Tag Archives: smart

#436252 After AI, Fashion and Shopping Will ...

AI and broadband are eating retail for breakfast. In the first half of 2019, we’ve seen 19 retailer bankruptcies. And the retail apocalypse is only accelerating.

What’s coming next is astounding. Why drive when you can speak? Revenue from products purchased via voice commands is expected to quadruple from today’s US$2 billion to US$8 billion by 2023.

Virtual reality, augmented reality, and 3D printing are converging with artificial intelligence, drones, and 5G to transform shopping on every dimension. And as a result, shopping is becoming dematerialized, demonetized, democratized, and delocalized… a top-to-bottom transformation of the retail world.

Welcome to Part 1 of our series on the future of retail, a deep-dive into AI and its far-reaching implications.

Let’s dive in.

A Day in the Life of 2029
Welcome to April 21, 2029, a sunny day in Dallas. You’ve got a fundraising luncheon tomorrow, but nothing to wear. The last thing you want to do is spend the day at the mall.

No sweat. Your body image data is still current, as you were scanned only a week ago. Put on your VR headset and have a conversation with your AI. “It’s time to buy a dress for tomorrow’s event” is all you have to say. In a moment, you’re teleported to a virtual clothing store. Zero travel time. No freeway traffic, parking hassles, or angry hordes wielding baby strollers.

Instead, you’ve entered your own personal clothing store. Everything is in your exact size…. And I mean everything. The store has access to nearly every designer and style on the planet. Ask your AI to show you what’s hot in Shanghai, and presto—instant fashion show. Every model strutting down the runway looks exactly like you, only dressed in Shanghai’s latest.

When you’re done selecting an outfit, your AI pays the bill. And as your new clothes are being 3D printed at a warehouse—before speeding your way via drone delivery—a digital version has been added to your personal inventory for use at future virtual events.

The cost? Thanks to an era of no middlemen, less than half of what you pay in stores today. Yet this future is not all that far off…

Digital Assistants
Let’s begin with the basics: the act of turning desire into purchase.

Most of us navigate shopping malls or online marketplaces alone, hoping to stumble across the right item and fit. But if you’re lucky enough to employ a personal assistant, you have the luxury of describing what you want to someone who knows you well enough to buy that exact right thing most of the time.

For most of us who don’t, enter the digital assistant.

Right now, the four horsemen of the retail apocalypse are waging war for our wallets. Amazon’s Alexa, Google’s Now, Apple’s Siri, and Alibaba’s Tmall Genie are going head-to-head in a battle to become the platform du jour for voice-activated, AI-assisted commerce.

For baby boomers who grew up watching Captain Kirk talk to the Enterprise’s computer on Star Trek, digital assistants seem a little like science fiction. But for millennials, it’s just the next logical step in a world that is auto-magical.

And as those millennials enter their consumer prime, revenue from products purchased via voice-driven commands is projected to leap from today’s US$2 billion to US$8 billion by 2023.

We are already seeing a major change in purchasing habits. On average, consumers using Amazon Echo spent more than standard Amazon Prime customers: US$1,700 versus US$1,300.

And as far as an AI fashion advisor goes, those too are here, courtesy of both Alibaba and Amazon. During its annual Singles’ Day (November 11) shopping festival, Alibaba’s FashionAI concept store uses deep learning to make suggestions based on advice from human fashion experts and store inventory, driving a significant portion of the day’s US$25 billion in sales.

Similarly, Amazon’s shopping algorithm makes personalized clothing recommendations based on user preferences and social media behavior.

Customer Service
But AI is disrupting more than just personalized fashion and e-commerce. Its next big break will take place in the customer service arena.

According to a recent Zendesk study, good customer service increases the possibility of a purchase by 42 percent, while bad customer service translates into a 52 percent chance of losing that sale forever. This means more than half of us will stop shopping at a store due to a single disappointing customer service interaction. These are significant financial stakes. They’re also problems perfectly suited for an AI solution.

During the 2018 Google I/O conference, CEO Sundar Pichai demoed the Google Duplex, their next generation digital assistant. Pichai played the audience a series of pre-recorded phone calls made by Google Duplex. The first call made a reservation at a restaurant, the second one booked a haircut appointment, amusing the audience with a long “hmmm” mid-call.

In neither case did the person on the other end of the phone have any idea they were talking to an AI. The system’s success speaks to how seamlessly AI can blend into our retail lives and how convenient it will continue to make them. The same technology Pichai demonstrated that can make phone calls for consumers can also answer phones for retailers—a development that’s unfolding in two different ways:

(1) Customer service coaches: First, for organizations interested in keeping humans involved, there’s Beyond Verbal, a Tel Aviv-based startup that has built an AI customer service coach. Simply by analyzing customer voice intonation, the system can tell whether the person on the phone is about to blow a gasket, is genuinely excited, or anything in between.

Based on research of over 70,000 subjects in more than 30 languages, Beyond Verbal’s app can detect 400 different markers of human moods, attitudes, and personality traits. Already it’s been integrated in call centers to help human sales agents understand and react to customer emotions, making those calls more pleasant, and also more profitable.

For example, by analyzing word choice and vocal style, Beyond Verbal’s system can tell what kind of shopper the person on the line actually is. If they’re an early adopter, the AI alerts the sales agent to offer them the latest and greatest. If they’re more conservative, it suggests items more tried-and-true.

(2) Replacing customer service agents: Second, companies like New Zealand’s Soul Machines are working to replace human customer service agents altogether. Powered by IBM’s Watson, Soul Machines builds lifelike customer service avatars designed for empathy, making them one of many helping to pioneer the field of emotionally intelligent computing.

With their technology, 40 percent of all customer service interactions are now resolved with a high degree of satisfaction, no human intervention needed. And because the system is built using neural nets, it’s continuously learning from every interaction—meaning that percentage will continue to improve.

The number of these interactions continues to grow as well. Software manufacturer Autodesk now includes a Soul Machine avatar named AVA (Autodesk Virtual Assistant) in all of its new offerings. She lives in a small window on the screen, ready to soothe tempers, troubleshoot problems, and forever banish those long tech support hold times.

For Daimler Financial Services, Soul Machines built an avatar named Sarah, who helps customers with arguably three of modernity’s most annoying tasks: financing, leasing, and insuring a car.

This isn’t just about AI—it’s about AI converging with additional exponentials. Add networks and sensors to the story and it raises the scale of disruption, upping the FQ—the frictionless quotient—in our frictionless shopping adventure.

Final Thoughts
AI makes retail cheaper, faster, and more efficient, touching everything from customer service to product delivery. It also redefines the shopping experience, making it frictionless and—once we allow AI to make purchases for us—ultimately invisible.

Prepare for a future in which shopping is dematerialized, demonetized, democratized, and delocalized—otherwise known as “the end of malls.”

Of course, if you wait a few more years, you’ll be able to take an autonomous flying taxi to Westfield’s Destination 2028—so perhaps today’s converging exponentials are not so much spelling the end of malls but rather the beginning of an experience economy far smarter, more immersive, and whimsically imaginative than today’s shopping centers.

Either way, it’s a top-to-bottom transformation of the retail world.

Over the coming blog series, we will continue our discussion of the future of retail. Stay tuned to learn new implications for your business and how to future-proof your company in an age of smart, ultra-efficient, experiential retail.

Want a copy of my next book? If you’ve enjoyed this blogified snippet of The Future is Faster Than You Think, sign up here to be eligible for an early copy and access up to $800 worth of pre-launch giveaways!

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.)

This article originally appeared on diamandis.com. Read the original article here.

Image Credit: Image by Pexels from Pixabay Continue reading

Posted in Human Robots

#436217 4 Ways Autonomous Technology Can ...

Photo by Matan Segev from Pexels Autonomous technologies are changing the way we interact with the world around us exponentially. Artificial intelligence (AI) and machine learning (ML) technology is responsible for automated shopping and smart homes, among many other consumers innovations. And, in the business world, autonomous tools are changing the workplace as we know it. While many …

The post 4 Ways Autonomous Technology Can Streamline Your Business appeared first on TFOT. Continue reading

Posted in Human Robots

#436188 The Blogger Behind “AI ...

Sure, artificial intelligence is transforming the world’s societies and economies—but can an AI come up with plausible ideas for a Halloween costume?

Janelle Shane has been asking such probing questions since she started her AI Weirdness blog in 2016. She specializes in training neural networks (which underpin most of today’s machine learning techniques) on quirky data sets such as compilations of knitting instructions, ice cream flavors, and names of paint colors. Then she asks the neural net to generate its own contributions to these categories—and hilarity ensues. AI is not likely to disrupt the paint industry with names like “Ronching Blue,” “Dorkwood,” and “Turdly.”

Shane’s antics have a serious purpose. She aims to illustrate the serious limitations of today’s AI, and to counteract the prevailing narrative that describes AI as well on its way to superintelligence and complete human domination. “The danger of AI is not that it’s too smart,” Shane writes in her new book, “but that it’s not smart enough.”

The book, which came out on Tuesday, is called You Look Like a Thing and I Love You. It takes its odd title from a list of AI-generated pick-up lines, all of which would at least get a person’s attention if shouted, preferably by a robot, in a crowded bar. Shane’s book is shot through with her trademark absurdist humor, but it also contains real explanations of machine learning concepts and techniques. It’s a painless way to take AI 101.

She spoke with IEEE Spectrum about the perils of placing too much trust in AI systems, the strange AI phenomenon of “giraffing,” and her next potential Halloween costume.

Janelle Shane on . . .

The un-delicious origin of her blog
“The narrower the problem, the smarter the AI will seem”
Why overestimating AI is dangerous
Giraffing!
Machine and human creativity

The un-delicious origin of her blog IEEE Spectrum: You studied electrical engineering as an undergrad, then got a master’s degree in physics. How did that lead to you becoming the comedian of AI?
Janelle Shane: I’ve been interested in machine learning since freshman year of college. During orientation at Michigan State, a professor who worked on evolutionary algorithms gave a talk about his work. It was full of the most interesting anecdotes–some of which I’ve used in my book. He told an anecdote about people setting up a machine learning algorithm to do lens design, and the algorithm did end up designing an optical system that works… except one of the lenses was 50 feet thick, because they didn’t specify that it couldn’t do that.
I started working in his lab on optics, doing ultra-short laser pulse work. I ended up doing a lot more optics than machine learning, but I always found it interesting. One day I came across a list of recipes that someone had generated using a neural net, and I thought it was hilarious and remembered why I thought machine learning was so cool. That was in 2016, ages ago in machine learning land.
Spectrum: So you decided to “establish weirdness as your goal” for your blog. What was the first weird experiment that you blogged about?
Shane: It was generating cookbook recipes. The neural net came up with ingredients like: “Take ¼ pounds of bones or fresh bread.” That recipe started out: “Brown the salmon in oil, add creamed meat to the mixture.” It was making mistakes that showed the thing had no memory at all.
Spectrum: You say in the book that you can learn a lot about AI by giving it a task and watching it flail. What do you learn?
Shane: One thing you learn is how much it relies on surface appearances rather than deep understanding. With the recipes, for example: It got the structure of title, category, ingredients, instructions, yield at the end. But when you look more closely, it has instructions like “Fold the water and roll it into cubes.” So clearly this thing does not understand water, let alone the other things. It’s recognizing certain phrases that tend to occur, but it doesn’t have a concept that these recipes are describing something real. You start to realize how very narrow the algorithms in this world are. They only know exactly what we tell them in our data set.
BACK TO TOP↑ “The narrower the problem, the smarter the AI will seem” Spectrum: That makes me think of DeepMind’s AlphaGo, which was universally hailed as a triumph for AI. It can play the game of Go better than any human, but it doesn’t know what Go is. It doesn’t know that it’s playing a game.
Shane: It doesn’t know what a human is, or if it’s playing against a human or another program. That’s also a nice illustration of how well these algorithms do when they have a really narrow and well-defined problem.
The narrower the problem, the smarter the AI will seem. If it’s not just doing something repeatedly but instead has to understand something, coherence goes down. For example, take an algorithm that can generate images of objects. If the algorithm is restricted to birds, it could do a recognizable bird. If this same algorithm is asked to generate images of any animal, if its task is that broad, the bird it generates becomes an unrecognizable brown feathered smear against a green background.
Spectrum: That sounds… disturbing.
Shane: It’s disturbing in a weird amusing way. What’s really disturbing is the humans it generates. It hasn’t seen them enough times to have a good representation, so you end up with an amorphous, usually pale-faced thing with way too many orifices. If you asked it to generate an image of a person eating pizza, you’ll have blocks of pizza texture floating around. But if you give that image to an image-recognition algorithm that was trained on that same data set, it will say, “Oh yes, that’s a person eating pizza.”
BACK TO TOP↑ Why overestimating AI is dangerous Spectrum: Do you see it as your role to puncture the AI hype?
Shane: I do see it that way. Not a lot of people are bringing out this side of AI. When I first started posting my results, I’d get people saying, “I don’t understand, this is AI, shouldn’t it be better than this? Why doesn't it understand?” Many of the impressive examples of AI have a really narrow task, or they’ve been set up to hide how little understanding it has. There’s a motivation, especially among people selling products based on AI, to represent the AI as more competent and understanding than it actually is.
Spectrum: If people overestimate the abilities of AI, what risk does that pose?
Shane: I worry when I see people trusting AI with decisions it can’t handle, like hiring decisions or decisions about moderating content. These are really tough tasks for AI to do well on. There are going to be a lot of glitches. I see people saying, “The computer decided this so it must be unbiased, it must be objective.”

“If the algorithm’s task is to replicate human hiring decisions, it’s going to glom onto gender bias and race bias.”
—Janelle Shane, AI Weirdness blogger
That’s another thing I find myself highlighting in the work I’m doing. If the data includes bias, the algorithm will copy that bias. You can’t tell it not to be biased, because it doesn’t understand what bias is. I think that message is an important one for people to understand.
If there’s bias to be found, the algorithm is going to go after it. It’s like, “Thank goodness, finally a signal that’s reliable.” But for a tough problem like: Look at these resumes and decide who’s best for the job. If its task is to replicate human hiring decisions, it’s going to glom onto gender bias and race bias. There’s an example in the book of a hiring algorithm that Amazon was developing that discriminated against women, because the historical data it was trained on had that gender bias.
Spectrum: What are the other downsides of using AI systems that don’t really understand their tasks?
Shane: There is a risk in putting too much trust in AI and not examining its decisions. Another issue is that it can solve the wrong problems, without anyone realizing it. There have been a couple of cases in medicine. For example, there was an algorithm that was trained to recognize things like skin cancer. But instead of recognizing the actual skin condition, it latched onto signals like the markings a surgeon makes on the skin, or a ruler placed there for scale. It was treating those things as a sign of skin cancer. It’s another indication that these algorithms don’t understand what they’re looking at and what the goal really is.
BACK TO TOP↑ Giraffing Spectrum: In your blog, you often have neural nets generate names for things—such as ice cream flavors, paint colors, cats, mushrooms, and types of apples. How do you decide on topics?
Shane: Quite often it’s because someone has written in with an idea or a data set. They’ll say something like, “I’m the MIT librarian and I have a whole list of MIT thesis titles.” That one was delightful. Or they’ll say, “We are a high school robotics team, and we know where there’s a list of robotics team names.” It’s fun to peek into a different world. I have to be careful that I’m not making fun of the naming conventions in the field. But there’s a lot of humor simply in the neural net’s complete failure to understand. Puns in particular—it really struggles with puns.
Spectrum: Your blog is quite absurd, but it strikes me that machine learning is often absurd in itself. Can you explain the concept of giraffing?
Shane: This concept was originally introduced by [internet security expert] Melissa Elliott. She proposed this phrase as a way to describe the algorithms’ tendency to see giraffes way more often than would be likely in the real world. She posted a whole bunch of examples, like a photo of an empty field in which an image-recognition algorithm has confidently reported that there are giraffes. Why does it think giraffes are present so often when they’re actually really rare? Because they’re trained on data sets from online. People tend to say, “Hey look, a giraffe!” And then take a photo and share it. They don’t do that so often when they see an empty field with rocks.
There’s also a chatbot that has a delightful quirk. If you show it some photo and ask it how many giraffes are in the picture, it will always answer with some non zero number. This quirk comes from the way the training data was generated: These were questions asked and answered by humans online. People tended not to ask the question “How many giraffes are there?” when the answer was zero. So you can show it a picture of someone holding a Wii remote. If you ask it how many giraffes are in the picture, it will say two.
BACK TO TOP↑ Machine and human creativity Spectrum: AI can be absurd, and maybe also creative. But you make the point that AI art projects are really human-AI collaborations: Collecting the data set, training the algorithm, and curating the output are all artistic acts on the part of the human. Do you see your work as a human-AI art project?
Shane: Yes, I think there is artistic intent in my work; you could call it literary or visual. It’s not so interesting to just take a pre-trained algorithm that’s been trained on utilitarian data, and tell it to generate a bunch of stuff. Even if the algorithm isn’t one that I’ve trained myself, I think about, what is it doing that’s interesting, what kind of story can I tell around it, and what do I want to show people.

The Halloween costume algorithm “was able to draw on its knowledge of which words are related to suggest things like sexy barnacle.”
—Janelle Shane, AI Weirdness blogger
Spectrum: For the past three years you’ve been getting neural nets to generate ideas for Halloween costumes. As language models have gotten dramatically better over the past three years, are the costume suggestions getting less absurd?
Shane: Yes. Before I would get a lot more nonsense words. This time I got phrases that were related to real things in the data set. I don’t believe the training data had the words Flying Dutchman or barnacle. But it was able to draw on its knowledge of which words are related to suggest things like sexy barnacle and sexy Flying Dutchman.
Spectrum: This year, I saw on Twitter that someone made the gothy giraffe costume happen. Would you ever dress up for Halloween in a costume that the neural net suggested?
Shane: I think that would be fun. But there would be some challenges. I would love to go as the sexy Flying Dutchman. But my ambition may constrict me to do something more like a list of leg parts.
BACK TO TOP↑ Continue reading

Posted in Human Robots

#436184 Why People Demanded Privacy to Confide ...

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

Between 1964 and 1966, Joseph Weizenbaum, a German American computer scientist at MIT’s artificial intelligence lab, developed the first-ever chatbot [PDF].

While there were already some rudimentary digital language generators in existence—programs that could spit out somewhat coherent lines of text—Weizenbaum’s program was the first designed explicitly for interactions with humans. The user could type in some statement or set of statements in their normal language, press enter, and receive a response from the machine. As Weizenbaum explained, his program made “certain kinds of natural-language conversation between man and computer possible.”

He named the program Eliza after Eliza Doolittle, the working-class hero of George Bernard Shaw’s Pygmalion who learns how to talk with an upper-class accent. The new Eliza was written for the 36-bit IBM 7094, an early transistorized mainframe computer, in a programming language that Weizenbaum developed called MAD-SLIP.

Because computer time was a valuable resource, Eliza could only be run via a time-sharing system; the user interacted with the program remotely via an electric typewriter and printer. When the user typed in a sentence and pressed enter, a message was sent to the mainframe computer. Eliza scanned the message for the presence of a keyword and used it in a new sentence to form a response that was sent back, printed out, and read by the user.

To encourage ongoing dialogue, Weizenbaum designed Eliza to simulate the type of conversational style used by a Rogerian psychoanalyst. The program would take something the user said and reflect it back with a question, as can be seen in the example below. (Notice how the program takes keywords like “boyfriend” and “depressed” and re-uses them.)

Human: Men are all alike.

Computer: IN WHAT WAY?

Human: They're always bugging us about something or other.

Computer: CAN YOU THINK OF A SPECIFIC EXAMPLE?

Human: Well, my boyfriend made me come here.

Computer: YOUR BOYFRIEND MADE YOU COME HERE

Human: He says I'm depressed much of the time.

Computer: I AM SORRY TO HEAR YOU ARE DEPRESSED

Human: It's true. I am unhappy.

Weizenbaum chose this mode of dialogue for Eliza because it gave the impression that the computer understood what was being said without having to offer anything new to the conversation. It created the illusion of comprehension and engagement in a mere 200 lines of code.

To test Eliza’s capacity to engage an interlocutor, Weizenbaum invited students and colleagues into his office and let them chat with the machine while he looked on. He noticed, with some concern, that during their brief interactions with Eliza, many users began forming emotional attachments to the algorithm. They would open up to the machine and confess problems they were facing in their lives and relationships.

During their brief interactions with Eliza, many users began forming emotional attachments to the algorithm.

Even more surprising was that this sense of intimacy persisted even after Weizenbaum described how the machine worked and explained that it didn’t really understand anything that was being said. Weizenbaum was most troubled when his secretary, who had watched him build the program from scratch over many months, insisted that he leave the room so she could talk to Eliza in private.

For Weizenbaum, this experiment with Eliza made him question an idea that Alan Turing had proposed in 1950 about machine intelligence. In his paper, entitled “Computing Machinery and Intelligence,” Turing suggested that if a computer could conduct a convincingly human conversation in text, one could assume it was intelligent—an idea that became the basis of the famous Turing Test.

But Eliza demonstrated that convincing communication between a human and a machine could take place even if comprehension only flowed from one side: The simulation of intelligence, rather than intelligence itself, was enough to fool people. Weizenbaum called this the Eliza effect, and believed it was a type of “delusional thinking” that humanity would collectively suffer from in the digital age. This insight was a profound shock for Weizenbaum, and one that came to define his intellectual trajectory over the next decade.

The simulation of intelligence, rather than intelligence itself, was enough to fool people.

In 1976, he published Computing Power and Human Reason: From Judgment to Calculation [PDF], which offered a long meditation on why people are willing to believe that a simple machine might be able to understand their complex human emotions.

In this book, he argues that the Eliza effect signifies a broader pathology afflicting “modern man.” In a world conquered by science, technology, and capitalism, people had grown accustomed to viewing themselves as isolated cogs in a large and uncaring machine. In such a diminished social world, Weizenbaum reasoned, people had grown so desperate for connection that they put aside their reason and judgment in order to believe that a program could care about their problems.

Weizenbaum spent the rest of his life developing this humanistic critique of artificial intelligence and digital technology. His mission was to remind people that their machines were not as smart as they were often said to be. And that even though it sometimes appeared as though they could talk, they were never really listening.

This is the fourth installment of a six-part series on the history of natural language processing. Last week’s post described Andrey Markov and Claude Shannon’s painstaking efforts to create statistical models of language for text generation. Come back next Monday for part five, “In 2016, Microsoft’s Racist Chatbot Revealed the Dangers of Conversation.”

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

Posted in Human Robots

#436151 Natural Language Processing Dates Back ...

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

We’re in the middle of a boom time for natural language processing (NLP), the field of computer science that focuses on linguistic interactions between humans and machines. Thanks to advances in machine learning over the past decade, we’ve seen vast improvements in speech recognition and machine translation software. Language generators are now good enough to write coherent news articles, and virtual agents like Siri and Alexa are becoming part of our daily lives.

Most trace the origins of this field back to the beginning of the computer age, when Alan Turing, writing in 1950, imagined a smart machine that could interact fluently with a human via typed text on a screen. For this reason, machine-generated language is mostly understood as a digital phenomenon—and a central goal of artificial intelligence (AI) research.

This six-part series will challenge that common understanding of NLP. In fact, attempts to design formal rules and machines that can analyze, process, and generate language go back hundreds of years.

Attempts to design formal rules and machines that can analyze, process, and generate language go back hundreds of years.

While specific technologies have changed over time, the basic idea of treating language as a material that can be artificially manipulated by rule-based systems has been pursued by many people in many cultures and for many different reasons. These historical experiments reveal the promise and perils of attempting to simulate human language in non-human ways—and they hold lessons for today’s practitioners of cutting-edge NLP techniques.

The story begins in medieval Spain. In the late 1200s, a Jewish mystic by the name of Abraham Abulafia sat down at a table in his small house in Barcelona, picked up a quill, dipped it in ink, and began combining the letters of the Hebrew alphabet in strange and seemingly random ways. Aleph with Bet, Bet with Gimmel, Gimmel with Aleph and Bet, and so on.

Abulafia called this practice “the science of the combination of letters.” He wasn’t actually combining letters at random; instead he was carefully following a secret set of rules that he had devised while studying an ancient Kabbalistic text called the Sefer Yetsirah. This book describes how God created “all that is formed and all that is spoken” by combining Hebrew letters according to sacred formulas. In one section, God exhausts all possible two-letter combinations of the 22 Hebrew letters.

By studying the Sefer Yetsirah, Abulafia gained the insight that linguistic symbols can be manipulated with formal rules in order to create new, interesting, insightful sentences. To this end, he spent months generating thousands of combinations of the 22 letters of the Hebrew alphabet and eventually emerged with a series of books that he claimed were endowed with prophetic wisdom.

For Abulafia, generating language according to divine rules offered insight into the sacred and the unknown, or as he put it, allowed him to “grasp things which by human tradition or by thyself thou would not be able to know.”

Combining letters to generate language allows thou to “grasp things which by human tradition or by thyself thou would not be able to know.”
—Abraham Abulafia, mystic

But other Jewish scholars considered this rudimentary language generation a dangerous act that bordered on the profane. The Talmud tells stories of rabbis who, by the magical act of permuting language according to the formulas set out in the Sefer Yetsirah, created artificial creatures called golems. In these tales, rabbis manipulated the letters of the Hebrew alphabet to replicate God’s act of creation, using the sacred formulas to imbue inanimate objects with life.

In some of these myths, the rabbis used this skill for practical reasons, to make animals to eat when hungry or servants to help them with domestic duties. But many of these golem stories end badly. In one particularly well-known fable, Judah Loew ben Bezalel, the 16th century rabbi of Prague, used the sacred practice of letter combinatorics to conjure a golem to protect the Jewish community from antisemitic attacks, only to see the golem turn violently on him instead.

This “science of the combination of letters” was a rudimentary form of natural language processing, as it involved combining letters of the Hebrew alphabet according to specific rules. For Kabbalists, it was a double-edged sword: a way to access new forms of knowledge and wisdom, but also an inherently dangerous practice that could bring about unintended consequences.

This tension reappears throughout the long history of language processing, and still echoes in discussions about the most cutting-edge NLP technology of our digital era.

This is the first installment of a six-part series on the history of natural language processing. Come back next Monday for part two, “In the 17th Century, Leibniz Dreamed of a Machine That Could Calculate Ideas​.”

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

Posted in Human Robots