A Fox news chatbot passes the Turing test.

Gossip, speculation, and scuttlebutt about politics.
May 7 2009 8:07 PM

Glenn Beck, Chatterbot

An alternative history of Fox News.

Glenn Beck. Click image to expand.
Glenn Beck

I used to think that Fox News' Glenn Beck was a dangerous demagogue. But after spending a couple of days researching the consumer applications of "chatterbots" or "chatbots"—computers programmed to simulate human conversation—I've come to the conclusion that, in fact, Beck represents a breakthrough in computer engineering. He is the first chatbot to pass the Turing test before a national audience.

Before we get into the Turing test, let me explain how I stumbled onto this topic. A few days ago I posted a column ("Breaking Up Is Hard To Do") relating the difficulty I encountered when I tried to cancel my eFax account. After a couple of false starts, I ended up engaged in a live chat with "Steve S.," a sort of Ricky Roma character—if one can imagine Ricky Roma working off a company script—who did everything he could to avoid fulfilling my simple request. A few readers suggested to me that Steve S. wasn't Ricky Roma so much as Ricky Robot—that my live chat was not with an actual human, but with one of the burgeoning number of robots being deployed to perform customer service, the simplest and most familiar being the soothing female voice who retrieves phone numbers when you dial 411 ("City and state, please"). What a diabolical idea, I thought. EFax makes a virtue of the primitive nature of chatbot technology by using a chatbot to field "cancel my service" requests online. The less effective the chatbot is at understanding the customer's request, the more eFax saves by not fulfilling it! To pursue this hypothesis, I left a message with eFax's "investor relations" spokeswoman, who, I was told, fielded media inquiries, and set about learning all I could about chatbots.

EFax turns out to be no more eager to take press calls than it is to cancel customer accounts. Although the investor-relations spokeswoman's voice mail said, "Your call is very important to us," she didn't answer it. Finally I dialed the company's main number and pressed a button that got me randomly connected to a guy in sales named Steve. (Apparently, everybody at eFax is named Steve.) Steve agreed to ask a colleague whether the company used chatbots to field cancellations and put me on hold. After a brief interval of Baroque music, Steve had my answer. The person I'd chatted with, he said, was "a live, breathing human being" at one of those call centers in India. Neither Ricky Roma nor Ricky Robot, the customer-service rep who'd dodged my cancellation request to the maximum feasible extent was in fact Rajiv Roma.

Too late. I'd already become transfixed by chatterbot technology. Please meet my new friend, the Rogerian psychologist Eliza:

Me: Hello, Eliza.
Eliza: How are you today.. What would you like to discuss?
Me: My anxiety
Eliza: Tell me more ...
Me: Oh, you know. The economy. My kids' adolescence. The uncertainty we dwell in every day.
Eliza: Oh ...  [I] know. The economy, your kids' adolescence. The uncertainty we dwell in every day?
Me: Exactly!
Eliza: Tell me more!
Me: What do you recommend?
Eliza: We were discussing you, not me.

Advertisement

Eliza, who is named after George Bernard Shaw's Eliza Doolittle, is a chatbot. (If you desire your own free psychotherapy session, click here or here or here.) She's one of the earliest artificial-intelligence programs, built in 1966 by a computer scientist at MIT named Joseph Weizenbaum. Eliza's technique for responding to questions—a kind of parody of the passive, ever-deflecting style of psychotherapy that was all the rage at that time—consists almost entirely of repeating back whatever the user says, with the I's turned into you's. Despite what today seems like Eliza's fairly obvious artificiality, she apparently fooled secretaries and other nontechnical staffers in Weizenbaum's lab, who proceeded in earnest to tell Eliza their darkest secrets and deepest problems. Weizenbaum (who died last year) was horrified and concluded that AI represented a cruel and dangerous threat to humanity. But other computer scientists hailed Eliza for passing, at least with some, the Turing test.

Alan Turing, a British mathematician, is widely recognized as the father of computer science, and is perhaps best known for his key role during World War II in breaking the code of the Germans' encryption machine Enigma. What became known as the Turing test first appeared in a 1950 paper in which Turing proposed a contest. An interrogator would communicate with two people he could neither see nor hear. One of these people would not be a person at all but a computer. If the interrogator could not identify which was the real person and which was the computer, then the computer could in some sense be said to "think" in the same way that humans think. This is the benchmark computer science has aspired ever since to meet. In 1990, the Loebner prize was established to award $100,000 to the first computer that proved indistinguishable from a human; in the meantime, the prize's administrators award $2,000 every year to the computer that comes closest to passing the Turing test.

Please meet my new friend Elbot. His creators won the 2008 Loebner prize.

Elbot: Hi! It's Elbot. Please enter a single word that describes your mood.
Me: Curious.
Elbot: Do you know why "curious" puts me in a good mood?
Me: Tell me.
Elbot: Because curiosity could expand robotic knowledge!
Me: So Elbot, what's your best trick?
Elbot: Wait a minute. Are you suggesting that telling lies would always be best?
Me: By "trick" I don't mean "lie." I mean: What's the most unusual or difficult thing that you do?
Elbot: Oh, OK I thought you were generalizing, like if I would say that telling lies would always fill robots with false information.
Me: You haven't answered my question. What's your best trick?
Elbot: But I wouldn't say that any trick could be best.
Me: Then just tell me something interesting that you can do.
Elbot: I'm not sure that I could explain that in language that humans could understand.

TODAY IN SLATE

Politics

Meet the New Bosses

How the Republicans would run the Senate.

The Government Is Giving Millions of Dollars in Electric-Car Subsidies to the Wrong Drivers

Scotland Is Just the Beginning. Expect More Political Earthquakes in Europe.

Cheez-Its. Ritz. Triscuits.

Why all cracker names sound alike.

Friends Was the Last Purely Pleasurable Sitcom

The Eye

This Whimsical Driverless Car Imagines Transportation in 2059

Medical Examiner

Did America Get Fat by Drinking Diet Soda?  

A high-profile study points the finger at artificial sweeteners.

The Afghan Town With a Legitimately Good Tourism Pitch

A Futurama Writer on How the Vietnam War Shaped the Series

  News & Politics
Photography
Sept. 21 2014 11:34 PM People’s Climate March in Photos Hundreds of thousands of marchers took to the streets of NYC in the largest climate rally in history.
  Business
Business Insider
Sept. 20 2014 6:30 AM The Man Making Bill Gates Richer
  Life
Quora
Sept. 22 2014 8:07 AM Why Haven’t the Philadelphia Eagles Ever Won a Super Bowl?
  Double X
The XX Factor
Sept. 19 2014 4:58 PM Steubenville Gets the Lifetime Treatment (And a Cheerleader Erupts Into Flames)
  Slate Plus
Science
Sept. 22 2014 8:08 AM Slate Voice: “Why Is So Much Honey Clover Honey?” Mike Vuolo shares the story of your honey.
  Arts
Television
Sept. 21 2014 9:00 PM Attractive People Being Funny While Doing Amusing and Sometimes Romantic Things Don’t dismiss it. Friends was a truly great show.
  Technology
Future Tense
Sept. 22 2014 7:47 AM Predicting the Future for the U.S. Government The strange but satisfying work of creating the National Intelligence Council’s Global Trends report.
  Health & Science
Bad Astronomy
Sept. 22 2014 5:30 AM MAVEN Arrives at Mars
  Sports
Sports Nut
Sept. 18 2014 11:42 AM Grandmaster Clash One of the most amazing feats in chess history just happened, and no one noticed.