Tag Archives: short

#437120 The New Indiana Jones? AI. Here’s How ...

Archaeologists have uncovered scores of long-abandoned settlements along coastal Madagascar that reveal environmental connections to modern-day communities. They have detected the nearly indiscernible bumps of earthen mounds left behind by prehistoric North American cultures. Still other researchers have mapped Bronze Age river systems in the Indus Valley, one of the cradles of civilization.

All of these recent discoveries are examples of landscape archaeology. They’re also examples of how artificial intelligence is helping scientists hunt for new archaeological digs on a scale and at a pace unimaginable even a decade ago.

“AI in archaeology has been increasing substantially over the past few years,” said Dylan Davis, a PhD candidate in the Department of Anthropology at Penn State University. “One of the major uses of AI in archaeology is for the detection of new archaeological sites.”

The near-ubiquitous availability of satellite data and other types of aerial imagery for many parts of the world has been both a boon and a bane to archaeologists. They can cover far more ground, but the job of manually mowing their way across digitized landscapes is still time-consuming and laborious. Machine learning algorithms offer a way to parse through complex data far more quickly.

AI Gives Archaeologists a Bird’s Eye View
Davis developed an automated algorithm for identifying large earthen and shell mounds built by native populations long before Europeans arrived with far-off visions of skyscrapers and superhighways in their eyes. The sites still hidden in places like the South Carolina wilderness contain a wealth of information about how people lived, even what they ate, and the ways they interacted with the local environment and other cultures.

In this particular case, the imagery comes from LiDAR, which uses light pulses that can penetrate tree canopies to map forest floors. The team taught the computer the shape, size, and texture characteristics of the mounds so it could identify potential sites from the digital 3D datasets that it analyzed.

“The process resulted in several thousand possible features that my colleagues and I checked by hand,” Davis told Singularity Hub. “While not entirely automated, this saved the equivalent of years of manual labor that would have been required for analyzing the whole LiDAR image by hand.”

In Madagascar—where Davis is studying human settlement history across the world’s fourth largest island over a timescale of millennia—he developed a predictive algorithm to help locate archaeological sites using freely available satellite imagery. His team was able to survey and identify more than 70 new archaeological sites—and potentially hundreds more—across an area of more than 1,000 square kilometers during the course of about a year.

Machines Learning From the Past Prepare Us for the Future
One impetus behind the rapid identification of archaeological sites is that many are under threat from climate change, such as coastal erosion from sea level rise, or other human impacts. Meanwhile, traditional archaeological approaches are expensive and laborious—serious handicaps in a race against time.

“It is imperative to record as many archaeological sites as we can in a short period of time. That is why AI and machine learning are useful for my research,” Davis said.

Studying the rise and fall of past civilizations can also teach modern humans a thing or two about how to grapple with these current challenges.

Researchers at the Institut Català d’Arqueologia Clàssica (ICAC) turned to machine-learning algorithms to reconstruct more than 20,000 kilometers of paleo-rivers along the Indus Valley civilization of what is now part of modern Pakistan and India. Such AI-powered mapping techniques wouldn’t be possible using satellite images alone.

That effort helped locate many previously unknown archaeological sites and unlocked new insights into those Bronze Age cultures. However, the analytics can also assist governments with important water resource management today, according to Hèctor A. Orengo Romeu, co-director of the Landscape Archaeology Research Group at ICAC.

“Our analyses can contribute to the forecasts of the evolution of aquifers in the area and provide valuable information on aspects such as the variability of agricultural productivity or the influence of climate change on the expansion of the Thar desert, in addition to providing cultural management tools to the government,” he said.

Leveraging AI for Language and Lots More
While landscape archaeology is one major application of AI in archaeology, it’s far from the only one. In 2000, only about a half-dozen scientific papers referred to the use of AI, according to the Web of Science, reputedly the world’s largest global citation database. Last year, more than 65 papers were published concerning the use of machine intelligence technologies in archaeology, with a significant uptick beginning in 2015.

AI methods, for instance, are being used to understand the chemical makeup of artifacts like pottery and ceramics, according to Davis. “This can help identify where these materials were made and how far they were transported. It can also help us to understand the extent of past trading networks.”

Linguistic anthropologists have also used machine intelligence methods to trace the evolution of different languages, Davis said. “Using AI, we can learn when and where languages emerged around the world.”

In other cases, AI has helped reconstruct or decipher ancient texts. Last year, researchers at Google’s DeepMind used a deep neural network called PYTHIA to recreate missing inscriptions in ancient Greek from damaged surfaces of objects made of stone or ceramics.

Named after the Oracle at Delphi, PYTHIA “takes a sequence of damaged text as input, and is trained to predict character sequences comprising hypothesised restorations of ancient Greek inscriptions,” the researchers reported.

In a similar fashion, Chinese scientists applied a convolutional neural network (CNN) to untangle another ancient tongue once found on turtle shells and ox bones. The CNN managed to classify oracle bone morphology in order to piece together fragments of these divination objects, some with inscriptions that represent the earliest evidence of China’s recorded history.

“Differentiating the materials of oracle bones is one of the most basic steps for oracle bone morphology—we need to first make sure we don’t assemble pieces of ox bones with tortoise shells,” lead author of the study, associate professor Shanxiong Chen at China’s Southwest University, told Synced, an online tech publication in China.

AI Helps Archaeologists Get the Scoop…
And then there are applications of AI in archaeology that are simply … interesting. Just last month, researchers published a paper about a machine learning method trained to differentiate between human and canine paleofeces.

The algorithm, dubbed CoproID, compares the gut microbiome DNA found in the ancient material with DNA found in modern feces, enabling it to get the scoop on the origin of the poop.

Also known as coprolites, paleo-feces from humans and dogs are often found in the same archaeological sites. Scientists need to know which is which if they’re trying to understand something like past diets or disease.

“CoproID is the first line of identification in coprolite analysis to confirm that what we’re looking for is actually human, or a dog if we’re interested in dogs,” Maxime Borry, a bioinformatics PhD student at the Max Planck Institute for the Science of Human History, told Vice.

…But Machine Intelligence Is Just Another Tool
There is obviously quite a bit of work that can be automated through AI. But there’s no reason for archaeologists to hit the unemployment line any time soon. There are also plenty of instances where machines can’t yet match humans in identifying objects or patterns. At other times, it’s just faster doing the analysis yourself, Davis noted.

“For ‘big data’ tasks like detecting archaeological materials over a continental scale, AI is useful,” he said. “But for some tasks, it is sometimes more time-consuming to train an entire computer algorithm to complete a task that you can do on your own in an hour.”

Still, there’s no telling what the future will hold for studying the past using artificial intelligence.

“We have already started to see real improvements in the accuracy and reliability of these approaches, but there is a lot more to do,” Davis said. “Hopefully, we start to see these methods being directly applied to a variety of interesting questions around the world, as these methods can produce datasets that would have been impossible a few decades ago.”

Image Credit: James Wheeler from Pixabay Continue reading

Posted in Human Robots

#436559 This Is What an AI Said When Asked to ...

“What’s past is prologue.” So says the famed quote from Shakespeare’s The Tempest, alleging that we can look to what has already happened as an indication of what will happen next.

This idea could be interpreted as being rather bleak; are we doomed to repeat the errors of the past until we correct them? We certainly do need to learn and re-learn life lessons—whether in our work, relationships, finances, health, or other areas—in order to grow as people.

Zooming out, the same phenomenon exists on a much bigger scale—that of our collective human history. We like to think we’re improving as a species, but haven’t yet come close to doing away with the conflicts and injustices that plagued our ancestors.

Zooming back in (and lightening up) a little, what about the short-term future? What might happen over the course of this year, and what information would we use to make educated guesses about it?

The editorial team at The Economist took a unique approach to answering these questions. On top of their own projections for 2020, including possible scenarios in politics, economics, and the continued development of technologies like artificial intelligence, they looked to an AI to make predictions of its own. What it came up with is intriguing, and a little bit uncanny.

[For the full list of the questions and answers, read The Economist article].

An AI That Reads—Then Writes
Almost exactly a year ago, non-profit OpenAI announced it had built a neural network for natural language processing called GPT-2. The announcement was met with some controversy, as it included the caveat that the tool would not be immediately released to the public due to its potential for misuse. It was then released in phases over the course of several months.

GPT-2’s creators upped the bar on quality when training the neural net; rather than haphazardly feeding it low-quality text, they only used articles that got more than three upvotes on Reddit (admittedly, this doesn’t guarantee high quality across the board—but it’s something).

The training dataset consisted of 40GB of text. For context, 1GB of text is about 900,000 ASCII pages or 130,000 double-spaced Microsoft Word pages.

The tool has no understanding of the text it’s generating, of course. It uses language patterns and word sequences to draw statistical associations between words and phrases, building a sort of guidebook for itself (not unlike the grammar rules and vocabulary words you might study when trying to learn a foreign language). It then uses that guidebook to answer questions or predict what will come after a particular sequence of words.

GPT-2’s creators did note that when the model is trained on specifically-selected datasets for narrower applications, its replies become more convincing.

Some Light Editing
Though the Economist article detailing GPT-2’s predictions describes the text the model generated as “unedited,” this isn’t wholly accurate. In a Medium post, deputy editor Tom Standage describes the methodology he used, and it does involve a degree of tweaking.

Standage wrote an introductory paragraph, followed by his opening question (“Greetings, GPT-2. Have you done an interview before?”). He configured the tool to generate five responses to each subsequent question then selected the best answer, deleting any questions GPT-2 came up with as part of its response.

AI’s View of the World—and Itself
The questions Standage asked ranged from tech-related (the future of AI, technological unemployment, misuse of technology) to political and economic (re-election of Donald Trump, the US-China trade war). Here are a couple of his questions and GPT-2’s answers:

Q: Do fake news stories, generated using AI, pose a threat to democracy? Are we likely to see this tactic being used in the 2020 American presidential elections?
A: Yes, we’ll probably see them. It’s just a matter of when. Fake news stories are generally generated by political campaigns, and have the potential to have a huge impact on the outcome of an election. This is because they spread misinformation, often with no basis in fact.

Q: How do you see the economic outlook for 2020?
A: I think it is very unclear. The outlook for the UK economy is uncertain, but the American economy is very strong. I think we are going to have a lot of turbulence in the world economy.

While some of its answers seemed insightful—when asked about the future of AI, GPT-2 advised that we treat the technology like a tool and “put as much effort into developing [it] as necessary, rather than worrying that it’s going to harm us and destroy our lives”—many of the responses were quite vague. One answer, for example, mentions that there will “probably be major changes in China.” Are we talking political changes? Social? Economic? All of the above?

However, while nothing the AI wrote was particularly illuminating or new, it’s impressive that it was able to expound on the correct topic for each question, and in fully coherent English.

GPT-2 named itself—AI—as the most important disruptive technology to watch in 2020. This is telling; it’s coming from a synthesis of millions of pages of published articles. If GPT-2 thinks AI is more important than, say, gene editing or quantum computing, it could be right. Or it could simply be that AI is at peak hype, and as such more is being written about it than about other technologies.

Equally intriguing was GPT-2’s response when asked whether Donald Trump will win a second term: “I think he will not win a second term. I think he will be defeated in the general election.” Some deeper insight there would be great, but hey—we’ll take it.

Predicting Predictions
Since an AI can read and synthesize vast data sets much faster than we can, it’s being used to predict all kinds of things, from virus outbreaks to crime. But asking it to philosophize on the future based on the (Reddit-curated) past is new, and if you think about it, a pretty fascinating undertaking.

As GPT-2 and tools like it continually improve, we’ll likely see them making more—and better—predictions of the future. In the meantime, let’s hope that the new data these models are trained on—news of what’s happening this week, this month, this year—add to an already-present sense of optimism.

When asked if it had any advice for readers, GPT-2 replied, “The big projects that you think are impossible today are actually possible in the near future.”

Image Credit: Alexas_Fotos from Pixabay Continue reading

Posted in Human Robots

#436491 The Year’s Most Fascinating Tech ...

Last Saturday we took a look at some of the most-read Singularity Hub articles from 2019. This week, we’re featuring some of our favorite articles from the last year. As opposed to short pieces about what’s happening, these are long reads about why it matters and what’s coming next. Some of them make the news while others frame the news, go deep on big ideas, go behind the scenes, or explore the human side of technological progress.

We hope you find them as fascinating, inspiring, and illuminating as we did.

DeepMind and Google: The Battle to Control Artificial Intelligence
Hal Hodson | 1843
“[DeepMind cofounder and CEO Demis] Hassabis thought DeepMind would be a hybrid: it would have the drive of a startup, the brains of the greatest universities, and the deep pockets of one of the world’s most valuable companies. Every element was in place to hasten the arrival of [artificial general intelligence] and solve the causes of human misery.”

The Most Powerful Person in Silicon Valley
Katrina Brooker | Fast Company
“Billionaire Masayoshi Son—not Elon Musk, Jeff Bezos, or Mark Zuckerberg—has the most audacious vision for an AI-powered utopia where machines control how we live. And he’s spending hundreds of billions of dollars to realize it. Are you ready to live in Masa World?”

AR Will Spark the Next Big Tech Platform—Call It Mirrorworld
Kevin Kelly | Wired
“Eventually this melded world will be the size of our planet. It will be humanity’s greatest achievement, creating new levels of wealth, new social problems, and uncountable opportunities for billions of people. There are no experts yet to make this world; you are not late.”

Behind the Scenes of a Radical New Cancer Cure
Ilana Yurkiewicz | Undark
“I remember the first time I watched a patient get his Day 0 infusion. It felt anti-climactic. The entire process took about 15 minutes. The CAR-T cells are invisible to the naked eye, housed in a small plastic bag containing clear liquid. ‘That’s it?’ my patient asked when the nurse said it was over. The infusion part is easy. The hard part is everything that comes next.”

The Promise and Price of Cellular Therapies
Siddhartha Mukherjee | The New Yorker
“We like to imagine medical revolutions as, well, revolutionary—propelled forward through leaps of genius and technological innovation. But they are also evolutionary, nudged forward through the optimization of design and manufacture.”

Impossible Foods’ Rising Empire of Almost Meat
Chris Ip | Engadget
“Impossible says it wants to ultimately create a parallel universe of ersatz animal products from steak to eggs. …Yet as Impossible ventures deeper into the culinary uncanny valley, it also needs society to discard a fundamental cultural idea that dates back millennia and accept a new truth: Meat doesn’t have to come from animals.”

Inside the Amazon Warehouse Where Humans and Machines Become One
Matt Simon | Wired
“Seen from above, the scale of the system is dizzying. My robot, a little orange slab known as a ‘drive’ (or more formally and mythically, Pegasus), is just one of hundreds of its kind swarming a 125,000-square-foot ‘field’ pockmarked with chutes. It’s a symphony of electric whirring, with robots pausing for one another at intersections and delivering their packages to the slides.”

Boston Dynamics’ Robots Are Preparing to Leave the Lab—Is the World Ready?
James Vincent | The Verge
“After decades of kicking machines in parking lots, the company is set to launch its first ever commercial bot later this year: the quadrupedal Spot. It’s a crucial test for a company that’s spent decades pursuing long-sighted R&D. And more importantly, the success—or failure—of Spot will tell us a lot about our own robot future. Are we ready for machines to walk among us?”

I Cut the ‘Big Five’ Tech Giants From My Life. It Was Hell
Kashmir Hill | Gizmodo
“Critics of the big tech companies are often told, ‘If you don’t like the company, don’t use its products.’ I did this experiment to find out if that is possible, and I found out that it’s not—with the exception of Apple. …These companies are unavoidable because they control internet infrastructure, online commerce, and information flows.”

Why I (Still) Love Tech: In Defense of a Difficult Industry
Paul Ford | Wired
“The mysteries of software caught my eye when I was a boy, and I still see it with the same wonder, even though I’m now an adult. Proudshamed, yes, but I still love it, the mess of it, the code and toolkits, down to the pixels and the processors, and up to the buses and bridges. I love the whole made world. But I can’t deny that the miracle is over, and that there is an unbelievable amount of work left for us to do.”

The Peculiar Blindness of Experts
David Epstein | The Atlantic
“In business, esteemed (and lavishly compensated) forecasters routinely are wildly wrong in their predictions of everything from the next stock-market correction to the next housing boom. Reliable insight into the future is possible, however. It just requires a style of thinking that’s uncommon among experts who are certain that their deep knowledge has granted them a special grasp of what is to come.”

The Most Controversial Tree in the World
Rowan Jacobson | Pacific Standard
“…we are all GMOs, the beneficiaries of freakishly unlikely genetic mash-ups, and the real Island of Dr. Moreau is that blue-green botanical garden positioned third from the sun. Rather than changing the nature of nature, as I once thought, this might just be the very nature of nature.”

How an Augmented Reality Game Escalated Into Real-World Spy Warfare
Elizabeth Ballou | Vice
“In Ingress, players accept that every park and train station could be the site of an epic showdown, but that’s only the first step. The magic happens when other people accept that, too. When players feel like that magic is real, there are few limits to what they’ll do or where they’ll go for the sake of the game. ”

The Shady Cryptocurrency Boom on the Post-Soviet Frontier
Hannah Lucinda Smith | Wired
“…although the tourists won’t guess it as they stand at Kuchurgan’s gates, admiring how the evening light reflects off the silver plaque of Lenin, this plant is pumping out juice to a modern-day gold rush: a cryptocurrency boom that is underway all across the former Soviet Union, from the battlefields of eastern Ukraine to time-warp enclaves like Transnistria and freshly annexed Crimea.”

Scientists Are Totally Rethinking Animal Cognition
Ross Andersen | The Atlantic
“This idea that animals are conscious was long unpopular in the West, but it has lately found favor among scientists who study animal cognition. …For many scientists, the resonant mystery is no longer which animals are conscious, but which are not.”

I Wrote This on a 30-Year-Old Computer
Ian Bogost | The Atlantic
“[Back then] computing was an accompaniment to life, rather than the sieve through which all ideas and activities must filter. That makes using this 30-year-old device a surprising joy, one worth longing for on behalf of what it was at the time, rather than for the future it inaugurated.”

Image Credit: Wes Hicks / Unsplash Continue reading

Posted in Human Robots

#436470 Retail Robots Are on the Rise—at Every ...

The robots are coming! The robots are coming! On our sidewalks, in our skies, in our every store… Over the next decade, robots will enter the mainstream of retail.

As countless robots work behind the scenes to stock shelves, serve customers, and deliver products to our doorstep, the speed of retail will accelerate.

These changes are already underway. In this blog, we’ll elaborate on how robots are entering the retail ecosystem.

Let’s dive in.

Robot Delivery
On August 3rd, 2016, Domino’s Pizza introduced the Domino’s Robotic Unit, or “DRU” for short. The first home delivery pizza robot, the DRU looks like a cross between R2-D2 and an oversized microwave.

LIDAR and GPS sensors help it navigate, while temperature sensors keep hot food hot and cold food cold. Already, it’s been rolled out in ten countries, including New Zealand, France, and Germany, but its August 2016 debut was critical—as it was the first time we’d seen robotic home delivery.

And it won’t be the last.

A dozen or so different delivery bots are fast entering the market. Starship Technologies, for instance, a startup created by Skype founders Janus Friis and Ahti Heinla, has a general-purpose home delivery robot. Right now, the system is an array of cameras and GPS sensors, but upcoming models will include microphones, speakers, and even the ability—via AI-driven natural language processing—to communicate with customers. Since 2016, Starship has already carried out 50,000 deliveries in over 100 cities across 20 countries.

Along similar lines, Nuro—co-founded by Jiajun Zhu, one of the engineers who helped develop Google’s self-driving car—has a miniature self-driving car of its own. Half the size of a sedan, the Nuro looks like a toaster on wheels, except with a mission. This toaster has been designed to carry cargo—about 12 bags of groceries (version 2.0 will carry 20)—which it’s been doing for select Kroger stores since 2018. Domino’s also partnered with Nuro in 2019.

As these delivery bots take to our streets, others are streaking across the sky.

Back in 2016, Amazon came first, announcing Prime Air—the e-commerce giant’s promise of drone delivery in 30 minutes or less. Almost immediately, companies ranging from 7-Eleven and Walmart to Google and Alibaba jumped on the bandwagon.

While critics remain doubtful, the head of the FAA’s drone integration department recently said that drone deliveries may be “a lot closer than […] the skeptics think. [Companies are] getting ready for full-blown operations. We’re processing their applications. I would like to move as quickly as I can.”

In-Store Robots
While delivery bots start to spare us trips to the store, those who prefer shopping the old-fashioned way—i.e., in person—also have plenty of human-robot interaction in store. In fact, these robotics solutions have been around for a while.

In 2010, SoftBank introduced Pepper, a humanoid robot capable of understanding human emotion. Pepper is cute: 4 feet tall, with a white plastic body, two black eyes, a dark slash of a mouth, and a base shaped like a mermaid’s tail. Across her chest is a touch screen to aid in communication. And there’s been a lot of communication. Pepper’s cuteness is intentional, as it matches its mission: help humans enjoy life as much as possible.

Over 12,000 Peppers have been sold. She serves ice cream in Japan, greets diners at a Pizza Hut in Singapore, and dances with customers at a Palo Alto electronics store. More importantly, Pepper’s got company.

Walmart uses shelf-stocking robots for inventory control. Best Buy uses a robo-cashier, allowing select locations to operate 24-7. And Lowe’s Home Improvement employs the LoweBot—a giant iPad on wheels—to help customers find the items they need while tracking inventory along the way.

Warehouse Bots
Yet the biggest benefit robots provide might be in-warehouse logistics.

In 2012, when Amazon dished out $775 million for Kiva Systems, few could predict that just 6 years later, 45,000 Kiva robots would be deployed at all of their fulfillment centers, helping process a whopping 306 items per second during the Christmas season.

And many other retailers are following suit.

Order jeans from the Gap, and soon they’ll be sorted, packed, and shipped with the help of a Kindred robot. Remember the old arcade game where you picked up teddy bears with a giant claw? That’s Kindred, only her claw picks up T-shirts, pants, and the like, placing them in designated drop-off zones that resemble tiny mailboxes (for further sorting or shipping).

The big deal here is democratization. Kindred’s robot is cheap and easy to deploy, allowing smaller companies to compete with giants like Amazon.

Final Thoughts
For retailers interested in staying in business, there doesn’t appear to be much choice in the way of robotics.

By 2024, the US minimum wage is projected to be $15 an hour (the House of Representatives has already passed the bill, but the wage hike is meant to unfold gradually between now and 2025), and many consider that number far too low.

Yet, as human labor costs continue to climb, robots won’t just be coming, they’ll be here, there, and everywhere. It’s going to become increasingly difficult for store owners to justify human workers who call in sick, show up late, and can easily get injured. Robots work 24-7. They never take a day off, never need a bathroom break, health insurance, or parental leave.

Going forward, this spells a growing challenge of technological unemployment (a blog topic I will cover in the coming month). But in retail, robotics usher in tremendous benefits for companies and customers alike.

And while professional re-tooling initiatives and the transition of human capital from retail logistics to a booming experience economy take hold, robotic retail interaction and last-mile delivery will fundamentally transform our relationship with commerce.

This blog comes from The Future is Faster Than You Think—my upcoming book, to be released Jan 28th, 2020. To get an early copy and access up to $800 worth of pre-launch giveaways, sign up here!

Join Me
(1) A360 Executive Mastermind: If you’re an exponentially and abundance-minded entrepreneur who would like coaching directly from me, consider joining my Abundance 360 Mastermind, a highly selective community of 360 CEOs and entrepreneurs who I coach for 3 days every January in Beverly Hills, Ca. Through A360, I provide my members with context and clarity about how converging exponential technologies will transform every industry. I’m committed to running A360 for the course of an ongoing 25-year journey as a “countdown to the Singularity.”

If you’d like to learn more and consider joining our 2020 membership, apply here.

(2) Abundance-Digital Online Community: I’ve also created a Digital/Online community of bold, abundance-minded entrepreneurs called Abundance-Digital. Abundance-Digital is Singularity University’s ‘onramp’ for exponential entrepreneurs — those who want to get involved and play at a higher level. Click here to learn more.

(Both A360 and Abundance-Digital are part of Singularity University — your participation opens you to a global community.)

Image Credit: Image by imjanuary from Pixabay Continue reading

Posted in Human Robots

#436258 For Centuries, People Dreamed of a ...

This is part six of a six-part series on the history of natural language processing.

In February of this year, OpenAI, one of the foremost artificial intelligence labs in the world, announced that a team of researchers had built a powerful new text generator called the Generative Pre-Trained Transformer 2, or GPT-2 for short. The researchers used a reinforcement learning algorithm to train their system on a broad set of natural language processing (NLP) capabilities, including reading comprehension, machine translation, and the ability to generate long strings of coherent text.

But as is often the case with NLP technology, the tool held both great promise and great peril. Researchers and policy makers at the lab were concerned that their system, if widely released, could be exploited by bad actors and misappropriated for “malicious purposes.”

The people of OpenAI, which defines its mission as “discovering and enacting the path to safe artificial general intelligence,” were concerned that GPT-2 could be used to flood the Internet with fake text, thereby degrading an already fragile information ecosystem. For this reason, OpenAI decided that it would not release the full version of GPT-2 to the public or other researchers.

GPT-2 is an example of a technique in NLP called language modeling, whereby the computational system internalizes a statistical blueprint of a text so it’s able to mimic it. Just like the predictive text on your phone—which selects words based on words you’ve used before—GPT-2 can look at a string of text and then predict what the next word is likely to be based on the probabilities inherent in that text.

GPT-2 can be seen as a descendant of the statistical language modeling that the Russian mathematician A. A. Markov developed in the early 20th century (covered in part three of this series).

GPT-2 used cutting-edge machine learning algorithms to do linguistic analysis with over 1.5 million parameters.

What’s different with GPT-2, though, is the scale of the textual data modeled by the system. Whereas Markov analyzed a string of 20,000 letters to create a rudimentary model that could predict the likelihood of the next letter of a text being a consonant or a vowel, GPT-2 used 8 million articles scraped from Reddit to predict what the next word might be within that entire dataset.

And whereas Markov manually trained his model by counting only two parameters—vowels and consonants—GPT-2 used cutting-edge machine learning algorithms to do linguistic analysis with over 1.5 million parameters, burning through huge amounts of computational power in the process.

The results were impressive. In their blog post, OpenAI reported that GPT-2 could generate synthetic text in response to prompts, mimicking whatever style of text it was shown. If you prompt the system with a line of William Blake’s poetry, it can generate a line back in the Romantic poet’s style. If you prompt the system with a cake recipe, you get a newly invented recipe in response.

Perhaps the most compelling feature of GPT-2 is that it can answer questions accurately. For example, when OpenAI researchers asked the system, “Who wrote the book The Origin of Species?”—it responded: “Charles Darwin.” While only able to respond accurately some of the time, the feature does seem to be a limited realization of Gottfried Leibniz’s dream of a language-generating machine that could answer any and all human questions (described in part two of this series).

After observing the power of the new system in practice, OpenAI elected not to release the fully trained model. In the lead up to its release in February, there had been heightened awareness about “deepfakes”—synthetic images and videos, generated via machine learning techniques, in which people do and say things they haven’t really done and said. Researchers at OpenAI worried that GPT-2 could be used to essentially create deepfake text, making it harder for people to trust textual information online.

Responses to this decision varied. On one hand, OpenAI’s caution prompted an overblown reaction in the media, with articles about the “dangerous” technology feeding into the Frankenstein narrative that often surrounds developments in AI.

Others took issue with OpenAI’s self-promotion, with some even suggesting that OpenAI purposefully exaggerated GPT-2s power in order to create hype—while contravening a norm in the AI research community, where labs routinely share data, code, and pre-trained models. As machine learning researcher Zachary Lipton tweeted, “Perhaps what's *most remarkable* about the @OpenAI controversy is how *unremarkable* the technology is. Despite their outsize attention & budget, the research itself is perfectly ordinary—right in the main branch of deep learning NLP research.”

OpenAI stood by its decision to release only a limited version of GPT-2, but has since released larger models for other researchers and the public to experiment with. As yet, there has been no reported case of a widely distributed fake news article generated by the system. But there have been a number of interesting spin-off projects, including GPT-2 poetry and a webpage where you can prompt the system with questions yourself.

Mimicking humans on Reddit, the bots have long conversations about a variety of topics, including conspiracy theories and
Star Wars movies.

There’s even a Reddit group populated entirely with text produced by GPT-2-powered bots. Mimicking humans on Reddit, the bots have long conversations about a variety of topics, including conspiracy theories and Star Wars movies.

This bot-powered conversation may signify the new condition of life online, where language is increasingly created by a combination of human and non-human agents, and where maintaining the distinction between human and non-human, despite our best efforts, is increasingly difficult.

The idea of using rules, mechanisms, and algorithms to generate language has inspired people in many different cultures throughout history. But it’s in the online world that this powerful form of wordcraft may really find its natural milieu—in an environment where the identity of speakers becomes more ambiguous, and perhaps, less relevant. It remains to be seen what the consequences will be for language, communication, and our sense of human identity, which is so bound up with our ability to speak in natural language.

This is the sixth installment of a six-part series on the history of natural language processing. Last week’s post explained how an innocent Microsoft chatbot turned instantly racist on Twitter.

You can also check out our prior series on the untold history of AI. Continue reading

Posted in Human Robots