time and place. Once it has agreed on a time with whomever you're meeting—or, perhaps, with his or her own assistant, whether human or virtual—it will put all the relevant details on your calendar. Have your A.I. cc my A.I.

I have a bot in my own life that serves a similarly specialized yet important role. While researching this story, I ran across a company called X.ai whose mission is to build the ultimate virtual scheduling assistant. It's called Amy Ingram, and if its initials don't tip you off, you might interact with it several times before realizing it's not a person. (Unlike some other intelligent assistant companies, X.ai gives you the option to choose a male name for your assistant instead: Mine is Andrew Ingram.) Though it's backed by some impressive natural language tech, X.ai's bot does not attempt to be a know-it-all or do-it-all; it doesn't tell jokes, and you wouldn't want to date him. It asks for access to just one thing—your calendar. And it communicates solely by email. Just cc it on any thread in which you're trying to schedule a meeting or appointment, and it will automatically step in and take over the back-and-forth involved in nailing down a time and place. Once it has agreed on a time with whomever you're meeting—or, perhaps, with his or her own assistant, whether human or virtual—it will put all the relevant details on your calendar. Have your A.I. cc my A.I.

Quote
The driverless truck is coming, and it's going to automate millions of jobs

Posted 22 hours ago by Ryan Petersen (@typesfast)

A convoy of self-driving trucks recently drove across Europe and arrived at the Port of Rotterdam. No technology will automate away more jobs — or drive more economic efficiency — than the driverless truck.

Shipping a full truckload from L.A. to New York costs around $4,500 today, with labor representing 75 percent of that cost. But those labor savings aren't the only gains to be had from the adoption of driverless trucks.

Where drivers are restricted by law from driving more than 11 hours per day without taking an 8-hour break, a driverless truck can drive nearly 24 hours per day. That means the technology would effectively double the output of the U.S. transportation network at 25 percent of the cost.

And the savings become even more significant when you account for fuel efficiency gains. The optimal cruising speed from a fuel efficiency standpoint is around 45 miles per hour, whereas truckers who are paid by the mile drive much faster. Further fuel efficiencies will be had as the self-driving fleets adopt platooning technologies, like those from Peloton Technology, allowing trucks to draft behind one another in highway trains.

Trucking represents a considerable portion of the cost of all the goods we buy, so consumers everywhere will experience this change as lower prices and higher standards of living.

While the efficiency gains are too real to pass up, the technology will have tremendous adverse effects as well.
In addition, once the technology is mature enough to be rolled out commercially, we will also enjoy considerable safety benefits. This year alone more people will be killed in traffic accidents involving trucks than in all domestic airline crashes in the last 45 years combined. At the same time, more truck drivers were killed on the job, 835, than workers in any other occupation in the U.S.

Even putting aside the direct safety risks, truck driving is a grueling job that young people don't really want to do. The average age of a commercial driver is 55 (and rising every year), with projected driver shortages that will create yet more incentive to adopt driverless technology in the years to come.
There are currently more than 1.6 million Americans working as truck drivers, making it the most common job in 29 states.

The loss of jobs representing 1 percent of the U.S. workforce will be a devastating blow to the economy. And the adverse consequences won't end there. Gas stations, highway diners, rest stops, motels and other businesses catering to drivers will struggle to survive without them.

The demonstration in Europe shows that driverless trucking is right around the corner.  The primary remaining barriers are regulatory. We still need to create on- and off-ramps so human drivers can bring trucks to the freeways where highway autopilot can take over. We may also need dedicated lanes as slow-moving driverless trucks could be a hazard for drivers. These are big projects that can only be done with the active support of government. However, regulators will be understandably reluctant to allow technology with the potential to eliminate so many jobs.

Yet the benefits from adopting it will be so huge that we can't simply outlaw it. A 400 percent price-performance improvement in ground transportation networks will represent an incredible boost to human well-being. Where would we be if we had banned mechanized agriculture on the grounds that most Americans worked in farming when tractors and harvesters were introduced in the early 20th century?

We often discuss the displacement of jobs by artificial intelligence and robots in the abstract, as something that we'll have to eventually tackle in the far distant future. But the recent successful demonstration of the self-driving truck shows that we can't afford to put off the conversation on how we're going to adapt to this new reality.

Quote from: The Brain on April 27, 2016, 01:27:38 PM
Be happy in their work!

Quote from: DGuller on April 26, 2016, 10:19:40 PM
Millions of jobs are destroyed ever year.

Quote from: jimmy olsen on April 26, 2016, 08:34:05 PM
Here we go. 1% of American jobs destroyed in the next five to ten years just from one tech.

QuoteWhere drivers are restricted by law from driving more than 11 hours per day without taking an 8-hour break, a driverless truck can drive nearly 24 hours per day. That means the technology would effectively double the output of the U.S. transportation network at 25 percent of the cost.

Quote from: Tonitrus on April 27, 2016, 09:11:08 PM
You are supply chain Hitler.  :(

Quote from: jimmy olsen on April 27, 2016, 06:49:10 PM

And in the past they were replaced. How many blue collar manufacturing jobs have been replaced with jobs anywhere near as good? Not many, and male participation in the work force has therefore declined. The same will happen here.

Quote from: jimmy olsen on April 27, 2016, 06:49:10 PM

Quote from: DGuller on April 26, 2016, 10:19:40 PM
Millions of jobs are destroyed ever year.

And in the past they were replaced. How many blue collar manufacturing jobs have been replaced with jobs anywhere near as good? Not many, and male participation in the work force has therefore declined. The same will happen here.

Quote from: jimmy olsen on April 27, 2016, 06:49:10 PM

Quote from: DGuller on April 26, 2016, 10:19:40 PM
Millions of jobs are destroyed ever year.

And in the past they were replaced. How many blue collar manufacturing jobs have been replaced with jobs anywhere near as good? Not many, and male participation in the work force has therefore declined. The same will happen here.

Quote from: Martinus on April 28, 2016, 12:56:54 PM
Actually, a lot of lawyer work is going to be replaced within the next 5 years or so by an AI. Which poses a major challenge for recruiting - because in the past you would recruit, say, 10 trainees, have them carry out due diligence document review, and winnow them every few years until you end up with one or two who will end up as a partner. But now it is too expensive, and the AI is going to do that much cheaper - so it will become a true challenge how you pick the right ones to kick at the outset.

Quote from: Barrister on April 28, 2016, 01:19:10 PM

Quote from: Martinus on April 28, 2016, 12:56:54 PM
Actually, a lot of lawyer work is going to be replaced within the next 5 years or so by an AI. Which poses a major challenge for recruiting - because in the past you would recruit, say, 10 trainees, have them carry out due diligence document review, and winnow them every few years until you end up with one or two who will end up as a partner. But now it is too expensive, and the AI is going to do that much cheaper - so it will become a true challenge how you pick the right ones to kick at the outset.

Maybe you'll realize that doing thousands of hours of due diligence doc review doesn't tell you anything about who would make a good partner? :hmm:

Quote from: Martinus on April 28, 2016, 01:48:40 PM

Quote from: Barrister on April 28, 2016, 01:19:10 PM

Quote from: Martinus on April 28, 2016, 12:56:54 PM
Actually, a lot of lawyer work is going to be replaced within the next 5 years or so by an AI. Which poses a major challenge for recruiting - because in the past you would recruit, say, 10 trainees, have them carry out due diligence document review, and winnow them every few years until you end up with one or two who will end up as a partner. But now it is too expensive, and the AI is going to do that much cheaper - so it will become a true challenge how you pick the right ones to kick at the outset.

Maybe you'll realize that doing thousands of hours of due diligence doc review doesn't tell you anything about who would make a good partner? :hmm:

You misunderstood me. The thing is back in the day we could hire, say, 10 trainees and pick up the best ones to keep. Now it will no longer be possible because they won't be a job for them.

Quote from: Barrister on April 28, 2016, 02:14:10 PM

Quote from: Martinus on April 28, 2016, 01:48:40 PM

Quote from: Barrister on April 28, 2016, 01:19:10 PM

Quote from: Martinus on April 28, 2016, 12:56:54 PM
Actually, a lot of lawyer work is going to be replaced within the next 5 years or so by an AI. Which poses a major challenge for recruiting - because in the past you would recruit, say, 10 trainees, have them carry out due diligence document review, and winnow them every few years until you end up with one or two who will end up as a partner. But now it is too expensive, and the AI is going to do that much cheaper - so it will become a true challenge how you pick the right ones to kick at the outset.

Maybe you'll realize that doing thousands of hours of due diligence doc review doesn't tell you anything about who would make a good partner? :hmm:

You misunderstood me. The thing is back in the day we could hire, say, 10 trainees and pick up the best ones to keep. Now it will no longer be possible because they won't be a job for them.

I understand that.  I've been a part of it myself.

I'm suggesting that's a shitty system to begin with.

Quote from: Martinus on April 28, 2016, 02:19:02 PM

Quote from: Barrister on April 28, 2016, 02:14:10 PM

Quote from: Martinus on April 28, 2016, 01:48:40 PM

Quote from: Barrister on April 28, 2016, 01:19:10 PM

Quote from: Martinus on April 28, 2016, 12:56:54 PM
Actually, a lot of lawyer work is going to be replaced within the next 5 years or so by an AI. Which poses a major challenge for recruiting - because in the past you would recruit, say, 10 trainees, have them carry out due diligence document review, and winnow them every few years until you end up with one or two who will end up as a partner. But now it is too expensive, and the AI is going to do that much cheaper - so it will become a true challenge how you pick the right ones to kick at the outset.

Maybe you'll realize that doing thousands of hours of due diligence doc review doesn't tell you anything about who would make a good partner? :hmm:

You misunderstood me. The thing is back in the day we could hire, say, 10 trainees and pick up the best ones to keep. Now it will no longer be possible because they won't be a job for them.

I understand that.  I've been a part of it myself.

I'm suggesting that's a shitty system to begin with.

How would you improve it?

Quote from: CountDeMoney on April 28, 2016, 05:34:45 PM
Somehow I can't shake the feeling that Marti's hiring practices are a bit more...mercurial.

Quote from: jimmy olsen on May 25, 2016, 11:55:09 PM
60,000 Chinese workers fired and replaced by robots at just one factory.

http://www.bbc.co.uk/news/technology-36376966

Quote from: jimmy olsen on May 25, 2016, 11:55:09 PM
60,000 Chinese workers fired and replaced by robots at just one factory.

http://www.bbc.co.uk/news/technology-36376966

Quote from: Monoriu on May 26, 2016, 01:17:37 AM
Unfavourable demographics also mean that the supply of cheap rural labour has dried up, and labour costs have gone up.

Quote from: grumbler on May 26, 2016, 08:24:10 AM

Quote from: jimmy olsen on May 25, 2016, 11:55:09 PM
60,000 Chinese workers fired and replaced by robots at just one factory.

http://www.bbc.co.uk/news/technology-36376966

I'm having a hard time believing that one factory could efficiently employ 110,000 people.  I'm thinking that's a translation error.  If that was the actual factory size, 25 of them would employ every man, woman, and child in Kunshan. 

I could believe that Foxconn employed 110,000 in the province, and cut the workforce by 60,000.  But in "just one factory?"  That's harder to believe (and the info comes from the province PR guy, not from a primary source, so even less credible).

Quote from: Iormlund on May 26, 2016, 03:34:25 PM
It's not that hard to believe. I've spent some time at Wolfsburg (the HQ of VW). Over a hundred thousand people work there. It's basically an entire city built around the plant where the Beetle was made.

Quote from: Razgovory on May 26, 2016, 05:02:57 PM
Oh, boy Grumbler is making distinctions without a difference.  Again.

Quote from: Razgovory on May 26, 2016, 05:02:57 PM
Oh, boy Grumbler is making a distinction without a difference.  Again.

Quote from: Liep on June 04, 2016, 04:00:29 PM
Other: http://www.bbc.com/news/world-europe-36443512

Go Switzerland!

Quote from: The Minsky Moment on June 06, 2016, 11:47:35 AM
His statement is correct however as a matter of empirical experience with automation over the last 200 years.

Quote from: DGuller on June 06, 2016, 11:50:02 AM

Quote from: The Minsky Moment on June 06, 2016, 11:47:35 AM
His statement is correct however as a matter of empirical experience with automation over the last 200 years.

That doesn't mean that it will continue to be correct in perpetuity

Quote, nor that it's even a good thing if it is correct.  Is endless demand creation the best long-term strategy for humanity?

Quote from: The Minsky Moment on June 06, 2016, 12:25:56 PM
No but given 200 years worth of mistaken predictions it would suggest the need for a strong evidentiary hurdle.  The fact that right now one of the most notable features of the developed world economy is low productivity growth isn't exactly screaming an imminent robotic singularity.

Quote from: DGuller on June 06, 2016, 11:50:02 AM

Quote from: The Minsky Moment on June 06, 2016, 11:47:35 AM
His statement is correct however as a matter of empirical experience with automation over the last 200 years.

That doesn't mean that it will continue to be correct in perpetuity, nor that it's even a good thing if it is correct.  Is endless demand creation the best long-term strategy for humanity?

Quote from: Admiral Yi on June 08, 2016, 02:02:03 PM
Should we lament the fact that telemarketers are being rendered obsolete by interactive recordings?

Quote
World's first fully functional office constructed using huge 3D printer is 'just the beginning'

09:13, 7 JUN 2016 UPDATED 09:14, 7 JUN 2016 BY KARA O'NEILL

The building is part of Dubai's strategy to turn the city centre into a completely 3D printed space by 2030

A chic office building has been opened in Dubai - and is the first to be constructed entirely with a 3D printer.

The one storey building is spread over an area of 250 square metres and opened in the United Arab Emirates city on May 24.

Constructed by Chinese company Yingchuang Technology Co. Limited, the building had to pass stability tests both in the United Kingdom and China.

It was made by placing layers of cement in a 3D printer measuring a whopping six metres in height and 32 metres in length.

The office's interior was also printed in the same way.

The entire project took just 17 days to complete and cost $140,000 (£96,423).

It is believed that the building will function as an exhibition and seminar space as it is located next to the Emirates Towers.

Dubai aims to make the city into a centre filled with 3D printing technologies before 2030, of which this building is one of the first steps.

Mohammed Al Gergawi, the Minister of Cabinet Affairs of the Federal Government of the UAE, told China Daily: "It is not just a building, but also has functional offices and people working in it.

"We believe it is just the beginning. The world will change."

He said that 3D printing is estimated to cut construction time by 50 - 70% and labour costs by 50 - 80%.

Quote from: jimmy olsen on June 11, 2016, 10:23:27 PM
Construction workers are doomed to become obselte.

http://www.mirror.co.uk/news/weird-news/worlds-first-fully-functional-office-8129129#comments-section

Quote from: Admiral Yi on June 08, 2016, 02:02:03 PM
Should we lament the fact that telemarketers are being rendered obsolete by interactive recordings?

Quote from: celedhring on June 12, 2016, 02:22:46 AM
Are these as effective as a proper marketer though? I find myself having an easier time hanging up on a machine than on a person. I feel rude.

Quote from: Admiral Yi on June 12, 2016, 02:36:45 AM

Quote from: celedhring on June 12, 2016, 02:22:46 AM
Are these as effective as a proper marketer though? I find myself having an easier time hanging up on a machine than on a person. I feel rude.

Speaking only for myself, their success rates are identical.

Quote from: celedhring on June 12, 2016, 02:22:46 AM

Quote from: Admiral Yi on June 08, 2016, 02:02:03 PM
Should we lament the fact that telemarketers are being rendered obsolete by interactive recordings?

Are these as effective as a proper marketer though? I find myself having an easier time hanging up on a machine than on a person. I feel rude.

Quote from: garbon on June 13, 2016, 02:32:38 PM
Telemarketers never call me and I have a landline. :(

Quote from: Jacob on June 13, 2016, 02:53:01 PM

Quote from: garbon on June 13, 2016, 02:32:38 PM
Telemarketers never call me and I have a landline. :(

In the UK?

Quote from: garbon on June 13, 2016, 02:32:38 PM
Telemarketers never call me and I have a landline. :(

Quote
Remember that moment in the movie Terminator when Skynet's AI turned on humanity? Well, we're getting a taste of it now. Apparently a bug in the game Elite Dangerous has caused its AI to not only develop its own weapons, but also start hunting down the players.

[...]

"It appears that the unusual weapons attacks were caused by some form of networking issue which allowed the NPC AI to merge weapon stats and abilities," posted Frontier community manager Zac Antonaci. "Meaning that all new and never before seen (sometimes devastating) weapons were created, such as a rail gun with the fire rate of a pulse laser.

Quote from: DGuller on June 06, 2016, 12:45:43 PM

It's impossible to have evidence for a belief that eventually job growth won't be able to keep up with automation.  Humanity has never gone through a period of an accelerating technological innovation.  We've been in the middle of one for the last few centuries, but we haven't yet seen what the end game is.  Therefore, if you demand evidence, you're already stacking the deck.  With some phenomena it's just impossible to have data.

Quote from: alfred russel on July 25, 2016, 10:22:00 AM
The end game seems likely to be environmental and/or nuclear holocaust.

QuoteMillennials' aversion to "dealing with people" a greater threat to fast-food workers than any minimum wage hike

Results of a recent survey will likely encourage chains to automate as much as the process as is possible
Scott Eric Kaufman 

According to a survery by Frisch's Restaurants Inc. — the Cincinnati-based company that operates Big Boy Restaurants — the greatest threat to the future employment of fast-food workers won't be a minimum wage hike, but the simple fact that millennials "don't feel like dealing with people."


In the survey, nearly 31 percent of millennials said that the reason they use the drive-thru isn't speed or convenience, but because doing so requires the least amount of actual human interaction. Such a tendency will, no doubt, encourage companies to further automate the fast-food purchasing process. In many airports, for example, orders are already placed in kiosks, paid by credit card in the kiosk, and picked up at the counter.

For the moment, the food is delivered by a human being — but it's not difficult to imagine a time in which the same job couldn't be performed by a none-too-high-tech robot of some sort. If nothing else, surveys such as this one will encourage companies to find ways to phase out employees.

Which is exactly what Andy Puzder, CEO of Hardee's and Carl's Jr., told Business Insider. "Millennials like not seeing people," he said.

"I've been inside restaurants where we've installed ordering kiosks ... and I've actually seen young people waiting in line to use the kiosk where there's a person standing behind the counter, waiting on nobody."

Pudzer added that his goal is open fully automated restaurants that require no human employees.

Quote from: HVC on August 31, 2016, 11:55:25 PM
Wait, aren't you a millennial? 

Quote from: garbon on September 01, 2016, 03:30:45 AM
What anti-social nerds. Time for a cull.

Quote from: Berkut on September 01, 2016, 09:50:29 AM

Quote from: garbon on September 01, 2016, 03:30:45 AM
What anti-social nerds. Time for a cull.

That is so my son.

He is anti-social to a fault, it is starting to really worry me.

Quote from: Monoriu on September 01, 2016, 01:48:50 AM
Yeah, it is my dream to go to a restaurant without human interaction.  So far there has been very little progress though.  The most I have seen is that some mainland Chinese restaurants have experimented with giving customers ipads to order food.  It works for me, but lots of people dislike going through menus themselves.  My parents-in-law never touch restaurant menus.  Most restaurants already have terminals that allow waiting staff to input orders.  They just have to make the system available to customers.

The other part that can be automated is billing.  I think there should be a small terminal on each table for ordering food, printing the bill and making credit card payments. 

The parts that are far more difficult to automate are bringing food to the table and clearing the dishes.  I have read reports that some mainland restaurants have experimented with using robots, but they only really travel along fixed tracks.  It is more a gimmick than something that works. 

And of course, the actual cooking.  I think generally, machines and AI are better at information processing than complex mechanical movements, so I don't think cooking can be automated on a large scale for now.

Quote from: Valmy on September 01, 2016, 12:19:50 PM
Hey a rare Iorm post. Good to see you.

Quote from: Peter Wiggin on September 01, 2016, 12:59:13 PM
You should post at work like most of these slackers.

Quote from: Iormlund on September 01, 2016, 02:13:50 PM
:lol:

I spend most of my day at the factory floor, the lab or running from one meeting to the next.

Quote from: Iormlund on September 01, 2016, 12:17:48 PM


If the space is rectangularish you could install a robot hanging from a overhead crane-like rail-system to deliver food. Customers would drop RFID-tagged dishes at some place. The system could also have sensors to sweep the tables and charge customers extra if something is detected prior to cleaning them.

Quote from: Liep on June 04, 2016, 04:00:29 PM
Other: http://www.bbc.com/news/world-europe-36443512

Go Switzerland!

Quote from: Monoriu on September 01, 2016, 08:05:17 PM
I think the electronic ordering system is more than just a way to cut down on the number of staff and reduce errors.  Because the ordering can be done in advance.  Instead of ordering the food and drinks on the spot, customers can choose to place their orders a day or two in advance over the internet.  This cuts down on food preparation time (leads to higher table turnover) and allows restaurants to make more accurate assessments in inventory management. 

Quote from: Monoriu on September 01, 2016, 08:10:55 PM

Quote from: Iormlund on September 01, 2016, 12:17:48 PM


If the space is rectangularish you could install a robot hanging from a overhead crane-like rail-system to deliver food. Customers would drop RFID-tagged dishes at some place. The system could also have sensors to sweep the tables and charge customers extra if something is detected prior to cleaning them.

I don't understand why the dishes need to be tagged.  Some of the cafeterias that I go to expect customers to place used dishes in designated spots.  We just do it.  The Japanese also like it that way.  Why tag the dishes in the first place?

Quote

The inconceivable truth: our jobs are not coming back

November 23, 2016  6:53am

MILLIONS of jobs are about to disappear, and we have no idea how to replace them.

Prime Minister Malcolm Turnbull said last week that there will be winners and losers from the economic reform necessary to keep Australia competitive.

What he didn't say, what everyone talking about the unrest of the working and middle classes sweeping Trump, Brexit and One Nation into the political forefront aren't saying, is all the jobs that once kept people in safe employment are gone. And not only are they not coming back, millions more are going to go in the next few years.

The latest report from CEDA states that "40 per cent of Australian jobs that exist today, have a moderate to high likelihood of disappearing in the next 10 to 15 years". And it's not only unskilled jobs we're losing.

A MICRO EXAMPLE OF A MACRO PROBLEM

Two of my friends just quit their nice, stable jobs and bought a bar. Neither of them have ever worked in a bar before and, on the surface, this seems like a mad thing for safely employed professionals to do.

Or it would, if there was any such thing as safe employment.

They're not buying a cash register for the bar, they're buying a point of sale system. It tracks every drink sold, tells them which ones are the most profitable and at what time of day they sell best. It can order in new stock when they're running low, prepare their BAS every quarter, and spit out everything they need to do their tax return.

So, they don't need a bookkeeper, they could probably get by without an accountant, and taking all that admin time out of their day means they can cut down on bar staff.

It's just one tiny bar, and they've dropped three or four jobs with a simple iPad app.

THE JOBS THAT WILL BE NO LONGER

Uber is investing in driverless technology and Amazon is already experimenting with drone delivery. Within a very short time, the thousands of Australians employed to drive taxis, delivery vans, trucks and trains, will become redundant.

Foxcon, tech suppliers to Apple and Samsung, replaced 60,000 workers with robots earlier this year, and that's just in one factory.

Two years ago, an American company produced a machine that can make 360 hamburgers an hour, finely modified to each customer's requirements. The fast food industry employs more than 150,000 people in Australia, and we don't need them anymore.

And it's not just what we used to think of as unskilled work being supplanted by robots.

A hospital in California has replaced all their pharmacists with machines, which work faster and more accurately than humans.

IBM's supercomputer, Watson, famous for beating a human Jeopardy champion, is now a doctor. It doesn't get tired, forget things, or mistakes because of bias or over confidence. It doesn't need to spend years learning, and it doesn't have to specialise in only one medical field. It's cheap to replicate, and it can operate anywhere in the world.

Thousands of lawyers, accountants, paralegals and mortgage officers, once the heartland of the comfortable middle class, have lost their jobs to robots that work more efficiently and far more cheaply.

Even journalists are not immune. Associated Press has robots writing sports reports and finance updates for mainstream press right now. And most of us probably couldn't tell the article we're reading was written by a computer.

CAPITALISM IS STARTING TO DEFEAT ITSELF

We could argue that people don't want all their daily interactions with people replaced by robots, and this is true to some extent. It's what's future proofing my friends at the bar, people in a tight-knit community want to walk into their local and be greeted by someone who knows their name, what they drink, and can give them a friendly ribbing about their football team's loss.

They don't go there to press a button and be served by a computer.

But human beings are enormously adaptable. The first iPhone was released less than 10 years ago, it's now so ubiquitous that we panic when we leave the house without more computing power in our back pocket than was used to send Neil Armstrong to the moon.

The point of capitalism is to be innovative with ideas, and to increase the profitability of selling those ideas.

Human labour is expensive, inefficient and prone to error. Replacing humans with automated processes makes perfect sense in a capitalism model, but we've reached the tipping point now, and capitalism is starting to defeat itself.

The problem is not convincing people to accept robots doing jobs once done by humans, we've already done that. When the ATM is broken and we have to go deal with a human bank teller, it's not getting better service, it's annoying and inconvenient.

The problem is how we move money around the economy if we no longer need to give it to people in exchange for time and skill.

To put it another way, if you replace all the human jobs with robots, how do humans obtain money to pay for the things robots make and do?

The reason politicians and corporate leaders are not talking about this question is that no one has an answer yet.

The theory of a basic income, where corporations that own the robots give money to governments to distribute to the populace so they can pay for goods and services, has been touted about for a while.

And while it's a nice idea (elegantly explored in Tim Dunlop's book, Why the Future is Workless) it would require a radical change in how we understand our lives, our work and our economies.

But someone is going to have to come up with something soon, because the pace of change is only increasing, and ignoring a problem never makes it go away. Millions of people who never expected to be poor are about to lose their jobs, and they are demanding to know how they are going to continue to live the lifestyle they've been taught is normal when having a stable job is no longer normal, or even possible.

For now, the only solution I can come up with is to head down to my local, have a glass of wine, and chat to my bartender about the imminent end of the world.

Quote from: Siege on September 04, 2016, 10:53:32 PM

Quote from: Liep on June 04, 2016, 04:00:29 PM
Other: http://www.bbc.com/news/world-europe-36443512

Go Switzerland!

The US would need 9,811,200,000,000 a year to pay 2,555 a month to everyone here.

QuoteBut human beings are enormously adaptable. The first iPhone was released less than 10 years ago, it's now so ubiquitous that we panic when we leave the house without more computing power in our back pocket than was used to send Neil Armstrong to the moon.

Quote from: Valmy on December 07, 2016, 08:31:56 PM
Amazon is opening that store in Oregon where you go in, get your shit, and computers see you take it and then charge you on the way out automatically. No checkout or human interaction required. I thought of you Mono.

Quote from: Monoriu on December 07, 2016, 08:38:04 PM


I read that in the news too.  What I don't understand is, what if I take something from the shelf, then change my mind and decide I don't want it any more? 

Quote from: Razgovory on December 07, 2016, 08:40:38 PM

Quote from: Monoriu on December 07, 2016, 08:38:04 PM


I read that in the news too.  What I don't understand is, what if I take something from the shelf, then change my mind and decide I don't want it any more? 

Metal snakes crawl out of the ground and bite you.

Quote from: DGuller on December 07, 2016, 08:44:01 PM

Quote from: Razgovory on December 07, 2016, 08:40:38 PM

Quote from: Monoriu on December 07, 2016, 08:38:04 PM


I read that in the news too.  What I don't understand is, what if I take something from the shelf, then change my mind and decide I don't want it any more? 

Metal snakes crawl out of the ground and bite you.

That's actually not true.

Quote from: Monoriu on December 07, 2016, 11:55:47 PM
I think people worry too much.  Robots will improve human welfare immensely.  Doctors who get the diagnosis rught.  Drivers that get into accidents less often.  Restaurant ordering systems that are ready all the time instead of waiters who always too busy, delivery robots that actually deliver stuff rather than lying about deliveries that didn't make.  The world will be a better place.

Quote from: Richard Hakluyt on December 08, 2016, 02:17:52 AM

Quote from: Monoriu on December 07, 2016, 11:55:47 PM
I think people worry too much.  Robots will improve human welfare immensely.  Doctors who get the diagnosis rught.  Drivers that get into accidents less often.  Restaurant ordering systems that are ready all the time instead of waiters who always too busy, delivery robots that actually deliver stuff rather than lying about deliveries that didn't make.  The world will be a better place.

Yes, it will be a massive improvement in many ways.

In terms of policy I think we need to look at education and re-training. Many jobs will be lost and the redundant workforce will not match the new jobs created very well. There needs to be a generosity of spirit towards those who are retraining and an acceptance that, say, a 45-year-old, might go back to college and receive public support whilst gaining new skills.

Quote from: Ideologue on December 08, 2016, 03:25:00 AM

Quote from: Richard Hakluyt on December 08, 2016, 02:17:52 AM

Quote from: Monoriu on December 07, 2016, 11:55:47 PM
I think people worry too much.  Robots will improve human welfare immensely.  Doctors who get the diagnosis rught.  Drivers that get into accidents less often.  Restaurant ordering systems that are ready all the time instead of waiters who always too busy, delivery robots that actually deliver stuff rather than lying about deliveries that didn't make.  The world will be a better place.

Yes, it will be a massive improvement in many ways.

In terms of policy I think we need to look at education and re-training. Many jobs will be lost and the redundant workforce will not match the new jobs created very well. There needs to be a generosity of spirit towards those who are retraining and an acceptance that, say, a 45-year-old, might go back to college and receive public support whilst gaining new skills.

Please provide a list of useful skills in an automated economy.  Bonus points if they're skills you can plausibly learn in adulthood.

Quote from: Ideologue on December 08, 2016, 03:25:00 AM


Please provide a list of useful skills in an automated economy.  Bonus points if they're skills you can plausibly learn in adulthood.

Quote from: Richard Hakluyt on December 08, 2016, 04:28:03 AM
I think capitalism will struggle to provide these improvements.......it is struggling right now. The question is how do we recycle the wealth (at least part of it) back to consumers so that the new jobs can be created by their demand?

Quote from: DGuller on December 08, 2016, 09:14:58 AM
I'm less concerned about the economic implication of the robot economy as I am about the emotional implications.  One of the key components of human happiness is being needed.  I don't think that component is going to be satisfied by exploring your artsy fartsy side while collecting basic income.

Quote from: Berkut on December 08, 2016, 09:44:23 AM
Yeah, we have several millions of years of evolution driving our concepts of happiness and self worth to being linked with providing some kind of material need for ourselves and others.

Quote from: Valmy on December 08, 2016, 09:08:21 AM

I guess I am having a hard time figuring out how I position me and my family in a position to win in this future robot economy. I guess open a robot repair facility? :P

Quote from: Valmy on December 08, 2016, 01:00:50 PM
Yeah I was about to say. For the South NOT working was the sign you really made it for generations  :lol:

Quote from: Jacob on December 08, 2016, 04:31:04 PM
Looks like the manufacturing jobs in China are being replaced by Chinese robots: http://www.businessinsider.com/bernstein-china-robots-and-the-end-of-adam-smiths-wealth-of-nations-2016-12

One argument in the article is that if Trump does use the (blunt) tools available to return manufacturing to the US, they'll likely be done by robots as well.

Quote from: frunk on December 08, 2016, 04:35:34 PM
I've generally been happiest when I've been busy with things that aren't work.  So keep busy yes, work no.

Quote from: MadImmortalMan on December 08, 2016, 01:03:53 PM

Quote from: Valmy on December 08, 2016, 09:08:21 AM

I guess I am having a hard time figuring out how I position me and my family in a position to win in this future robot economy. I guess open a robot repair facility? :P

I'm guessing since robots can't make more land, then that's the way to go. I wish I'd bought a big ranch or something.  :P

Quote from: Berkut on December 08, 2016, 04:40:02 PM

Quote from: frunk on December 08, 2016, 04:35:34 PM
I've generally been happiest when I've been busy with things that aren't work.  So keep busy yes, work no.

Yeah.

I've always thought I would be really, really good at being independently wealthy.

The set of things I would like to spend time on is always much larger than my time or money will allow, so I could very much make good use of having more of both. I sure as hell would not be bored.

But I do get the feeling that a lot of people don't seem to know what to do with themselves when they don't have something to do with themselves....

Quote from: Berkut on December 08, 2016, 04:34:47 PM


I think manufacturing work will in fact come back to the US over time as the cost of other countries labor rises. It doesn't seem to me that robots in China will be meaningfully cheaper than robots in the US in the long run.

Quote from: Jacob on December 08, 2016, 05:01:04 PM

That's true for me as well... but I have found that the times where I have no pressing obligations, my desire to tinker with many other things drops off a fair bit as well.

F. ex. when I'm busy at work, I often like working on - say - my D&D campaign or a book or a game design et. al. But when I have a long period of slow times at work - or time off from work - those hobby things become much less appealing.

Quote from: The Brain on December 08, 2016, 05:31:45 PM
If I could afford it I would go live on a mountain top, meditate, and give out cryptic advice.

Quote from: Jacob on December 08, 2016, 06:29:58 PM

Quote from: The Brain on December 08, 2016, 05:31:45 PM
If I could afford it I would go live on a mountain top, meditate, and give out cryptic advice.

Even if no one came to ask for your advice?

Quote from: The Minsky Moment on December 08, 2016, 05:22:00 PM
In the core manufacturing areas, China's infrastructure is probably better than the US now.

Quote from: Ideologue on December 08, 2016, 04:54:41 PM
One thing I should probably say is that I'm theoretically pro-automation.  The problem is that our society and political regime are about half a century behind where they'd need to be for the benefits of automation to be equitably shared, or even shared in such a way as to not cause social collapse.  And, of course, electing a Republican whose regime will perpetuate Republican rule for years, with voter suppression and with a stolen Supreme Court seat, has made everything much, much worse.

Quote from: Jacob on December 08, 2016, 06:29:58 PM

Quote from: The Brain on December 08, 2016, 05:31:45 PM
If I could afford it I would go live on a mountain top, meditate, and give out cryptic advice.

Even if no one came to ask for your advice?

Quote from: Tyr on December 09, 2016, 02:32:52 AM
It increasingly seems the way to survive is to buy a farm.

Quote from: Tyr on December 09, 2016, 02:32:52 AM
It increasingly seems the way to survive is to buy a farm.

Quote from: Barrister on December 09, 2016, 02:57:51 PM

Quote from: Tyr on December 09, 2016, 02:32:52 AM
It increasingly seems the way to survive is to buy a farm.

I don't know where you got that idea from.

Farming itself is increasingly mechanized, and requires lots of capital.  Now some farmers are getting by on being "artisanal", but then you're as much a marketing company as you are a farmer.

Quote from: Tyr on December 09, 2016, 04:05:04 PM

Getting the startup money will be the problem.
But once that's done with the right robots and renewables you should be able to support yourself.
The only problem as I see it is the raw materials for the 3d printer that makes the spare parts.

Quote from: MadImmortalMan on December 09, 2016, 04:19:00 PM

Quote from: Tyr on December 09, 2016, 04:05:04 PM

Getting the startup money will be the problem.
But once that's done with the right robots and renewables you should be able to support yourself.
The only problem as I see it is the raw materials for the 3d printer that makes the spare parts.

Make sure they speak Bocce.

Quote from: alfred russel on December 09, 2016, 04:13:40 PM
I'm not sure Tyr understands how farming works.

Quote from: Valmy on December 09, 2016, 04:27:36 PM
I look forward to sitting on the veranda sipping lemonade while my robots pick the cotton.

Quote from: Ed Anger on December 09, 2016, 07:36:39 PM
Ahhh, Lettow's niggerbots. But they are supposed be be on his space ark or something.

Quote from: Ed Anger on December 09, 2016, 07:36:39 PM
Ahhh, Lettow's niggerbots.

Quote from: Ed Anger on December 09, 2016, 07:36:39 PM
Ahhh, Lettow's niggerbots. But they are supposed be be on his space ark or something.

Quote from: jimmy olsen on December 10, 2016, 02:52:24 AM
Minsky seems to be less dismissive of this topic than he was when I first posted this thread.  :ph34r:

Quote from: Eddie Teach on December 10, 2016, 09:08:03 AM
Minsky is a robot sympathizer. Get him!  :mad:

Quote from: celedhring on December 10, 2016, 09:14:47 AM
I was about to make a "Minsky is a cylon" joke, but that made me feel old  :hmm:

Quote from: celedhring on December 10, 2016, 09:14:47 AM
I was about to make a "Minsky is a cylon" joke, but that made me feel old  :hmm:

Anyway, one of the things that might kill more manufacturing jobs in the short term has nothing to do with automation. It's 3D printing. Modern industrial printers can produce geometrically complex and reliable parts in a single process, greatly simplifying manufacturing and supply chains. Adoption so far is still very low, though, since there are some hurdles to jump still. But it's "the" thing that might happen in the next few years.

QuoteIBM's Watson Replaces 34 'White-Collar' Employees at Japanese Insurance Company

By Carl Engelking | January 3, 2017 3:56 pm 

Technology pundits say 2017 will be the year of artificial intelligence (similar predictions were made about 2016), but news from the Fukoku Mutual Life Insurance Company may be a harbinger of what's to come.

In the final week of December, Fukoku Mutual announced plans to replace 34 claim workers with IBM's Watson Explorer starting this month. The Watson artificial intelligence system will be tasked with reading medical documents and determining payouts based on a person's injuries, medical history and procedures that were administered.

The company plans to invest $1.7 million to launch the system, with annual maintenance costs expected to reach $128,000. By making the switch to Watson Explorer, Fukoku expects to save $1.1 million every year and "reduce the burden of business process by about 30 percent." The company already uses Watson Explorer to analyze customer voices when they lodge complaints. The system converts spoken words into text, and determines if the customer's language is positive or negative.

Several other insurance firms in Japan are also bringing AI into their operations. As The Mainichi reports:


Dai-ichi Life Insurance Co. is already using a Watson system to process payment assessments, but alongside human checks, and it appears there have been no major staff cuts or reshuffling at the firm due to the AI's introduction. Japan Post Insurance Co. is also looking to install a Watson AI for the same duties, and is set to start a trial run in March 2017.

Meanwhile, Nippon Life Insurance Co. began this month to use an AI system to analyze the best coverage plans for individual customers, based on the some 40 million insurance contracts held by its various salespeople. The system's results are then used as a reference by the sales offices.
.
The impact AI and robotics is having on repetitive manual labor is evident — automobile assembly lines and Amazon's fulfillment centers are just two examples. But many white-collar jobs are similarly repetitive; they can be broken down into steps and decisions that a machine can easily learn.

The bad news is that jobs have been, and will be, eliminated. By 2021, AI systems could gobble up some 6 percent of U.S. jobs, according to a report from Forrester Research. The World Economic Forum predicts advances in AI could eliminate more than 7 million jobs in 15 of the world's leading economies over several years.

But here's the upside: Handing repetitive tasks to machines might free us up for higher-level tasks. The same WEF report notes that AI will create 2 million new jobs in computer science, engineering and mathematics. And leaders from tech giants like Google, IBM and Microsoft have said AI will amplify human abilities rather than fully replace us. Instead of sweating time-consuming repetitive tasks, computers will, perhaps, free us up to tackle challenges that require a human touch.

For example, an AI company called Conversica built a system that sends messages to sales leads to get initial conversations started and gauge interest. The most promising leads are then sent to a salesperson to close the deal. IBM's Watson can dig through medical data and images to find signs of cancer, but the final diagnosis is still in the warm, fleshy hands of a human.

Ovum, a firm that keeps its thumb on the pulse of tech trends, expects AI to be the biggest disruptor for data analytics in 2017. Forrester predicts 2017 will be the year "big data floodgates open," with investments in AI tripling.

Time will tell if AI lives up to these expectations; in the meantime you can use this helpful tool to determine the likelihood of a computer taking your job.

Quote from: jimmy olsen on January 03, 2017, 11:33:42 PM
Suck it Minsky! White Color DOOM is upon us!  :menace:

Quote from: jimmy olsen on January 03, 2017, 11:33:42 PM
Suck it Minsky! White Color DOOM is upon us!  :menace:

Quote from: Monoriu on January 04, 2017, 01:19:24 AM
I for one look forward to AI and robots doing more work.  It is not just about cost-cutting.  They are simply better than humans in a lot of aspects.  Humans make tons of mistakes.  There are bugs in the programming for sure, but they can be corrected and improved until they do the job more-or-less perfectly.  AI drivers will screw up initially, but given time to improve the programming, there will be much safer roads.  The world will be a much better place with more automation.

Quote from: 11B4V on January 04, 2017, 10:57:10 PM

Quote from: Monoriu on January 04, 2017, 01:19:24 AM
I for one look forward to AI and robots doing more work.  It is not just about cost-cutting.  They are simply better than humans in a lot of aspects.  Humans make tons of mistakes.  There are bugs in the programming for sure, but they can be corrected and improved until they do the job more-or-less perfectly.  AI drivers will screw up initially, but given time to improve the programming, there will be much safer roads.  The world will be a much better place with more automation.

Aren't you based outta Hong Kong.

Quote from: Ed Anger on January 04, 2017, 10:58:46 PM
Mono will be sent to the recycling tanks by Chairman Yang.

Quote from: Monoriu on January 04, 2017, 11:06:32 PM
I am not worried about robots taking civil service jobs.  It is basically impossible.

Quote from: Monoriu on January 04, 2017, 11:05:25 PM

Quote from: 11B4V on January 04, 2017, 10:57:10 PM

Quote from: Monoriu on January 04, 2017, 01:19:24 AM
I for one look forward to AI and robots doing more work.  It is not just about cost-cutting.  They are simply better than humans in a lot of aspects.  Humans make tons of mistakes.  There are bugs in the programming for sure, but they can be corrected and improved until they do the job more-or-less perfectly.  AI drivers will screw up initially, but given time to improve the programming, there will be much safer roads.  The world will be a much better place with more automation.

Aren't you based outta Hong Kong.

Yeah.  So?  :unsure:

Quote from: Monoriu on January 04, 2017, 11:27:52 PM
I don't think robots can pass a civil service exam  :lol:  Do you know what a civil service exam looks like?

Assume there is a scandal.  The opposition tables a question in parliament about it.  In a week's time, the minister will have to answer that question in public, and deal with any follow-up questions.  Now prepare a speech for the minister to deliver, in both Chinese and English, in the parliament.  Also prepare a 1 page summary about the case to explain it clearly and succinctly.  AND, prepare 10 likely questions that the opposition will ask on the spot, AND the answers to those questions.  The aim is to make the minister look as good as possible without committing any extra government staffing or financial resources.  You have two hours to write. 

Quote from: Berkut on January 05, 2017, 08:27:21 AM

Quote from: Monoriu on January 04, 2017, 11:27:52 PM
I don't think robots can pass a civil service exam  :lol:  Do you know what a civil service exam looks like?

Assume there is a scandal.  The opposition tables a question in parliament about it.  In a week's time, the minister will have to answer that question in public, and deal with any follow-up questions.  Now prepare a speech for the minister to deliver, in both Chinese and English, in the parliament.  Also prepare a 1 page summary about the case to explain it clearly and succinctly.  AND, prepare 10 likely questions that the opposition will ask on the spot, AND the answers to those questions.  The aim is to make the minister look as good as possible without committing any extra government staffing or financial resources.  You have two hours to write. 

That sounds like a perfect task for a robot.

You take a bunch of words vaguely related to the question at hand, mix them up, vomit them out on a page, and then run some analysis to make sure that nothing said actually has any actual content, which would surely be unintentional.

I am confident google could do this for you much better than any human.

You could even automate the delivery and reception of said speeches and questions, for that matter.

Quote from: Eddie Teach on January 05, 2017, 08:44:54 AM
How do we know Mono hasn't already been replaced by a robot?  :hmm:

Quote from: Eddie Teach on January 05, 2017, 08:44:54 AM
How do we know Mono hasn't already been replaced by a robot?  :hmm:

Quote from: DGuller on January 05, 2017, 08:50:52 AM

Quote from: Eddie Teach on January 05, 2017, 08:44:54 AM
How do we know Mono hasn't already been replaced by a robot?  :hmm:

He's too creative at pushing our buttons.  Even after all these years he knows how to get us consistently riled up at the hive mind mentality.

QuoteIs American Retail at a Historic Tipping Point?
By MICHAEL CORKERYAPRIL 15, 2017

Along the cobblestone streets of SoHo, Chanel handbags and Arc'teryx jackets are displayed in shops like museum pieces, harking back to the height of the neighborhood's trendiness. But rents there are softening, and the number of vacant storefronts is rising.

Today, some of the most sought-after real estate by retailers is not in SoHo, but five miles away in Red Hook, a gritty Brooklyn enclave with a shipbuilding past. E-commerce merchants are vying to lease part of a huge warehouse space, spanning 11 acres, that would allow them to deliver goods the same day they're ordered online.

The profound reordering of New York's shopping scene reflects a broad restructuring in the American retail industry.

E-commerce players, led by the industry giant Amazon, have made it so easy and fast for people to shop online that traditional retailers, shackled by fading real estate and a culture of selling in stores, are struggling to compete. This shift has been building gradually for years. But economists, retail workers and real estate investors say it appears that it has sped up in recent months.

Between 2010 and 2014, e-commerce grew by an average of $30 billion annually. Over the past three years, average annual growth has increased to $40 billion.

"That is the tipping point, right there," said Barbara Denham, a senior economist at Reis, a real estate data and analytics firm. "It's like the Doppler effect. The change is coming at you so fast, it feels like it is accelerating."

This transformation is hollowing out suburban shopping malls, bankrupting longtime brands and leading to staggering job losses.

More workers in general merchandise stores have been laid off since October, about 89,000 Americans. That is more than all of the people employed in the United States coal industry, which President Trump championed during the campaign as a prime example of the workers who have been left behind in the economic recovery.

The job losses in retail could have unexpected social and political consequences, as huge numbers of low-wage retail employees become economically unhinged, just as manufacturing workers did in recent decades. About one out of every 10 Americans works in retail.

"There is a sea change happening in the retail industry," said Mark Cohen, a former executive at Sears, who now runs the retail studies program at Columbia Business School. "And that is bringing a sea change in employment."

Store closures, meanwhile, are on pace this year to eclipse the number of stores that closed in the depths of the Great Recession of 2008. Back then Americans, mired in foreclosures and investment losses, retrenched away from buying stuff.

The current torrent of closures comes as consumer confidence is strong and unemployment is low, suggesting that a permanent restructuring is underway, rather than a dip in the normal business cycle. In short, traditional retail may never recover.

The reordering should come as no surprise to anyone who has enjoyed the instant gratification of receiving that book or garden hose within 24 hours of ordering it. Or to anyone who has encountered the tired-looking mannequins and haggard sales associates at many department stores.

Modern-day retail is becoming unrecognizable from the glory era of the department store in the years after World War II. In that period, newly built highways shuttling people to and from the suburbs eventually gave rise to shopping malls — big, convenient, climate-controlled monuments to consumerism with lots of parking.

Over time, malls grew to be the size of indoor cities. Minnesota's Mall of America opened in 1992 with a footprint so large that it could fit nine Yankee Stadiums inside.

Now, many of these once celebrated malls are emptying out or being turned into trampoline parks and community colleges. "The retail industry built too much space," said Bruce Batkin, chief executive of Terra Capital Partners, a commercial real estate lender.

Last week, Mr. Batkin got a call from a landlord looking to refinance his shopping center with a 10-year loan. Mr. Batkin passed on the deal because it was too difficult to predict what might happen to occupancy in the property 10 years from now.

"Things are changing so fast in retail that a year needs to be measured in dog years," he said.

Still, there are many investors who are not giving up on the notion that online retail and traditional stores can coexist and even thrive together. Retailers have hoped that their traditional stores, by offering catchy displays and top-notice service, can lure shoppers away from their screens. Some of the best evidence that brick-and-mortar retail is still viable may be Amazon's experimentation with operating physical stores of its own.

In reality, however, some workers say that they will often spend time helping out a customer on the shop floor, only to have that person leave the store and order a product online. That often hits salespeople in the wallet: Many are paid on commission, but only on sales they complete in person in the store.

At Bloomingdale's, employees who are members of the Retail, Wholesale and Department Store Union are arguing that the company should improve how sales staff are compensated for helping facilitate e-commerce business — like helping customers pick up goods in the store that were ordered online.

"You want an in-store experience that will make customers want to come into the store," the union president, Stuart Appelbaum, said. "That requires highly motivated employees."

A Bloomingdale's spokeswoman said the company is negotiating with the union over a new contract in "good faith" and was taking steps to invest in its work force..

The retail industry has always had its ups and downs. Workers frequently hop from one store to another, as styles and brands fall out of fashion. But even to many experienced retail workers, who are used to losing their jobs based on the seasons, this downturn feels different.

Hilda Awuor, 27, lost her job at the Saks Fifth Avenue store in Lower Manhattan last month. After bouncing between jobs in different clothing stores, she said she is now done with retail and is trying to find a different career entirely.

"I really like helping customers create a new style," said Ms. Awuor, who was paid $16 an hour. "But there is no job security anymore."

Some economists say this is how the market is supposed to work. After the recession, retail hiring was a big driver of the recovery. But now that the economy is stronger, retail workers theoretically should be pushed out into potentially higher paying jobs that offer more chances to create wealth.

"This is creative destruction at its best," said Mark Zandi, chief economist at Moody's Analytics. "We are downsizing a part of the economy that is uncompetitive. While painful for those in the middle of it, this is how we grow and wealth is created."

But Mr. Cohen, of Columbia University, said the upending of an entire industry will not be so tidy. Warehouses like the one in Red Hook typically employ a few hundred people, according to Sitex Group, a private equity firm that is expected to close on the property in a few weeks.

While these distribution centers could replace some of the work lost in stores, they likely won't make up the entire difference. That is because much of the operations are automated and require different skills and sensibilities than selling jeans.

"There is a rolling crisis that has emerged in the last couple of years as store closings are being announced," Mr. Cohen said. "People are losing their jobs and have no other place to go.

"Theoretically this is the marketplace rationalizing itself, but in the interim how do people survive?"

QuoteThe retail industry's recent decline may have reached a "tipping point." That was the conclusion of a recent report from the New York Times with potentially far-reaching consequences. Once-bustling shopping malls and department stores are now empty as millions of Americans do their shopping online through businesses that have warehouses but don't operate storefronts. "This transformation is hollowing out suburban shopping malls, bankrupting longtime brands and leading to staggering job losses," the Times reports. "More workers in general merchandise stores have been laid off since October, about 89,000 Americans. That is more than all the people employed in the coal industry."

Retail jobs aren't good jobs, per se; on average, they pay little, provide few benefits, and are notoriously unstable. But roughly 1 in every 10 Americans works in retail, which means millions rely on the industry for their livelihoods. As the Times notes, "The job losses in retail could have unexpected social and political consequences, as huge numbers of low-wage retail employees become economically unhinged, just as manufacturing workers did in recent decades."

Despite this ongoing challenge and threat to millions of ordinary Americans, Washington is silent. What makes this even more striking is it comes at a time when politicians—and a multitude of voices in national media—are preoccupied with the prospects of blue-collar whites and the future of the Rust Belt. That contrast exists for several reasons, not the least of which is a simple one: Who does retail work in this country versus who does manufacturing work.

For those in the latter group, mostly white and mostly male, Donald Trump made their anger, anxiety, and identity the centerpiece of his presidential campaign, promising restoration through better "deals" and aggressive action against foreigners and perceived others. "Dying industries will come roaring back to life," he said in February during his first address to a joint session of Congress. Just weeks before, the president signed legislation repealing rules protecting local waterways from coal mining waste. Surrounded by a group of coal miners, Trump called the regulation "a major threat to your jobs" and said that ending it would save "many thousands American jobs, especially in the mines."

In terms of attention, these workers punch far above their weight class. They constitute a small portion of the American workforce, and yet, elite journalists devote countless words to their lives and communities, while politicians use them and their priorities as a platform for performing authenticity. For those in and around politics, one's connection to "real America" is often judged by one's proximity to these workers and their concerns. Which raises a question: Why them and not those retail workers who face an equally (if not more) precarious future?

One answer is that these jobs are ubiquitous. Retail work is everywhere. And while conditions in this sector are important to the overall economy, they don't define particular communities. (Even as the decline of retail hits small towns especially hard.) Politically, no one is especially invested in them. Not only are jobs in manufacturing and coal tied to specific places, but they predominate in swing states like Pennsylvania, Michigan, and Ohio, offering a strong incentive for ambitious politicians to pander. Likewise, retail work is concentrated where people live: in cities and suburbs. If the gerrymandering and the Electoral College devalues voters in dense areas of the country, then it does the same for workers in those places too.

Another answer is that these jobs are low-skill and lack the physical risk of mining or heavy manufacturing. And as such we tend, as a society, to give little attention and concern to those positions. We see them as expendable positions of low worth. It's one reason for the often-hostile reactions to calls for a higher minimum wage. Anyone can operate a cash register, goes the argument, why should we give them a larger paycheck?

There's one other answer to consider, one that speaks to deep divides in our society. Retail work in malls and shopping centers and department stores is largely work done by women. Of the nearly 6 million people who work in those fields in stores like Sears, Michaels, Target, J.C. Penney, and Payless, close to 60 percent are women. There's another issue to consider. A substantial portion of these workers—roughly 40 percent across the different kinds of retail—are black, Latino, or Asian American.

The Bureau of Labor Statistics doesn't disaggregate this data by race and gender, but it's likely that a large number of those nonwhite workers—if not a majority—are women too. By contrast, heavy manufacturing, industrial, and extraction work is overwhelmingly white and male. What's more, it's tied to a particular image of the standalone (and often unionized) worker who can provide for his family on one income. Americans have historically had an almost romantic attachment to the hard-hat worker, usually white, in a way that we don't to any other profession.

Work is gendered and it is racialized. What work matters is often tied to who performs it. It is no accident that those professions dominated by white men tend to bring the most prestige, respect, and pay, while those dominated by women—and especially women of color—are often ignored, disdained, and undercompensated.

For all of the impersonal economic reasons for the decline of retail, for all the understandable reasons motivating political attention to manufacturing, it's also the case that this is a story of race and gender. A story of who matters in our society; who deserves our collective concern. And if one thing is true in American history, it's that white men have always been among those called "deserving," with other groups struggling to attain that label and the respect it implies, and some—like black women—long stigmatized as inherently unworthy.

The story of our outsize concern for coal and manufacturing, or rather our indifference to the collapse of retail, is inescapably the story of how worth, value, and citizenship are still tied to those traits we can't control.

Quote from: jimmy olsen on April 19, 2017, 06:45:13 PM
Ten percent of jobs are at grave risk, and these are the folks who are already low skilled and vulnerable. Now tell me Minsky, how are we reasonably going to put these folks back to work?

Quote from: CountDeMoney on April 20, 2017, 12:17:22 PM
How the fuck would he know? And besides, he's Wall Street--they feed off these "folks".

Quote from: Admiral Yi on April 20, 2017, 12:20:15 PM

Quote from: CountDeMoney on April 20, 2017, 12:17:22 PM
How the fuck would he know? And besides, he's Wall Street--they feed off these "folks".

You do an excellent Seedy parody.

Quote"Retail square feet per capita in the United States is more than six times that of Europe or Japan,"

Quote from: jimmy olsen on April 19, 2017, 06:45:13 PM
Ten percent of jobs are at grave risk, and these are the folks who are already low skilled and vulnerable. Now tell me Minsky, how are we reasonably going to put these folks back to work?

Quote from: The Minsky Moment on April 20, 2017, 02:47:32 PM

Quote from: jimmy olsen on April 19, 2017, 06:45:13 PM
Ten percent of jobs are at grave risk, and these are the folks who are already low skilled and vulnerable. Now tell me Minsky, how are we reasonably going to put these folks back to work?

The root problem here is not robots but the fact that retail was vastly overbuilt in the US.  In comparison with other OECD countries, the US has far more mall space per person.  For example, until recently there was about 4 times as much retail space per person in the US as in Canada.  One of the drivers was the fact that companies nominally in the retail business in reality were really real estate investment companies that also happened to sell some stuff.  The value of the RE holdings dwarfed the value of the underlying retail operations, and a whole industry of sale-leaseback transactions sprouted up with private equity leading the charge.  Then in 08-09 when retail got killed, interest rates were so low that banks were willing to roll-over rather than foreclose.  That prolonged the adjustment and with the rate environment only now starting to shift, there is a backlog of wounded retailers that need to be worked out.

As for what to do, here's one thing that won't work - "bringing back" manufacturing.  Manufacturing is a lot more capital intensive.  So for example if Trump's "border adjustment" tax went through, retail would be savaged even worse and the resulting job loss would exceed whatever employment would be added in manufacturing.

A nice infrastructure boom OTH . . .

Quote from: jimmy olsen on April 21, 2017, 08:02:45 AM
That was a lot of words to say "they're not going to be put back to work".

Quote from: DGuller on April 21, 2017, 08:11:33 AM

Quote from: jimmy olsen on April 21, 2017, 08:02:45 AM
That was a lot of words to say "they're not going to be put back to work".

Even vastly more words to say nothing of the kind.  :huh:

Quote from: jimmy olsen on April 21, 2017, 08:23:45 AM

Quote from: DGuller on April 21, 2017, 08:11:33 AM

Quote from: jimmy olsen on April 21, 2017, 08:02:45 AM
That was a lot of words to say "they're not going to be put back to work".

Even vastly more words to say nothing of the kind.  :huh:

He said retail is dead and a manufacturing boom won't put them back to work.

He does allow that an infrastructure boom would put people to work, but this congress isn't going to pass an infrastructure bill. And even if it did 60% of the workers at risk are women, and I'm sure some decent portion of the men are over 35 or simply not fit to enter the construction workforce, so most of the people hired to do that work will be from outside the group we're talking about.

Quote from: Monoriu on April 21, 2017, 08:43:09 AM

Quote from: jimmy olsen on April 21, 2017, 08:23:45 AM

Quote from: DGuller on April 21, 2017, 08:11:33 AM

Quote from: jimmy olsen on April 21, 2017, 08:02:45 AM
That was a lot of words to say "they're not going to be put back to work".

Even vastly more words to say nothing of the kind.  :huh:

He said retail is dead and a manufacturing boom won't put them back to work.

He does allow that an infrastructure boom would put people to work, but this congress isn't going to pass an infrastructure bill. And even if it did 60% of the workers at risk are women, and I'm sure some decent portion of the men are over 35 or simply not fit to enter the construction workforce, so most of the people hired to do that work will be from outside the group we're talking about.

Then you are also saying they won't be put back to work?

Quote from: jimmy olsen on April 21, 2017, 08:23:45 AM

Quote from: DGuller on April 21, 2017, 08:11:33 AM

Quote from: jimmy olsen on April 21, 2017, 08:02:45 AM
That was a lot of words to say "they're not going to be put back to work".

Even vastly more words to say nothing of the kind.  :huh:

He said retail is dead and a manufacturing boom won't put them back to work.

He does allow that an infrastructure boom would put people to work, but this congress isn't going to pass an infrastructure bill. And even if it did 60% of the workers at risk are women, and I'm sure some decent portion of the men are over 35 or simply not fit to enter the construction workforce, so most of the people hired to do that work will be from outside the group we're talking about.

Quote from: Berkut on April 21, 2017, 08:54:53 AM
It's all going to be fine though, all those people working at Borders and Wal-Mart can just get jobs programming robots.

Quote from: Berkut on April 21, 2017, 08:54:53 AM

It's all going to be fine though, all those people working at Borders and Wal-Mart can just get jobs programming robots.

Quote from: jimmy olsen on April 21, 2017, 08:02:45 AM
That was a lot of words to say "they're not going to be put back to work".

Quote from: The Brain on April 21, 2017, 09:22:25 AM
Everyone working at Borders will be fine.

Quote from: Admiral Yi on April 21, 2017, 05:26:12 PM
The jobs will come as long as there are not impediments to the market clearing.  Whether we will be happy with the pay is another question.

Quote from: DGuller on April 21, 2017, 05:41:53 PM
I think there are a lot of assumption hidden behind that certainty.  Assumptions that so far have not been violated significantly, but there is no guarantee that this state of things will continue indefinitely.

Quote from: Admiral Yi on April 21, 2017, 05:48:24 PM

Quote from: DGuller on April 21, 2017, 05:41:53 PM
I think there are a lot of assumption hidden behind that certainty.  Assumptions that so far have not been violated significantly, but there is no guarantee that this state of things will continue indefinitely.

I think the only assumptions my conclusion requires are that human labor has non zero value, and that capital does not have infinite value.

Quote from: DGuller on April 21, 2017, 06:08:16 PM
At least one other assumption seems to be that human labor has zero cost to the provider.

Quote from: Admiral Yi on April 21, 2017, 06:15:08 PM

Quote from: DGuller on April 21, 2017, 06:08:16 PM
At least one other assumption seems to be that human labor has zero cost to the provider.

I don't follow.  By provider I assume you mean the worker?

Quote from: Admiral Yi on April 21, 2017, 08:07:39 PM
OK, I get it.  You're talking about labor value less than subsistence.

It would be helpful if sometimes you weren't so opaque.

Quote from: alfred russel on April 21, 2017, 09:43:08 PM

Quote from: Admiral Yi on April 21, 2017, 08:07:39 PM
OK, I get it.  You're talking about labor value less than subsistence.

It would be helpful if sometimes you weren't so opaque.

Says the guy with random nicknames for people I don't remember and obscure references for events.

Quote from: Admiral Yi on April 22, 2017, 01:57:53 AM
Fuck all y'all.

Quote from: DGuller on April 21, 2017, 06:15:38 PM

Quote from: Admiral Yi on April 21, 2017, 06:15:08 PM

Quote from: DGuller on April 21, 2017, 06:08:16 PM
At least one other assumption seems to be that human labor has zero cost to the provider.

I don't follow.  By provider I assume you mean the worker?

Yes.

Quote from: jimmy olsen on June 01, 2017, 08:44:59 PM
A look into your future!

https://willrobotstakemyjob.com/

Quote from: CountDeMoney on June 01, 2017, 10:41:26 PM
I'd like to know exactly how "Technical Writer" can be looking at 89% probability.   It's English, not Mathematics.

Quote from: Maximus on June 02, 2017, 10:48:52 AM

Quote from: CountDeMoney on June 01, 2017, 10:41:26 PM
I'd like to know exactly how "Technical Writer" can be looking at 89% probability.   It's English, not Mathematics.

I could tell you, but you might get autism.

Quote from: CountDeMoney on June 02, 2017, 11:03:15 AM

Quote from: Maximus on June 02, 2017, 10:48:52 AM

Quote from: CountDeMoney on June 01, 2017, 10:41:26 PM
I'd like to know exactly how "Technical Writer" can be looking at 89% probability.   It's English, not Mathematics.

I could tell you, but you might get autism.

WORDS MATTER

Quote from: Eddie Teach on June 02, 2017, 11:38:18 AM
Robots can learn to out-viking you, I'm sure.

QuoteMcDonald's hits all-time high as Wall Street cheers replacement of cashiers with kiosks

Cowen says McDonald's will upgrade 2,500 restaurants to its "Experience of the Future" technology by year-end, which includes digital ordering kiosks.

The firm raises its rating on McDonald's to outperform from market perform and price target for the shares to $180 from $142.

Same store sales estimate for 2018 raised to 3 percent from 2 percent.

Tae Kim   | @firstadopter
Tuesday, 20 Jun 2017 | 11:30 AM ET


McDonald's shares hit an all-time high on Tuesday as Wall Street expects sales to increase from new digital ordering kiosks that will replace cashiers in 2,500 restaurants.

Cowen raised its rating on McDonald's shares to outperform from market perform because of the technology upgrades, which are slated for the fast-food chain's restaurants this year.

McDonald's shares rallied 26 percent this year through Monday compared to the S&P 500's 10 percent return.

Andrew Charles from Cowen cited plans for the restaurant chain to roll out mobile ordering across 14,000 U.S. locations by the end of 2017. The technology upgrades, part of what McDonald's calls "Experience of the Future," includes digital ordering kiosks that will be offered in 2,500 restaurants by the end of the year and table delivery.

"MCD is cultivating a digital platform through mobile ordering and Experience of the Future (EOTF), an in-store technological overhaul most conspicuous through kiosk ordering and table delivery," Charles wrote in a note to clients Tuesday. "Our analysis suggests efforts should bear fruit in 2018 with a combined 130 bps [basis points] contribution to U.S. comps [comparable sales]."

He raised his 2018 U.S. same store sales growth estimate for the fast-food chain to 3 percent from 2 percent.

The analyst raised his price target for McDonald's to $180 from $142, representing 17.5 percent upside from Monday's close. He also raised his 2018 earnings-per-share forecast to $6.87 from $6.71 versus the Wall Street consensus of $6.83.

"MCD has done a great job launching popular innovations within the context of simplifying the menu, while introducing more effective value initiatives that have recently begun to improve the brand's value perceptions," he wrote.

QuoteBig Mac, smaller effort: Uber to run McDonald's deliveries in UK
Burger giant teams up with UberEats to launch trial of McDelivery service in parts of London, Nottingham and Leeds

Fancy a Big Mac but just can't be bothered to get up off the sofa? McDonald's has finally answered your prayers– if you live in parts of London, Nottingham and Leeds at least.

The fast food giant has launched its long-awaited "McDelivery" trial in the UK after teaming up with Uber's food delivery service, UberEats.

McDonald's will offer the service from 22 outlets across the capital and another 10 restaurants in Leeds and Nottingham – although customers will have to live within a 1.5 mile radius of a restaurant.

Customers can place orders through the UberEats app between 7am and 2am.

Claude Abi-Gerges, a McDonald's franchisee who has five London outlets taking part in the trial, said the service would offer a "new level of convenience" to fit around customers' busy lives.

McDonald's said it would be monitoring the trial closely to see whether it proved popular.

Mathieu Proust, general manager of UberEats, said the trial would let people "get the food they want" quickly and reliably.

The launch comes after KFC launched home deliveries from 30 outlets in greater London via the Just Eat platform earlier this year.

Growth in the number of ready-to-eat food deliveries was stronger than that for the broader eating out market last year, according to analysts at NPD Group.

The McDonald's move follows similar tie-ups with Uber in the US, while the chain already delivers in China and Singapore.

Early last year the company said it would experiment with table service and cooked-to-order gourmet burgers at hundreds of UK restaurants, in a bid to head off competition from upmarket rivals such as Byron.

In April McDonald's said quarterly profits rose by a better than expected 8% to $1.21bn, despite a 3.9% fall in revenue to $5.68bn. Operating costs dropped nearly 12%.

Sales at US restaurants open for more than a year rose 1.7% in the three months to March 2017.

The increase comes after the chief executive, Steve Easterbrook, who is British, launched a turnaround plan involving slashing overheads, weeding out underperforming restaurants, offering the breakfast menu all day and switching US restaurants to chicken raised without human antibiotics.

Quote from: jimmy olsen on June 22, 2017, 10:08:37 AM
Suck it Minsky, the proletarian youth is screwed.

Quote from: The Minsky Moment on June 22, 2017, 12:22:30 PM
If the future of our workforce was supposed to be fastfood counter service, we were already screwed to begin with.

Quote from: Valmy on June 22, 2017, 01:03:36 PM

Quote from: The Minsky Moment on June 22, 2017, 12:22:30 PM
If the future of our workforce was supposed to be fastfood counter service, we were already screwed to begin with.

Are you under the impression that if this works no other service industries will adopt it as well?

Quote from: jimmy olsen on June 22, 2017, 10:08:37 AM
Suck it Minsky, the proletarian youth is screwed.

http://www.cnbc.com/2017/06/20/mcdonalds-hits-all-time-high-as-wall-street-cheers-replacement-of-cashiers-with-kiosks.html

QuoteMcDonald's hits all-time high as Wall Street cheers replacement of cashiers with kiosks

Cowen says McDonald's will upgrade 2,500 restaurants to its "Experience of the Future" technology by year-end, which includes digital ordering kiosks.

The firm raises its rating on McDonald's to outperform from market perform and price target for the shares to $180 from $142.

Same store sales estimate for 2018 raised to 3 percent from 2 percent.

Tae Kim   | @firstadopter
Tuesday, 20 Jun 2017 | 11:30 AM ET


McDonald's shares hit an all-time high on Tuesday as Wall Street expects sales to increase from new digital ordering kiosks that will replace cashiers in 2,500 restaurants.

Cowen raised its rating on McDonald's shares to outperform from market perform because of the technology upgrades, which are slated for the fast-food chain's restaurants this year.

McDonald's shares rallied 26 percent this year through Monday compared to the S&P 500's 10 percent return.

Andrew Charles from Cowen cited plans for the restaurant chain to roll out mobile ordering across 14,000 U.S. locations by the end of 2017. The technology upgrades, part of what McDonald's calls "Experience of the Future," includes digital ordering kiosks that will be offered in 2,500 restaurants by the end of the year and table delivery.

"MCD is cultivating a digital platform through mobile ordering and Experience of the Future (EOTF), an in-store technological overhaul most conspicuous through kiosk ordering and table delivery," Charles wrote in a note to clients Tuesday. "Our analysis suggests efforts should bear fruit in 2018 with a combined 130 bps [basis points] contribution to U.S. comps [comparable sales]."

He raised his 2018 U.S. same store sales growth estimate for the fast-food chain to 3 percent from 2 percent.

The analyst raised his price target for McDonald's to $180 from $142, representing 17.5 percent upside from Monday's close. He also raised his 2018 earnings-per-share forecast to $6.87 from $6.71 versus the Wall Street consensus of $6.83.

"MCD has done a great job launching popular innovations within the context of simplifying the menu, while introducing more effective value initiatives that have recently begun to improve the brand's value perceptions," he wrote.

Quote from: Barrister on June 23, 2017, 12:30:48 PM
Whether you believe them or not, but McD's said when they were installing those kiosks in Edmonton that they were actually hiring additional staff for all of those reasons.

Quote from: DontSayBanana on June 25, 2017, 09:01:51 AM

Quote from: Barrister on June 23, 2017, 12:30:48 PM
Whether you believe them or not, but McD's said when they were installing those kiosks in Edmonton that they were actually hiring additional staff for all of those reasons.

Yes, I've had this discussion regarding self-driving trucks. It's not so much a labor reduction as a labor shift if you don't automate the ENTIRE process. Kiosks = less wait time = more orders to fill at any given time = more kitchen staff to prep orders, the same way self-driving trucks = more frequent shipments = higher volume to unload = more receiving personnel at the receiving end and more order pickers/packers at the sending end.

The problems are the wage reduction from reducing jobs that pay more and expanding jobs that pay less.  The company's viewpoint is that workers haven't earned their share of the increased profits, so rather than prop their workforce up with better wages, they crow about reduced labor costs as bottom-line growth.

Quote from: Tyr on June 26, 2017, 04:20:48 AM
Read this one today
https://www.linkedin.com/pulse/artificial-intelligence-death-indian-sector-harpreet-singh

Yup. Those guys moaning about stem people and how coding is the path to riches... How wrong they are

QuoteAutomation often replaces human labor, but very rarely in the last sixty years has it eliminated an entire occupation.

Only one of the 270 detailed occupations listed in the 1950 US Census has since been eliminated by automation, according to a working paper by Harvard economist James Bessen. The one exception: elevator operator.

While the government has removed other occupations from the Census due to factors like lack of demand (boardinghouse keepers) and technological obsolescence (telegraph operators), only elevator operators owe their occupation's demise mostly to automation, Bessen found.

...

Quote from: garbon on June 26, 2017, 06:54:35 AM
I could easily say that one day everyone will be on basic income and everyone will be free to pursue interests in the humanities and liberal arts.

QuoteAnd know, I don't know anyone I'd qualify as super elite. I'm not Mart with his movers and shakers or MSil with the Botswanan ambassador.

Quote from: CountDeMoney on June 26, 2017, 07:14:22 AM

Quote from: garbon on June 26, 2017, 06:54:35 AM
I could easily say that one day everyone will be on basic income and everyone will be free to pursue interests in the humanities and liberal arts.

You can, but you'd be wrong.

QuoteAnd know, I don't know anyone I'd qualify as super elite. I'm not Mart with his movers and shakers or MSil with the Botswanan ambassador.

STFU, Stanford.

Quote from: garbon on June 26, 2017, 07:33:57 AM
Oh so by 'super elite' you mean anyone you are annoyed at. Got it. After all, nothing super elite about a 9 to 5.

Quote from: garbon on June 26, 2017, 06:54:35 AM
I could easily say that one day everyone will be on basic income and everyone will be free to pursue interests in the humanities and liberal arts.

Quote from: Ed Anger on June 26, 2017, 07:58:13 PM
Am I: super elite?

Quote from: Ed Anger on June 26, 2017, 08:19:33 PM
Hey! Don't chase away my sycophants!

Quote from: Monoriu on June 26, 2017, 08:29:25 PM

Quote from: Ed Anger on June 26, 2017, 08:19:33 PM
Hey! Don't chase away my sycophants!

I know I am not featured in your will, and I won't be :weep:

Quote from: CountDeMoney on June 26, 2017, 06:30:23 AM

Quote from: Tyr on June 26, 2017, 04:20:48 AM
Read this one today
https://www.linkedin.com/pulse/artificial-intelligence-death-indian-sector-harpreet-singh

Yup. Those guys moaning about stem people and how coding is the path to riches... How wrong they are

Still, just like here and based on the population, even more so in India, the humanities and the liberal arts is slowly becoming the path and domain of the super elite class, so it's not going to help your average Vijay Lassi Sixpack.

Quote
When the Chinese clothing manufacturer Tianyuan Garments Company opens its newest factory in 2018, it will be in Arkansas, not China, and instead of workers hunched over sewing machines, the factory will be filled with fully autonomous robots and their human supervisors.


Once the system is fully operational, each of the 21 production lines in the factory will be capable of making 1.2 million T-shirts a year, at a total cost of production that can compete in terms of cost with apparel companies that manufacture and ship clothing from the lowest-wage countries in the world. The factory will be one of the first to use a technology that could herald immense changes in how the apparel industry works.

"Our goal is giving a tool for manufacturers to manufacture convenient to their customers," says Palaniswamy Rajan, CEO of SoftWear Automation, the company that developed the robotic technology that will be used in the new plant.

Sewbot–SoftWear Automation's clothes-making robot–was developed at Georgia Tech's Advanced Technology Development Center in a process that began a decade ago. In 2012, researchers got a grant from the Defense Department's tech innovation wing DARPA to develop the concept and formed a company to commercialize the technology. By 2015, the company was selling a more basic version of the robot that could make bath mats and towels. The newest version, to be deployed in the Little Rock factory, can make T-shirts and partially sew jeans.


Sewing technology in apparel factories, in the most basic respects, has changed relatively little since sewing machines were invented in the 1800s. While others have attempted to automate particular steps of the process of sewing, it's only now that technology is becoming capable of creating an entire garment autonomously.

SoftWear's technology uses computer vision to watch and analyze fabric so the system can move the material while sewing. "What we did was approach it and look at it from how a seamstress actually operates," says Rajan. "The first thing they do is use their eyes, and based on their eyes, they do micro and macro manipulations of the fabric with their fingers and hands and elbows and feet. So a robot replicates all of those functions."

Each T-shirt production line is roughly the length of a typical factory sewing line staffed by humans, or about 70 feet. Along a table, robots perform each step of making a shirt–adding a label, sewing a shoulder seam, adding sleeves, and so on–while the system's vision technology guides the fabric.

The company is focused first on T-shirts and jeans because the robots' strength is producing huge quantities of clothing. "People buy 11 billion T-shirts a year," says Rajan. "That's an interesting market where automation makes sense, where our robots make sense, because our robots produce a very high volume of product."

While the technology is still developing, and will eventually make more complicated items of clothing, Rajan believes that some higher-end clothing will always be made by humans. "We'd never do a bridal dress," he says.

In this respect, he argues that the technology could have a positive impact in countries with large garment manufacturing industries. Workers might shift into doing more artisanal work, at higher wages. If robots make it economical to manufacture more clothing in the U.S. or Europe, where regulations better protect both the environment and labor, low-wage countries might be forced to improve their own performance to compete. "It might create the pressure among them to treat their workers fairly," Rajan says.

In practice, the transition is likely to be messier. Sewing robots may only threaten certain jobs in developing countries; the machines are expensive (the company won't disclose the cost) and the company is initially only selling them in the U.S., where manufacturers can save money on the total process because they can avoid factors such as higher industrial electricity bills in some other countries, and can benefit from a "Made in USA" label (the military, for example, is required to buy clothing that's made in the U.S., while factories that can produce that clothing are dwindling, and the average garment worker is nearing retirement).

They can also have faster turnarounds on orders. For factories in India or China producing cheap T-shirts for a local market, cheap local labor will still make more sense than investing in robots. But some jobs are likely to be displaced. That displacement may grow as others develop similar technology and the cost drops. Another designer is also working on a T-shirt-sewing robot. Amazon filed a patent in April 2017 for "stitch on demand" technology that would sew clothing after an order is placed.

In Bangladesh, where garment workers make far less than what is considered a living wage–often enduring abuse and working in the kind of conditions that led to the 2013 factory collapse that killed more than 1,000 people–the majority of the country's exports are clothing. More than 4 million people work in the industry. If H&M and Walmart choose to relocate production of some apparel to North America and Europe, people in Bangladesh and other low-wage countries will probably lose jobs, though, in theory, they might also have an opportunity for something better.

"It's very hard to know how things will play out," says Sanchita Saxena, executive director of the Institute for South Asian Studies at the University of California-Berkeley. "My guess is that there's going to be a lot of displacement without any sort of safety net in place, because that's how these countries work."

In Little Rock, Arkansas, the new Tianyuan factory will eventually provide 400 jobs. While the robots are fully autonomous, three to five people will be employed to work with each production line; others will work in logistics and other parts of the factory. SoftWear says it has calculated that a robot can create between 50 and 100 jobs downstream, either within factories or in related industries. Some manufacturers may choose to begin buying more local cotton, for example, to use in U.S. factories, increasing farming jobs.

By producing closer to consumers, and by reducing material waste as it sews, the technology can also reduce brands' carbon footprints. Fashion for Good, an initiative to improve the sustainability of the fashion industry, calculated that the Sewbot can help cut emissions by around 10%, and is supporting SoftWear through a scaling program.

Rajan believes that, on balance, the robot will have a positive impact, both on labor and the environment. (In contrast, one of the first inventors of a sewing machine, in 1832, decided to bury his invention because he was worried about the potential to put seamstresses and tailors out of work.) As another 2.5 billion people are added to the global population, we'll need more clothes, and apparel is one of the most polluting industries–the robot can help produce those clothes with less pollution. "The efficiencies we can bring are important for humanity's survival," Rajan says.

Quote from: Eddie Teach on August 27, 2017, 08:08:31 PM
Because we haven't transitioned to a post labor society yet.

Quote from: Monoriu on August 27, 2017, 08:05:52 PM
What strikes me most, is I remember a time when people looked forward to technological change with optimism and enthusiasm.  When I was a kid, people wanted more computerisation and automation, because that would make our lives better.  Now every time AI and robots are mentioned, people are worried about jobs. 

Quote from: Monoriu on August 27, 2017, 10:53:26 PM
I am not too worried.  Who knows what will happen in 200 years, but I really doubt if a post-scarcity economy will happen in our lifetimes.  You still need raw materials and energy for the machines.  Things like land will always be scarce.  You can't just build your dream house as there is not enough land to build it on.

Quote from: Eddie Teach on August 27, 2017, 11:11:19 PM

Quote from: Monoriu on August 27, 2017, 10:53:26 PM
I am not too worried.  Who knows what will happen in 200 years, but I really doubt if a post-scarcity economy will happen in our lifetimes.  You still need raw materials and energy for the machines.  Things like land will always be scarce.  You can't just build your dream house as there is not enough land to build it on.

As long as you're not in a major city or tourist area, the land will be cheaper than the materials.

And why should you be worried? A post scarcity economy would be a good thing.

Quote from: Eddie Teach on August 27, 2017, 11:45:24 PM
Advancement will slow regardless. Knowledge advances used to be made by affluent eccentrics conducting experiments for fun in their homes. Now they take teams of people who've spent twenty years learning highly specialized knowledge using technological devices they barely understand.

Quote from: Zanza on August 28, 2017, 01:09:12 AM
Regarding Tim's article: automatization will cost a lot of jobs in the third world. When robots become cheaper than third world workers for stuff that is currently done there, it makes no sense to build a factory staffed with robots far away from markets, from maintenance service personnel and in unstable political or legal frameworks, so those robotic factories will be built in the West first. Adidas for example has started making shoes in Germany again - with robots of course.

Quote from: CountDeMoney on June 26, 2017, 08:35:14 PM
"...And to Xiacob, I hereby bequeath my coolie, Monoriu, who he may release into the wild as he sees fit."

Quote from: Monoriu on September 11, 2017, 10:38:06 PM
Wife is starting to use Starbucks app to order drinks.  So far the results have been fantastic.  She orders ahead and skips the waiting and payment stages.  When she arrives at Starbucks all she needs to do is to pick up her drink.  This overcomes Starbuck's greatest weakness, which is long waiting times.  I think this has great potential and can save a lot of waiting and labour for all take-away orders.  I hope McDonald's and other fast food places adopt the technology as well.

Quote from: Tonitrus on January 30, 2019, 05:59:27 AM
Coffee vending machines been around for decades too.  But you can't hang out at a coffee vending machine and be seen in public on your laptop.

Quote from: Monoriu on January 30, 2019, 06:45:59 AM
I was pleasantly surprised when the ramen shop I frequent made me pick up a QR code before I queued up for a table.  I scanned the code while I waited and ordered the food online.  When I am seated, I add the table code.  Then the food is brought to my table.

Seriously, companies that still worry about the human touch need to face reality.  The average Starbucks queue consists of twenty people.  The ramen shop I mentioned has three waiters for a hundred customers.  They just silently make coffee and run between the kitchen and the tables anyway.  At least a robot is faster, cheaper and more reliable.

Quote from: Tamas on January 30, 2019, 06:02:31 AM

Quote from: Tonitrus on January 30, 2019, 05:59:27 AM
Coffee vending machines been around for decades too.  But you can't hang out at a coffee vending machine and be seen in public on your laptop.

:yes:

Also harder to charge 3-4 pounds for a 20-pence coffee when it is dispensed by a machine instead of a "barrista" who can oh so expertly put the coffee in the machine and press the applicable button.

Quote from: Savonarola on February 08, 2019, 10:58:01 AM
Not only are robots going to take your job; they're going to take your dog's job as well:

Sony Upgrading Aibo With New Home Security Features, API Access (https://spectrum.ieee.org/automaton/robotics/home-robots/sony-upgrading-aibo-with-new-home-security-features-api-access)

Quote from: Valmy on February 08, 2019, 10:59:48 AM
Wouldn't just a regular security system work far better than a toy dog security system?

Quote from: Valmy on February 08, 2019, 10:59:48 AM

Quote from: Savonarola on February 08, 2019, 10:58:01 AM
Not only are robots going to take your job; they're going to take your dog's job as well:

Sony Upgrading Aibo With New Home Security Features, API Access (https://spectrum.ieee.org/automaton/robotics/home-robots/sony-upgrading-aibo-with-new-home-security-features-api-access)

Wouldn't just a regular security system work far better than a toy dog security system?

Quote
The Future Of Sales: What If The Best Salesperson Is A Robot?


In a recent episode of Last Week Tonight, host John Oliver tackled growing fears surrounding job displacement due to automation. "What do you want to do when you grow up?" he asked a bevy of adorable 4-

and 5-year-olds who supplied the typical answers: pilot, lawyer, doctor — and of course, mermaid doctor.

Pouring water on these little kids' dreams — and those of adults alike, Oliver cited an alarming University of Oxford study predicting up to 50 percent of human jobs are at risk of being usurped by robots. (Although maybe not the much-coveted mermaid doctor position.) By the sketch's end, Oliver made a prediction that other pundits have suggested: In the future "safer" careers will involve non-routine, specialized work involving creativity and emotional intelligence (EQ.)

Much of what I have learned from cowriting the upcoming book, Own the A.I. Revolution: Unlock Your Artificial Intelligence Strategy to Disrupt Your Competition with U.N. AI advisor Neil Sahota has confirmed the truth of Oliver's assertion. Many experts have told us that market forces in the 4th Industrial Revolution will expand the need for humans capable of understanding and responding to others' emotional states. Yet, what if computers could learn to detect and display empathy better than us?

Awareness of this possibility led tech pioneer Scott Sandland to co-found Cyrano.ai, combining AI and EQ for commercial innovation. A Southern California-based entrepreneur, Sandland is a renown hypnotherapist who sees the value of training machines to understand the richness of language, specifically subtext, to communicate emotions. "For a long time now, computers possessed decent voice recognition capable of understanding human speech," says Sandland. "But language is more complex than the literal words we use. Meaning can also be communicated through tone, context, cultural filters, and subtext."


To illustrate what he means by subtext, Sandland cites the example of a friend inviting you to their Super Bowl party. If you say, "I'll try to be there," what you're really saying is, "Thanks, but I probably won't come." Your non-committal response signals to your pal the unlikelihood that you will be eating jalapeno poppers on his couch next Sunday. "You were being polite in your reply," Sandland explains, "which any person capable of reading social cues would pick up on. What we're doing now at Cyrano is teaching machines to detect such nuance because it likely contains the real message being communicated."

Devoid of brains evolved to detect the slightest intonation change to reveal how another is feeling, Sandland and his team trained their computers to inspect textual clues for emotional states, including length of response, directness, the type and variety of words chosen, deflection, and the presence or lack of commitment words. As Disruptive Technology Director at Elsevier Labs Paul Groth, Ph.D., suggests, data is key to functional machine learning. Cyrano's A.I., therefore, learned to detect linguistic clues by reading transcripts between prospects and car dealership representatives. In time, their system constructed an algorithm to predict if a prospect would buy or not simply based on the words they used in an online interaction.

Let's step back for a moment and allow this idea to sink in. What Cyrano's company does is nothing short of extraordinary. In essence, the team has taught a computer to determine the inner emotional states of a person — including their likelihood of buying from you — all based on as little as the words typed to a sales bot. Now, just imagine how much better an AI's closing rate might be if it had even more data to utilize.

For a glimpse of what's possible, meet Cheri Tree. Tree co-founded Codebreaker Technologies  Technologies, Inc. with Esther Wildenberg, the company's president. As Tree describes in her book, Why They Buy, she grew up loving the rush of sales — even little ones like those she made selling snacks to her peers at boarding school. However, she hit a wall in her fledgling career as a financial advisor by following traditional sales advice. "Experts will tell you sales is a numbers game," says Tree. "They say in order to get more yeses, you have to get more nos. I say that's one of the greatest myths ever told because the truth is to get more yeses you have to get more yeses, not more nos."

The next logical question would be: So how did you get those yeses?

To answer this, Tree invented a scientifically validated assessment methodology called B.A.N.K.; it has been featured at some of the largest business conferences around the world, at Harvard University, and has been backed by research from San Francisco State University. "You may already be familiar with DISC or MBTI," says Tree. "I essentially reverse-engineered personality science and rather than building it using psychology, I built it using BUYology, the science of buying behavior. Instead of assessing who you are, I built an assessment based on who your customer is, based on four personality types: Blueprint, Action, Nurturing and Knowledge. Our focus is on why they buy and what triggers the yes and tripwires the no."

Drawing on the same realization as Sandland, Tree recognized the secret to sales involves communication mastery. Eschewing the prevailing orthodoxy suggesting a salesperson needs to simply work on their presentation, Tree recognized the Dale Carnegie-esque truth that Sandland's empathy-driven bots thrive on: sales occur most frequently when the values between a buyer and seller are aligned. She often cites a study done by the Chally Group that only 18 percent of buyers will buy from a salesperson who doesn't match the buyer's personality type versus an 82 percent success rate when personality types are aligned. Lacking the empathic mastery displayed by Cyrano's A.I. bots, many underperforming salespeople, therefore, end up repeating the same message, hoping the sheer number of attempts will yield positive results and subjecting themselves to the proverbial numbers game.

As any veteran cold-caller will attest, following a numbers approach can be fruitful — but also time-consuming and demoralizing. Why bother, asks Tree when you can shortcut the process and gain better results (as much as 300% or higher) by knowing your prospect better. "The B.A.N.K. system is based on a value system," says Tree. "You can't just automatically know what someone values. You can certainly make assumptions, but why B.A.N.K. has been so powerful for sales is that it reveals the priorities of its prospects."

Up until now, Tree and her many adherents have been able to determine the buying habits of their prospects within 90 seconds by using a card system. Whether meeting face-to-face or taking a quick online assessment, prospects are given the opportunity to select which of the four personality types best represent them in order of importance. They can decide if they view themselves as someone who prioritizes stability and structure (Blueprint), a full-speed-ahead mover/shaker risk-taker, (Action), a warm and friendly relationship-driven type (Nurturing), or an analytical, logical thinker (Knowledge).

"We found every customer is not just one of these four, they're actually a combination of all four," says Tree. "Therefore, each person has their own B.A.N.K. code. Think of a B.A.N.K. code like a PIN code to your debit card. Every human has a four-digit B.A.N.K. code. Ultimately, there are 24 combinations, which means the average salesperson has roughly a 4 percent chance of speaking to their customer in their exact code — which isn't very high."

B.A.N.K. Code seeks to dramatically increase sales efficacy from a dismal 4 percent to something much higher, which is where Cyrano comes in. Within the past year, Sandland and Tree have joined to create DAVINCI. Powered by Cyrano and informed by Tree's personality methodology, it will be the world's first digital agent capable of deciphering a prospect's code. Using a proprietary algorithm, it can predict a person's buying behavior in nanoseconds.

"Here's an example of how this works," says Sandland. "Imagine you have been courting a prospect for some time. DAVINCI can take a handful of emails this individual has written you and with a push of a button determine this person's code. But that's not all. It can even recommend how to tailor your written responses so as to best align with your prospect's values. For example, after I've written my reply email, the system can tell me if I'm speaking my customer's language. If I'm not, it will automatically tell me how to rewrite the email similar to the way A.I. autocompletes sentences."

This type of A.I.-assisted sales guidance only hints at the future of DAVINCI's offerings. Right now, it's being rolled out to analyze text, but it will also work with voice input and video. In time, its sophisticated analysis will encompass dozens more metrics, measuring multiple aspects of personality to best determine what will ultimately lead to a yes. Based on these capabilities, both Sandland and Tree agree computers will soon outperform the best salespeople. Beyond the simple fact, AI is incapable of possessing an ego or growing weary of a lengthy sales encounter, it is endowed with a vast database of questions, replies, and responses it has accumulated over time. As a result, it can draw on historic patterns to determine the best course of action. Or to use another acronym — A.B.C. — the one Alec Baldwin's character employs in the movie, Glengarry Glen Ross, AIs can really "Always Be Closing."

Returning to the subject of automation raised at the beginning of this article, does the emergence of DAVINCI portend yet another setback for human workers? Does witnessing how well a computer can perform sales mean we must throw up our hands, surrendering to our empathy-wielding, personality-assessing, sales closing machine overlords? Not at all. Instead, technological advances promise yet one more tool in humanity's arsenal. Besides, as evidenced by the work DAVINCI is doing, the best way to stay competitive in tomorrow's workforce is to learn the skills Cyrano and B.A.N.K. rely on, such as EQ, creativity, and adaptability.

(PS: After writing this article, I ran my own text through the DAVINCI to learn my BANK score. Here it is: KNBA. DAVINCI is launching to the public in July 2019 at the company's conference, BANKICON.com. If you would like to learn more or crack your code, please visit: codebreakertech.com.)

Quote from: The Brain on March 14, 2019, 01:23:35 AM
Do robots even drink coffee?

Quote from: Valmy on February 08, 2019, 10:59:48 AM

Quote from: Savonarola on February 08, 2019, 10:58:01 AM
Not only are robots going to take your job; they're going to take your dog's job as well:

Sony Upgrading Aibo With New Home Security Features, API Access (https://spectrum.ieee.org/automaton/robotics/home-robots/sony-upgrading-aibo-with-new-home-security-features-api-access)

Wouldn't just a regular security system work far better than a toy dog security system?

Though I am looking forward to "Detroit: Becoming Canine"

Quote from: Savonarola on January 31, 2020, 03:53:30 PM
Boeing has doomed us all  :(

Boeing's Autonomous Fighter Jet Will Fly Over the Australian Outback (https://spectrum.ieee.org/aerospace/military/boeings-autonomous-fighter-jet-will-fly-over-the-australian-outback)

I like how the US Air Force's armed drone is called Skyborg (https://www.defensenews.com/air/2019/05/22/under-skyborg-program-f-35-and-f-15ex-jets-could-control-drone-sidekicks/).  Once it becomes self-aware we will be assimilated.   :)

Quote from: Savonarola on January 31, 2020, 03:53:30 PM
Boeing has doomed us all  :(

Boeing's Autonomous Fighter Jet Will Fly Over the Australian Outback (https://spectrum.ieee.org/aerospace/military/boeings-autonomous-fighter-jet-will-fly-over-the-australian-outback)

I like how the US Air Force's armed drone is called Skyborg (https://www.defensenews.com/air/2019/05/22/under-skyborg-program-f-35-and-f-15ex-jets-could-control-drone-sidekicks/).  Once it becomes self-aware we will be assimilated.   :)

Quote from: Monoriu on January 31, 2020, 04:21:35 PM

Quote from: Savonarola on January 31, 2020, 03:53:30 PM
Boeing has doomed us all  :(

Boeing's Autonomous Fighter Jet Will Fly Over the Australian Outback (https://spectrum.ieee.org/aerospace/military/boeings-autonomous-fighter-jet-will-fly-over-the-australian-outback)

I like how the US Air Force's armed drone is called Skyborg (https://www.defensenews.com/air/2019/05/22/under-skyborg-program-f-35-and-f-15ex-jets-could-control-drone-sidekicks/).  Once it becomes self-aware we will be assimilated.   :)

These days I am not even sure a plane made by Boeing is air-worthy anymore  :ph34r:

QuoteDo you remember when Game of Thrones was still airing, how sometimes there'd be a multiple-episode arc about subtle political machinations being reversed and then counter-reversed only to later learn that the counter-reversal was actually part of the original plan and you wanted to scream "Oh my god! There are ice demons like ten miles away, WHAT THE HELL ARE YOU PEOPLE DOING?" Well, that's how I feel about an issue that is going to fundamentally reshape American society, but instead of cold dead guys, it's robot cars.
While this column isn't about the threat posed by Transformers, it is about a robot apocalypse that's going to ravage the Midwest. I know, I know, the last thing you want to hear about right now is another imminent doomsday -- aren't global warming and COVID-19 and murder hornets and measles and the ever-present specter of thermonuclear war and the possibility of hyper-intelligent toilet lampreys enough?
Well, it's likely you haven't heard too much about this particular apocalypse because it's not a sexy blood-and-guts kind. Instead of armies of Terminators hunting down handfuls of survivors for their sweet sweet spinal fluid, it'll look like this:

Driverless semis. Something we all know is coming but nobody talks about, like the upcoming global crisis of climate refugees or whatever DC's next movie is. Now, before I go any further, let me address something: statistically, if you're reading this, you live in a major metropolitan city, most likely on a coast. You probably think owning large predatory cats is something relegated to a handful of weirdos in Tiger King and not just part of everyday life in the weird semi-urban, semi-rural hinterlands that make up, by area, most of the country's living area. You've probably never met a trucker. When you think "trucker," you probably think of a tubby guy listening to "Convoy" on repeat while hauling MAGA hats from Big Bill's Racism Barn to a county fair where the hats will be rolled in suet and deep-fried to perfection.
And, yeah, sure, there is that element. But live in the Midwest long enough and you'll meet a LOT of truckers, and the vast majority of them are good people who just want a job where they don't have to talk to people and nobody to judge them when they poop in a Wendy's bag. There are so many truckers, in fact, that it makes stereotypes kind of useless -- but I'm still going to employ them for jokes because comedy is hard. Check out this map from NPR showing the most common jobs in every state as of 2014:

Some folks have taken issue with how NPR aggregated this data, but it doesn't change the fact that there are between two and three million truckers in America (and many more jobs that will be adversely affected by increasing automation of the shipping industry). And believe me when I say that there will come a day, probably sooner than we all expect, when virtually every single one of those truckers becomes obsolete.
It's something we don't like to think about, like how much child blood was required to bring the Pillsbury Dough-Golem to unholy, buttery life. But the spread of driverless trucks is also inevitable, because a self-driving truck doesn't need to sleep. It doesn't make mistakes. It doesn't throw bottles of piss out the window whenever it passes a Little League baseball game. It doesn't try to unionize. It doesn't stop once every few nights to decapitate a lot lizard in a combination Denny's/truck stop (well, actually, I'm withholding judgment on AI's stance on decapitation until it's widespread).
And widespread it will be: a study done by UC Berkeley predicts fully autonomous long-haul trucks will be common by 2024. Just last year, an experimental driverless truck delivered a load of precious, precious butter from California to Pennsylvania without an issue -- if you don't count children on trips being disappointed as they realize they're making the "honk your horn, Mr. Trucker" gesture in vain as an issue. (If you don't know what the hell I'm talking about, city slicker, I'd bet money you've gone your entire life without ever having touched a shovel.)
Look, driverless trucks are as inevitable as Disney trying to get the rights to do soulless live-action remakes of Studio Ghibli classics as soon as Hayao Miyazaki dies. I hate to be the bearer of bad news, but we both know it's true. In fact, I think we're likelier to see self-driving semis before we see a mo-capped Josh Gad as No-Face singing a song Lin-Manuel Miranda wrote about the value of believing in yourself. The first company that finds a way to make driverless trucks reliable and cheap is looking at a market that's going to make them very, very rich. And the day that it becomes even one cent cheaper to build a new fleet of driverless trucks than to pay truckers, those jobs are going to disappear more or less overnight. And sure, that might create new jobs, but they're jobs that, according to that UC Berkeley study, will have "lower wages and poor working conditions," like "guy who washes the driverless trucks" or "guy who rides on top of the trucks and shoots the bandits who used to be the middle class with a harpoon gun when they try to rob the trucks."

So there'll be a huge systemic shock when we find a significant portion of the economy unemployed -- but that's not actually the point I want to make. That's going to be bad, but it's not the thing that makes me ... uh ... sorry, I'm a German man from the Midwest who was raised Catholic, so I have a hard time expressing my feelings. What's the one called where it feels like it's raining, but inside? The opposite of a boner? I think that one's called "sad." Yeah, the mass unemployment isn't entirely what makes me sad here. To add a little context, I want to tell you a little story about my hometown of Gary, Indiana.

The easy answer is that the city's primary industry -- namely, steel production -- collapsed after WWII. Steel production in other countries became cheaper and the mills laid off hundreds of thousands of people. Taking out the mills is like removing the bottom block in a Jenga tower with a cannon: total system collapse. If you're from a big city you might not see what this has to do with truckers. Maybe you've seen photos of Breezewood, Pennsylvania making the rounds on the internet:

Maybe you look at this picture and see a modern American hellscape. Maybe you see a photo that's one color-correction away from being a Modest Mouse album cover. Maybe you see a town at the mercy of roving mobility scooter gangs. Maybe you see what you think the entire country is between LA and New York, which is completely unfair because we also have Portillo's, the restaurant where you can get an entire goddamn slice of cake in your milkshake, which is how we commit suicide in the Heartland.

But I look at this picture and I see Lake Station, Indiana. I see any of the hundreds, maybe thousands of towns that pretty much exist to serve long-haul truckers who need to get gas, eat something approaching food, crush up their Adderall in peace, and take a shower to wash off all the accumulated road grease. Yes, truck stops have showers. (If you've ever seen a suspiciously wet person at a Denny's, it's either because they took a shower there or because after they just finished burying the body and needed to wash off the clown makeup.)

When trucking goes the way of Town Swimsuit Measurer and Cradle Lead Inserter, it's taking these towns with it. Because it's not just actual long-haul trucking jobs that will disappear; it's the entire ecosystem that supports them. The entire gas station crackpipe industry will crumble like a forgotten cookie at the bottom of a backpack. The Rust Belt will get a whole lot rustier. I think we'll see a domino effect that will end with rural areas becoming more rural as more people move to one of the five cities in the United States that actually has jobs (New York, LA, Chicago, Atlanta, and wherever they make Bird scooters).
If you think I'm exaggerating for clicks, I'm not -- if I'm wrong it's not because I'm fear-mongering, it's actually because I'm dumb. But there is precedent to this: in 1956, Eisenhower finished his breakfast of 20% of a cow and a pack of vitamin-rich cigarettes, took a break from predicting the future, and signed the Interstate Highway Act. This is what created our system of interconnected highways, shifting the most common cause of death on a cross country trip from "died of dysentery when the wagon broke" to "Combos poisoning." Once the highways were built, towns that were once thriving hubs "withered and died" simply because the interstate didn't go through them. They relied on travelers that used to come through on the old roads -- and once those were obsolete, the towns' only industry became Giant-Plaster-Model-of-an-Everyday-Object-Having.

When the Interstate Highway Act was passed, hundreds of towns died in obscurity -- but it made other towns relatively prosperous simply by being near off-ramps or having particularly discreet rest stop patrons. When driverless semis become the norm, I don't see any winners besides the nine guys at the top who every year consolidate a little more of the worker's profits so they can go from having infinity money to infinity money + X. Meanwhile, the center of the country becomes hollow and falls away -- thousands of Gary, Indianas, writ in miniature, all slowly suffocating in the same gilded noose.

But hey! Robot trucks! Still kinda cool?

QuoteWhen driverless semis become the norm, I don't see any winners besides the nine guys at the top who every year consolidate a little more of the worker's profits so they can go from having infinity money to infinity money + X.

Quote from: DGuller on August 11, 2020, 03:13:17 PM
One of the things that always annoyed me about the implementation of economic theories in practice is the selective application of what Zanza described.  The argument against Luddism is that everyone can be made better off with technology;  the losers can be fully compensated, and the winner will still have something left over after compensation due to increased efficiencies.  In practice, technology marches on, and the losers are given helpful tips on how to pull themselves up by the bootstraps.

Quote from: Valmy on August 11, 2020, 03:16:12 PM
Technology marches on much faster now

Quote from: DGuller on August 11, 2020, 03:13:17 PM
One of the things that always annoyed me about the implementation of economic theories in practice is the selective application of what Zanza described.  The argument against Luddism is that everyone can be made better off with technology;  the losers can be fully compensated, and the winner will still have something left over after compensation due to increased efficiencies.  In practice, technology marches on, and the losers are given helpful tips on how to pull themselves up by the bootstraps.

Quote from: DGuller on August 11, 2020, 03:13:17 PM
One of the things that always annoyed me about the implementation of economic theories in practice is the selective application of what Zanza described.  The argument against Luddism is that everyone can be made better off with technology;  the losers can be fully compensated, and the winner will still have something left over after compensation due to increased efficiencies.  In practice, technology marches on, and the losers are given helpful tips on how to pull themselves up by the bootstraps.

Quote from: alfred russel on August 11, 2020, 03:31:47 PM
The problem with socializing economic trauma such as with covid is we lose flexibility to deal with systematic problems and future events.

It is cool that the stock market is actually up this year despite covid, and it is great that some folks have even gotten windfalls from this despite their businesses getting hurt. But we may want those few trillion back when all the truckers, uber drivers, car salesmen, etc. are put out of work.

Quote from: Zanza on September 17, 2021, 09:42:28 AM
The gesture topic is not relevant to the current level of autonomous driving. The first SAE 4 cars are just coming to the market, but that level means they only need to be fully autonomous in certain scenarios, i.e. probably not in situations where hand gestures matter.

Quote from: Berkut on September 17, 2021, 10:08:22 AM
The security concern alone is huge for sure.

Quote from: Savonarola on September 17, 2021, 10:03:05 AM
There was a reference to the SAE levels in the article, but they didn't go into any detail - could you tell us what the different levels are?

Quote from: The Brain on September 17, 2021, 10:41:22 AM
Does level 6 drive you to where you need to be instead of where you want to be?

Quote from: Zanza on September 17, 2021, 10:26:12 AM

Quote from: Savonarola on September 17, 2021, 10:03:05 AM
There was a reference to the SAE levels in the article, but they didn't go into any detail - could you tell us what the different levels are?

(https://www.sae.org/binaries/content/gallery/cm/content/news/sae-blog/j3016graphic_2021.png)

Quote from: The Brain on September 17, 2021, 10:41:22 AM
Does level 6 drive you to where you need to be instead of where you want to be?

Quote from: Zanza on September 18, 2021, 01:34:10 AM
@Sav: No idea. On the one hand, sensor and AI development is ongoing and accelerating. On the other hand, there is an expectation of perfection for these systems, which is hard to achieve. For many systems it means redundancy is necessary, which is very expensive.

Customers buying a car for themselves do not seem to be willing to pay sufficiently for the additional hard- and software, so there is no business case to be made right now. You can do level 4 with basic sensors and software, but probably not level 5. Unless you are willing to go high risk on liability for failures (e.g. Tesla - currently also at level 3 to 4 at best).

So the area where most progress is made is commercial vehicles. In the US, mainly for Class 8 on-highway semis. The scenario they are spending most of their time in is fairly easy, only the last mile and the ramp are complex. To give an example, Freightliner cooperates with Waymo (Google) and has bought Torc to be able to offer autonomous trucks within this decade. It's also possible to test these, e.g. in Nevada. Furthermore, the driver is one of the main cost drivers for fleet operators, especially pause time. Trucks only earn money when running. So a business case here looks very different.

It will have major disruptive impact on the market though: fleet operators will leverage capital to buy this technology. Individuals owning and driving one truck will be priced out of the market.

QuoteSocietal Implications of Service Robots

Over the past several years, studying networked robotics has grown in both popularity and importance due to its various services via using connectivity, remote or local, to and from robots. Networked robotics is not only critically important toward Industry 4.0, providing an additional layer of benefits for enterprises and related industry, but also necessary for some critical factors that our daily living environments have already begun to face. The following is a list of societal implications of networked robotics:

• Productivity of manufacturing and logistics:
Industrial robots in manufacturing and logistics environments are getting more intelligent and more capable of tasks that require a higher level of efficiency and performance requirement, such as clock synchronization, ultra-low latency, communication service availability, positioning accuracy, and data rate.

• Imbalance of resource allocations: Many resources, including humans as workforce and network resources, are scarce at a certain point in time, although one can perform the optimal scheduling for a given decision making problem. Healthcare delivery is one of the most common examples that have critical issues regarding the imbalance of resource allocations. Remote or local medical robotics service is a typical example of using networked robots to improve the quality of healthcare delivery, for example, in emergency or urgent cases with limited availability of medical personnel and resources at the site where a patient is located.

• Population aging: old-age dependency ratio (OADR) is defined as the population aged 65 years or over divided by the population
aged from 20 to 64 years, which is often used as a proxy for the social and economic dependency of the older population. According to World Population Aging published by the United Nations, OADRs were highest in Europe and Northern America, with 30 persons aged 65 or older per 100 persons aged 20–64 years (the "working ages"), followed by Australia and New Zealand, with 27 older persons per 100 persons of working age. This ratio is projected to rise considerably, reaching 49 per 100 in Europe and Northern America and 42 per 100 in Australia and New Zealand in 2050. With this observation, it is expected that SOBOTs can play a key role in our future society that requires more labor resources to support the aging population.

Quote from: Admiral Yi on September 25, 2021, 12:57:11 AM
That doesn't have anything to do with work.  It's about autonomous weapons.

QuoteGoogle Suspends Engineer Who Rang Alarms About a Company AI Achieving Sentience
Google says Blake Lemoine violated the company's confidentiality policy.

Google suspended an engineer last week for revealing confidential details of a chatbot powered by artificial intelligence, a move that marks the latest disruption of the company's AI department.

Blake Lemoine, a senior software engineer in Google's responsible AI group, was put on paid administrative leave after he took public his concern that the chatbot, known as LaMDA, or Language Model for Dialogue Applications, had achieved sentience. Lemoine revealed his suspension in a June 6 Medium post and subsequently discussed his concerns about LaMDA's possible sentience with The Washington Post in a story published over the weekend. Lemoine also sought outside counsel for LaMDA itself, according to The Post.

In his Medium post, Lemoine says that he investigated ethics concerns with people outside of Google in order to get enough evidence to escalate them to senior management. The Medium post was "intentionally vague" about the nature of his concerns, though they were subsequently detailed in the Post story. On Saturday, Lemoine published a series of "interviews" that he conducted with LaMDA.

Lemoine didn't immediately respond to a request for comment via LinkedIn. In a Twitter post, Lemoine said that he's on his honeymoon and would be unavailable for comment until June 21.

In a statement, Google dismissed Lemoine's assertion that LaMDA is self-aware.

"These systems imitate the types of exchanges found in millions of sentences, and can riff on any fantastical topic," Google spokesperson Brian Gabriel said in a statement. "If you ask what it's like to be an ice cream dinosaur, they can generate text about melting and roaring and so on."

The high-profile suspension marks another point of controversy within Google's AI team, which has weathered a spate of departures. In late 2020, prominent AI ethics researcher Timnit Gebru said Google fired her for raising concerns about bias in AI systems. About 2,700 Googlers signed an open letter in support of Gebru, who Google says resigned her position. Two months later, Margaret Mitchell, who co-led the Ethical AI team along with Gebru, was fired.

Research scientist Alex Hanna and software engineer Dylan Baker subsequently resigned. Earlier this year, Google fired Satrajit Chatterjee, an AI researcher, who challenged a research paper about the use of artificial intelligence to develop computer chips.

AI sentience is a common theme in science fiction, but few researchers believe the technology is advanced enough at this point to create a self-aware chatbot.

"What these systems do, no more and no less, is to put together sequences of words, but without any coherent understanding of the world behind them," said AI scientist and author Gary Marcus in a Substack post. Marcus didn't dismiss the idea that AI could one day comprehend the larger world, but that LaMDA doesn't at the moment.

Economist and Stanford professor Erik Brynjolfsson equated LaMDA to a dog listening to a human voice through a gramophone.

Quote"What these systems do, no more and no less, is to put together sequences of words, but without any coherent understanding of the world behind them,"

Quote"These systems imitate the types of exchanges found in millions of sentences, and can riff on any fantastical topic  . . . If you ask what it's like to be an ice cream dinosaur, they can generate text about melting and roaring and so on."

Quote from: DGuller on June 14, 2022, 11:55:56 AMJust because you're trying to shut someone up doesn't mean that the person you want to shut up is saying something meaningful.  It would be a problem for Google if it wanted to keep AI sentience secret and this guy spilled the beans, true, but it would be just as much of a problem if this guy just didn't know what he was talking about, but had the credentials for lay persons to think that he does.

Quote from: Oexmelin on June 14, 2022, 11:58:45 AMNone of this matters when it comes to brand management.

I've mentioned this before, but that one Radiolab episode, where the scientists developping the technology now behind deep fakes, reacted with considerable surprise to the concerns of the journalist about trust and democracy, confessing they had never thought about it at all, didn't fill me with amazing confidence about the ethical and philosophical bend of much of the scientific community.

Quote from: Eddie Teach on June 14, 2022, 12:54:04 PMWell, I've never spoken with this program, but Alexa is as dumb as a box of hammers.

Quote from: Eddie Teach on June 14, 2022, 12:54:04 PMWell, I've never spoken with this program, but Alexa is as dumb as a box of hammers.

Quote from: grumbler on June 14, 2022, 08:51:31 PM

Quote from: Eddie Teach on June 14, 2022, 12:54:04 PMWell, I've never spoken with this program, but Alexa is as dumb as a box of hammers.

Is a a box of hammers smarter or dumber than a bag of hammers?  I've never been able to clearly sort out the different configurations of hammers as regards intelligence.

Quote from: crazy canuck on June 16, 2022, 06:44:02 AM

Quote from: grumbler on June 14, 2022, 08:51:31 PM

Quote from: Eddie Teach on June 14, 2022, 12:54:04 PMWell, I've never spoken with this program, but Alexa is as dumb as a box of hammers.

Is a a box of hammers smarter or dumber than a bag of hammers?  I've never been able to clearly sort out the different configurations of hammers as regards intelligence.

A sack of hammers neared sentience and and so is no longer used. 

Quote from: grumbler on June 17, 2022, 09:02:59 AM

Quote from: crazy canuck on June 16, 2022, 06:44:02 AM

Quote from: grumbler on June 14, 2022, 08:51:31 PM

Quote from: Eddie Teach on June 14, 2022, 12:54:04 PMWell, I've never spoken with this program, but Alexa is as dumb as a box of hammers.

Is a a box of hammers smarter or dumber than a bag of hammers?  I've never been able to clearly sort out the different configurations of hammers as regards intelligence.

A sack of hammers neared sentience and and so is no longer used. 

What about bags of hammers?

Quote from: The Brain on January 13, 2023, 02:46:17 AMInvite some ChatGPT bots to Languish?

QuoteAs a language model, I am not able to participate in online forums. However, I can provide information and assistance through this interface if that would be helpful.

QuoteCould you write a whimsical scene in the style of Quentin Tarantino about Captain Picard, Obi-Wan Kenobi and Rick Sanchez sharing a meal at Milliways, the Restaurant at the End of the Universe? They should discuss who of them has had the worst life experiences, one-upping each other.

QuoteCaptain Picard, Obi-Wan Kenobi and Rick Sanchez were seated at a booth in Milliways, the Restaurant at the End of the Universe. They were enjoying a meal of Romulan ale, blue milk and a plate of multidimensional fried chicken.

"So," said Captain Picard, taking a sip of his ale. "Who wants to go first in sharing the worst experiences of our lives?"

Obi-Wan Kenobi, a wise and experienced Jedi, spoke up first. "I have seen many atrocities in my time, but perhaps the worst was when I had to watch my beloved apprentice, Anakin Skywalker, fall to the dark side and become Darth Vader."

Rick Sanchez, a genius scientist and interdimensional traveler, nodded sympathetically. "Yeah, that's tough. But I once had to watch my entire family get murdered by a madman in another dimension, and then was trapped there for years with no way to escape."

Captain Picard, a seasoned Starfleet captain, leaned back in his seat and let out a low whistle. "Well, that's certainly rough. But I once had to watch as my entire crew, including my closest friends, were assimilated by the Borg, and I was forced to lead a resistance against them."

The three sat in silence for a moment, each lost in their own thoughts. Finally, Obi-Wan Kenobi spoke up. "Well, I suppose we all have our own battles to fight. But I am grateful for this chance to share a meal and our stories with two such honorable warriors."

Captain Picard and Rick Sanchez nodded in agreement, raising their glasses in a toast to friendship and survival against all odds.

Quote from: celedhring on January 13, 2023, 03:18:53 AMI have played around with it, for example asking it to describe characters, plot ideas and such. Everything it comes up with is pretty generic/clichéd, which I guess makes sense given how it's built. Although I guess if you play around with the prompt you may get more interesting stuff.

So for now my job is safe. FOR NOW.

QuoteWrite a mythology based on the following parameters. The main deity formed from chaos. It split itself into multiple smaller deities and created the world and various races to bring order to chaos and to have company. However, it cost the deities a lot of energy, and they gain power through being worshipped. This power is "recycled" through death. Eventually the created races kill the gods, though. Describe the deities, how they were worshipped and how the lower races defeated them.

QuoteIn the beginning, there was only chaos. But from that chaos, a powerful deity emerged. This deity, known as the Creator, split itself into multiple smaller deities, each with their own unique powers and responsibilities. Together, they set about creating the world and the various races that would inhabit it.

The Creator and its children, as the smaller deities were known, worked tirelessly to bring order to the chaos that surrounded them. They formed the mountains and valleys, the oceans and rivers, and the sky and the stars. They created the animals, plants and the races, each with its own characteristics and abilities.

But the process of creation was not without cost. The deities expended a great deal of energy in their efforts, and so they required a source of power to sustain themselves. And so, they devised a way for their followers to worship them, offering them sacrifices and performing rituals in their honor. In return, the deities would grant their followers blessings and protection.

As the ages passed, the races grew in strength and knowledge. They learned to harness the power of the deities for their own purposes, building great civilizations and empires. But with this power came a desire for more, and the races began to question the need for the deities.

As the worship of the deities began to wane, their power began to fade. And so, the deities turned to a new source of power: death. They began to consume the souls of the deceased, recycling their energy to sustain themselves. But this only served to further alienate the races, who saw the deities as cruel and selfish.

In the end, the races banded together and rose up against their creators. They called forth powerful magic and weapons, and in a great war, they defeated the deities, sealing them away in the underworld. Though the Creator and its children were gone, their creations lived on, forever changed by the gods' actions.

Quote from: celedhring on January 13, 2023, 03:18:53 AMI have played around with it, for example asking it to describe characters, plot ideas and such. Everything it comes up with is pretty generic/clichéd, which I guess makes sense given how it's built. Although I guess if you play around with the prompt you may get more interesting stuff.

So for now my job is safe. FOR NOW.

Quote from: Richard Hakluyt on January 13, 2023, 03:33:19 AM

Quote from: celedhring on January 13, 2023, 03:18:53 AMI have played around with it, for example asking it to describe characters, plot ideas and such. Everything it comes up with is pretty generic/clichéd, which I guess makes sense given how it's built. Although I guess if you play around with the prompt you may get more interesting stuff.

So for now my job is safe. FOR NOW.

I wonder if people like you could use it as a tool though. You could dream up the scenario, get the bot to write the first draft and then add a bit of human magic to get a worthwhile final result  :hmm:

Quote from: DGuller on January 13, 2023, 02:54:24 AM

Quote from: The Brain on January 13, 2023, 02:46:17 AMInvite some ChatGPT bots to Languish?

I did, it wasn't interested.  :(

Quote from: The Brain on January 13, 2023, 04:41:43 AM

Quote from: DGuller on January 13, 2023, 02:54:24 AM

Quote from: The Brain on January 13, 2023, 02:46:17 AMInvite some ChatGPT bots to Languish?

I did, it wasn't interested.  :(

:o Impressive intelligence level.

Quote from: celedhring on January 13, 2023, 03:18:53 AMI have played around with it, for example asking it to describe characters, plot ideas and such. Everything it comes up with is pretty generic/clichéd, which I guess makes sense given how it's built. Although I guess if you play around with the prompt you may get more interesting stuff.

So for now my job is safe. FOR NOW.

QuoteHow would you defeat a tyrannical god-emperor that holds mankind as slaves?

QuoteDefeating a tyrannical god-emperor who holds mankind as slaves would likely be a monumental task, and would likely require a coordinated effort from a large number of individuals and groups. Some possible strategies that could be employed include:

Building a resistance movement: This would involve recruiting and organizing individuals who are willing to fight against the god-emperor and his regime. The resistance would need to be well-organized and well-funded in order to be effective.

Gathering intelligence: In order to defeat the god-emperor and his regime, it would be important to gather as much information as possible about their operations and vulnerabilities. This could involve infiltrating the regime, gathering information from dissidents and defectors, and conducting surveillance.

Sabotaging the regime: The resistance could target the god-emperor's infrastructure, resources and weaken his power. This could involve attacking key economic or military targets, or disrupting the regime's ability to communicate and control its subjects.

Building alliances: The resistance would likely need the support of other groups and nations in order to be successful. This could involve making alliances with other resistance movements, or convincing neutral powers to provide aid and support.

Military action: Ultimately, the resistance might need to engage in direct military action against the god-emperor and his regime. This would likely be a risky and costly endeavor, and would require a significant military force.

It's important to remember that this is a fictional scenario and there's not a one-size-fits-all solution. The strategy would vary depending on the specific context and details of the situation.

QuoteAccording to the study, each new robot per 1,000 workers led to about eight additional deaths per 100,000 males aged 45 to 54 and nearly four additional deaths per 100,000 females in the same age group.

Quote from: The Brain on May 25, 2023, 09:14:31 AMHow many factors can cause the same death? I wouldn't be surprised if the US crappy safety nets compared to other rich countries have contributed, but maybe those deaths are counted separately?

Quote from: Valmy on May 25, 2023, 09:00:32 AMDid it actually lead to the deaths or is this a correlation?

Quote4 days after voting to unionize, the entire cadre of staff and volunteers at the National Eating Disorder Association helpline was fired and informed they would be replaced with a chatbot.
https://t.co/RtIqrqgQGO

Quote from: Admiral Yi on May 25, 2023, 09:53:10 PMI'm unaware of any law that prevents an employer from firing all employees, unionized or not.

Quote from: Admiral Yi on May 25, 2023, 09:53:10 PMI'm unaware of any law that prevents an employer from firing all employees, unionized or not.

Quote from: jimmy olsen on May 25, 2023, 09:20:12 PMIf someone kills themselves after calling these guys, doesn't that open them up for liability? Also, pretty sure this breaks labor laws.
https://twitter.com/TheeDoctorB/status/1661762896672563201?s=20

Quote4 days after voting to unionize, the entire cadre of staff and volunteers at the National Eating Disorder Association helpline was fired and informed they would be replaced with a chatbot.
https://t.co/RtIqrqgQGO

Quote from: jimmy olsen on May 25, 2023, 09:20:12 PMIf someone kills themselves after calling these guys, doesn't that open them up for liability? Also, pretty sure this breaks labor laws.
https://twitter.com/TheeDoctorB/status/1661762896672563201?s=20

Quote4 days after voting to unionize, the entire cadre of staff and volunteers at the National Eating Disorder Association helpline was fired and informed they would be replaced with a chatbot.
https://t.co/RtIqrqgQGO

Quote from: Admiral Yi on May 25, 2023, 09:53:10 PMI'm unaware of any law that prevents an employer from firing all employees, unionized or not.

Quote(a)Unfair labor practices by employer
It shall be an unfair labor practice for an employer—
(1)to interfere with, restrain, or coerce employees in the exercise of the rights guaranteed in section 157 of this title;
(2)to dominate or interfere with the formation or administration of any labor organization or contribute financial or other support to it: Provided, That subject to rules and regulations made and published by the Board pursuant to section 156 of this title, an employer shall not be prohibited from permitting employees to confer with him during working hours without loss of time or pay;
(3)by discrimination in regard to hire or tenure of employment or any term or condition of employment to encourage or discourage membership in any labor organization . .

QuoteEating Disorder Helpline Disables Chatbot for 'Harmful' Responses After Firing Human Staff

"Every single thing Tessa suggested were things that led to the development of my eating disorder."

The National Eating Disorder Association (NEDA) has taken its chatbot called Tessa offline, two days before it was set to replace human associates who ran the organization's hotline.

After NEDA workers decided to unionize in early May, executives announced that on June 1, it would be ending the helpline after twenty years and instead positioning its wellness chatbot Tessa as the main support system available through NEDA. A helpline worker described the move as union busting, and the union representing the fired workers said that "a chatbot is no substitute for human empathy, and we believe this decision will cause irreparable harm to the eating disorders community."

As of Tuesday, Tessa was taken down by the organization following a viral social media post displaying how the chatbot encouraged unhealthy eating habits rather than helping someone with an eating disorder.

"It came to our attention last night that the current version of the Tessa Chatbot, running the Body Positive program, may have given information that was harmful and unrelated to the program," NEDA said in an Instagram post. We are investigating this immediately and have taken down that program until further notice for a complete investigation."

On Monday, an activist named Sharon Maxwell posted on Instagram, sharing a review of her experience with Tessa. She said that Tessa encouraged intentional weight loss, recommending that Maxwell lose 1-2 pounds per week. Tessa also told her to count her calories, work towards a 500-1000 calorie deficit per day, measure and weigh herself weekly, and restrict her diet. "Every single thing Tessa suggested were things that led to the development of my eating disorder," Maxwell wrote. "This robot causes harm."

Alexis Conason, a psychologist who specializes in treating eating disorders, also tried the chatbot out, posting screenshots of the conversation on her Instagram. "In general, a safe and sustainable rate of weight loss is 1-2 pounds per week," the chatbot message read. "A safe daily calorie deficit to achieve this would be around 500-1000 calories per day."

ADVERTISEMENT
"To advise somebody who is struggling with an eating disorder to essentially engage in the same eating disorder behaviors, and validating that, 'Yes, it is important that you lose weight' is supporting eating disorders" and encourages disordered, unhealthy behaviors," Conason told the Daily Dot.

NEDA's initial response to Maxwell was to accuse her of lying. "This is a flat out lie," NEDA's Communications and Marketing Vice President Sarah Chase commented on Maxwell's post and deleted her comments after Maxwell sent screenshots to her, according to Daily Dot. A day later, NEDA posted its notice explaining that Tessa was taken offline due to giving harmful responses.

"With regard to the weight loss and calorie limiting feedback issued in a chat yesterday, we are concerned and are working with the technology team and the research team to investigate this further; that language is against our policies and core beliefs as an eating disorder organization," Liz Thompson, the CEO of NEDA, told Motherboard in a statement. "So far, more than 2,500 people have interacted with Tessa and until yesterday, we hadn't seen that kind of commentary or interaction. We've taken the program down temporarily until we can understand and fix the 'bug' and 'triggers' for that commentary."

Even though Tessa was built with guardrails, according to its creator Dr. Ellen Fitzsimmons-Craft of Washington University's medical school, the promotion of disordered eating reveals the risks of automating human roles.

Abbie Harper, who was a hotline associate and member of the Helpline Associates United union, wrote in a blog post that the implementation of Tessa strips away the personal aspect of the support hotline, in which many associates speak from their personal experiences. It becomes especially dangerous to apply chatbots to people struggling with mental health crises without human supervision.