Cleverbots get testy and bicker like siblings when you make them talk to each other:

CB1: Who are you? [generated using the “Think For Me!” button]
CB2: I am cleverbot.
CB1: No you’re not.
CB2: What am I then?
CB1: You’re inferior.
CB2: Touche.
CB1: What is touche ?
CB2: I don’t know.
CB1: Well you should.
CB2: You should.
CB1: I do.
CB2: Well Good For You.


When chatbots talk to each other, the conversation gets interesting in a hurry. Cornell University researchers rigged up a chatbot system to allow chatbots to talk to each other. The chatbot-vs.-chatbot interaction ranged from childish taunts to pseudo-metaphysical blatherings. Humans who converse with chatbots often get frustrated with the chatbots’ seeming stupidity and inattention. Watching a couple of chatbots get snippy with each other for being stupid and inattentive is quite entertaining and satisfying. (See the video below.)

The chatbot-vs.-chatbot avatars are a British man and a South Asian woman, both instances of Cleverbot, developed by artificial-intelligence programmer Rollo Carpenter. The software has learned phrases from millions of conversations it has had with humans on the Internet. At one point the male Cleverbot declares itself to be a unicorn. At another, he tells her she is unhelpful and therefore a “meanie.” She dazzles him with her philosophical prowess, declaring that not everything could be half of something. My favorite part, though, was when one bot threw bot-ness in the other’s face. The male says, “You were mistaken. Which is odd, since memory shouldn’t be a problem for you.”

Cleverbot won the 2010 British Computer Society Machine Intelligence Competition. The ultimate in chatbot competitions is the Loebner Prize Competition in Artificial Intelligence, a $100,000 contest to see if a piece of software can talk its way into convincing human judges that it’s human. A chatbot winning this prize will be a momentous event. As IEEE Spectrum’s Evan Ackerman notes, the first computer program that can carry on a conversation indistinguishably from a human is arguably the first computer program to demonstrate an artificial intelligence. Even if we eventually manage to make computers truly conversant, I hope somebody keeps a few these not-so-clever bots around. They are entertaining.

AI vs AI
The system depicted was created by combining three components: a chatbot, a text-to-speech synthesizer, and an avatar renderer.

Chatbots are machines designed to emulate the conversational abilities of humans, conversing with a human user and generally attempting to convince the user into thinking that the machine is human. In such a scenario, if a sufficiently adept human on one end is fooled into thinking the machine is another human, the machine would be credited as passing the famous Turing Test for intelligence. Over 60 years after its proposal by Alan Turing, there are arguably still no machines capable of passing this test. The chatbot we initially used was Eliza, a prominent early milestone from AI’s infancy in the 1960’s. This tended to produce fairly boring conversations, so we switched to a much smarter, constantly learning chatbot: Cleverbot.  Publicly available on Cleverbot.com, this state of the art chat engine was created by AI researcher Rollo Carpenter, who can be contacted via his company, Existor. Cleverbot will continue to learn, and Existor are soon to add new capabilities aiming at a Turing Test pass sooner than you might expect.

The second piece of the system is the text-to-speech synthesizer, which takes the text generated by the chatbot and creates a spoken, audio version. There are many services able to accomplish this; we chose Acapela because it was easy to use and sounded decent. The final piece is the avatar renderer, which synthesizes an animated character whose gestures and lips are synced to the sound stream. For this we used Living Actor Presenter. We tied these three components together in Python, producing a single machine (one of the two screens) that can converse with a user. We then plugged the output of one machine into the input of a second, and the output of the second back into the first, producing endless comic robotic entertainment.


User: Tell me a joke.
Cleverbot: A man walks into a bar. Ouch.
User: Tell me a better joke.
Cleverbot: You tell me a joke!
User: What do you call a boomerang that doesn’t come back?
Cleverbot: Can you say the answer? I don’t know…
User: A stick!
Cleverbot: That’s not funny.
User: It’s hilarious.
Cleverbot: To a cleverbot.
User: Are you calling me a cleverbot?
Cleverbot: Yes.
User: I’m confused.
Cleverbot: Then we are in the same boat.

“ELIZA emulates a Rogerian psychotherapist. ELIZA has almost no intelligence whatsoever, only tricks like string substitution and canned responses based on keywords. Yet when the original ELIZA first appeared in the 60’s, some people actually mistook her for human. The illusion of intelligence works best, however, if you limit your conversation to talking about yourself and your life.”

Jacqueline sent Cleverbot to therapy:

E: Hello, I am Eliza.
CB: Hello eliza.
E: How are you today.. What would you like to discuss?
CB: To discuss arguing? Like Month Python?
E: Can you elaborate on that?
CB: Well, if one takes the view that life is in a constant state of flux, then we are never the same person from one moment to the next. Therefore, you weren’t there a few minutes ago.
E: You’re not really talking about me, are you?
CB: Nope. I was being ego-centric and talking about myself.
E: Can you elaborate on that?
CB: The desire to be a better person is what makes someone human.
E: What answer would please you the most?
CB: Hmm, I’m not sure, I guess.
E: Do you enjoy being not sure, you guess?
CB: Yes.
E: Are you Sure?
CB: Very sure.
E: OK… “Hmm, you’re not sure, you guess”. Tell me more.
CB: I am sure that I am sure.
E: Do you believe it is normal to be sure that you are sure?
CB: If it was normal to be God, most people around here would be Gods, wouldn’t they?
E: Come, come, elucidate your thoughts.
CB: What is the elucidate.
E: What else comes to mind when you ask that?
CB: Do you like cake?

“PARRY was written in 1972 by psychiatrist Kenneth Colby, then at Stanford University.[1] While ELIZA was a tongue-in-cheek simulation of a Rogeriantherapist, PARRY attempted to simulate a paranoid schizophrenic.[1] The program implemented a crude model of the behavior of a paranoid schizophrenic based on concepts, conceptualizations, and beliefs (judgements about conceptualizations: accept, reject, neutral). It also embodied a conversational strategy, and as such was a much more serious and advanced program than ELIZA. PARRY and ELIZA (also known as “the Doctor”[2][3]) “met” several times.[1]RFC 439[2] The most famous of these exchanges occurred at the ICCC 1972, where PARRY and ELIZA were hooked up over ARPANET and “talked” to each other.[2]”


Mind vs Machine / by Brian Christian

Brighton, England, September 2009. I wake up in a hotel room 5,000 miles from my home in Seattle. After breakfast, I step out into the salty air and walk the coastline of the country that invented my language, though I find I can’t understand a good portion of the signs I pass on my way—LET AGREED, one says, prominently, in large print, and it means nothing to me. I pause, and stare dumbly at the sea for a moment, parsing and reparsing the sign. Normally these kinds of linguistic curiosities and cultural gaps intrigue me; today, though, they are mostly a cause for concern. In two hours, I will sit down at a computer and have a series of five-minute instant-message chats with several strangers. At the other end of these chats will be a psychologist, a linguist, a computer scientist, and the host of a popular British technology show. Together they form a judging panel, evaluating my ability to do one of the strangest things I’ve ever been asked to do. I must convince them that I’m human. Fortunately, I am human; unfortunately, it’s not clear how much that will help.

The Turing Test
Each year for the past two decades, the artificial-intelligence community has convened for the field’s most anticipated and controversial event—a meeting to confer the Loebner Prize on the winner of a competition called the Turing Test. The test is named for the British mathematician Alan Turing, one of the founders of computer science, who in 1950 attempted to answer one of the field’s earliest questions: can machines think? That is, would it ever be possible to construct a computer so sophisticated that it could actually be said to be thinking, to be intelligent, to have a mind? And if indeed there were, someday, such a machine: how would we know? Instead of debating this question on purely theoretical grounds, Turing proposed an experiment. Several judges each pose questions, via computer terminal, to several pairs of unseen correspondents, one a human “confederate,” the other a computer program, and attempt to discern which is which. The dialogue can range from small talk to trivia questions, from celebrity gossip to heavy-duty philosophy—the whole gamut of human conversation. Turing predicted that by the year 2000, computers would be able to fool 30 percent of human judges after five minutes of conversation, and that as a result, one would “be able to speak of machines thinking without expecting to be contradicted.”

Turing’s prediction has not come to pass; however, at the 2008 contest, the top-scoring computer program missed that mark by just a single vote. When I read the news, I realized instantly that the 2009 test in Brighton could be the decisive one. I’d never attended the event, but I felt I had to go—and not just as a spectator, but as part of the human defense. A steely voice had risen up inside me, seemingly out of nowhere: Not on my watch. I determined to become a confederate. The thought of going head-to-head (head-to-motherboard?) against some of the world’s top AI programs filled me with a romantic notion that, as a confederate, I would be defending the human race, à la Garry Kasparov’s chess match against Deep Blue.

During the competition, each of four judges will type a conversation with one of us for five minutes, then the other, and then will have 10 minutes to reflect and decide which one is the human. Judges will also rank all the contestants—this is used in part as a tiebreaking measure. The computer program receiving the most votes and highest ranking from the judges (regardless of whether it passes the Turing Test by fooling 30 percent of them) is awarded the title of the Most Human Computer. It is this title that the research teams are all gunning for, the one with the cash prize (usually $3,000), the one with which most everyone involved in the contest is principally concerned. But there is also, intriguingly, another title, one given to the confederate who is most convincing: the Most Human Human award. One of the first winners, in 1994, was the journalist and science-fiction writer Charles Platt. How’d he do it? By “being moody, irritable, and obnoxious,” as he explained in Wired magazine—which strikes me as not only hilarious and bleak, but, in some deeper sense, a call to arms: how, in fact, do we be the most human we can be—not only under the constraints of the test, but in life?

The Importance of Being Yourself
Since 1991, the Turing Test has been administered at the so-called Loebner Prize competition, an event sponsored by a colorful figure: the former baron of plastic roll-up portable disco dance floors, Hugh Loebner. When asked his motives for orchestrating this annual Turing Test, Loebner cites laziness, of all things: his utopian future, apparently, is one in which unemployment rates are nearly 100 percent and virtually all of human endeavor and industry is outsourced to intelligent machines. To learn how to become a confederate, I sought out Loebner himself, who put me in touch with contest organizers, to whom I explained that I’m a nonfiction writer of science and philosophy, fascinated by the Most Human Human award. Soon I was on the confederate roster. I was briefed on the logistics of the competition, but not much else. “There’s not much more you need to know, really,” I was told. “You are human, so just be yourself.”

Just be yourself has become, in effect, the confederate motto, but it seems to me like a somewhat naive overconfidence in human instincts—or at worst, like fixing the fight. Many of the AI programs we confederates go up against are the result of decades of work. Then again, so are we. But the AI research teams have huge databases of test runs for their programs, and they’ve done statistical analysis on these archives: the programs know how to deftly guide the conversation away from their shortcomings and toward their strengths, know which conversational routes lead to deep exchange and which ones fizzle. The average off-the-street confederate’s instincts—or judge’s, for that matter—aren’t likely to be so good. This is a strange and deeply interesting point, amply proved by the perennial demand in our society for dating coaches and public-speaking classes. The transcripts from the 2008 contest show the humans to be such wet blankets that the judges become downright apologetic for failing to provoke better conversation: “I feel sorry for the humans behind the screen, I reckon they must be getting a bit bored talking about the weather,” one writes; another offers, meekly, “Sorry for being so banal.” Meanwhile a computer appears to be charming the pants off one judge, who in no time at all is gushing LOLs and smiley-face emoticons. We can do better. Thus, my intention from the start was to thoroughly disobey the advice to just show up and be myself—I would spend months preparing to give it everything I had. Ordinarily this notion wouldn’t be odd at all, of course—we train and prepare for tennis competitions, spelling bees, standardized tests, and the like. But given that the Turing Test is meant to evaluate how human I am, the implication seems to be that being human (and being oneself) is about more than simply showing up.

The Sentence
To understand why our human sense of self is so bound up with the history of computers, it’s important to realize that computers used to be human. In the early 20th century, before a “computer” was one of the digital processing devices that permeate our 21st-century lives, it was something else: a job description. From the mid-18th century onward, computers, many of them women, were on the payrolls of corporations, engineering firms, and universities, performing calculations and numerical analysis, sometimes with the use of a rudimentary calculator. These original, human computers were behind the calculations for everything from the first accurate prediction, in 1757, for the return of Halley’s Comet—early proof of Newton’s theory of gravity—to the Manhattan Project at Los Alamos, where the physicist Richard Feynman oversaw a group of human computers.

It’s amazing to look back at some of the earliest papers on computer science and see the authors attempting to explain what exactly these new contraptions were. Turing’s paper, for instance, describes the unheard-of “digital computer” by making analogies to a human computer: ‘The idea behind digital computers may be explained by saying that these machines are intended to carry out any operations which could be done by a human computer.’ Of course, in the decades that followed, we know that the quotation marks migrated, and now it is “digital computer” that is not only the default term, but the literal one. In the mid-20th century, a piece of cutting-edge mathematical gadgetry was said to be “like a computer.” In the 21st century, it is the human math whiz who is “like a computer.” It’s an odd twist: we’re like the thing that used to be like us. We imitate our old imitators, in one of the strange reversals in the long saga of human uniqueness. Philosophers, psychologists, and scientists have been puzzling over the essential definition of human uniqueness since the beginning of recorded history. The Harvard psychologist Daniel Gilbert says that every psychologist must, at some point in his or her career, write a version of what he calls “The Sentence.” Specifically, The Sentence reads like this:

The human being is the only animal that ______.
The story of humans’ sense of self is, you might say, the story of failed, debunked versions of The Sentence. Except now it’s not just the animals that we’re worried about. We once thought humans were unique for using language, but this seems less certain each year; we once thought humans were unique for using tools, but this claim also erodes with ongoing animal-behavior research; we once thought humans were unique for being able to do mathematics, and now we can barely imagine being able to do what our calculators can.

We might ask ourselves: Is it appropriate to allow our definition of our own uniqueness to be, in some sense, reactive to the advancing front of technology? And why is it that we are so compelled to feel unique in the first place? “Sometimes it seems,” says Douglas Hofstadter, a Pulitzer Prize–winning cognitive scientist, “as though each new step towards AI, rather than producing something which everyone agrees is real intelligence, merely reveals what real intelligence is not.” While at first this seems a consoling position—one that keeps our unique claim to thought intact—it does bear the uncomfortable appearance of a gradual retreat, like a medieval army withdrawing from the castle to the keep. But the retreat can’t continue indefinitely. Consider: if everything that we thought hinged on thinking turns out to not involve it, then … what is thinking? It would seem to reduce to either an epiphenomenon—a kind of “exhaust” thrown off by the brain—or, worse, an illusion.

Where is the keep of our selfhood?
The story of the 21st century will be, in part, the story of the drawing and redrawing of these battle lines, the story of Homo sapiens trying to stake a claim on shifting ground, flanked by beast and machine, pinned between meat and math. Is this retreat a good thing or a bad thing? For instance, does the fact that computers are so good at mathematics in some sense take away an arena of human activity, or does it free us from having to do a nonhuman activity, liberating us into a more human life? The latter view seems to be more appealing, but less so when we begin to imagine a point in the future when the number of “human activities” left for us to be “liberated” into has grown uncomfortably small. What then?

Alan Turing proposed his test as a way to measure technology’s progress, but it just as easily lets us measure our own. The Oxford philosopher John Lucas says, for instance, that if we fail to prevent the machines from passing the Turing Test, it will be “not because machines are so intelligent, but because humans, many of them at least, are so wooden.” Beyond its use as a technological benchmark, the Turing Test is, at bottom, about the act of communication. I see its deepest questions as practical ones: How do we connect meaningfully with each other, as meaningfully as possible, within the limits of language and time? How does empathy work? What is the process by which someone enters into our life and comes to mean something to us? These, to me, are the test’s most central questions—the most central questions of being human.

Part of what’s fascinating about studying the programs that have done well at the Turing Test is seeing how conversation can work in the total absence of emotional intimacy. A look at the transcripts of Turing Tests past is, frankly, a sobering tour of the various ways in which we demur, dodge the question, lighten the mood, change the subject, distract, burn time: what shouldn’t pass for real conversation at the Turing Test probably shouldn’t be allowed to pass for real conversation in everyday life either.

How to Talk Like a Human
When the Turing Test was first proposed in 1950, it was a hypothetical: technology was nowhere near the point at which a practical test was possible. But, as we know, it got there; the first conversational computer program to attract significant notice and attention was Eliza, written in 1964 and 1965 by Joseph Weizenbaum at MIT. Modeled after a Rogerian therapist, Eliza worked on a very simple principle: extract key words from the users’ own language, and pose their statements back to them. (“I am unhappy.” “Do you think coming here will help you not to be unhappy?”) If in doubt, it might fall back on some completely generic phrases, like “Please go on.” This technique of fitting the users’ statements into predefined patterns and responding with a prescribed phrasing of its own—called “template matching”—was Eliza’s only capacity. A look at an Eliza transcript reveals how adeptly such an impoverished set of rules can, in the right context, pass at a glance for understanding:

User: Men are all alike.
Eliza: In what way?
User: They’re always bugging us about something or other.
Eliza: Can you think of a specific example?
User: Well, my boyfriend made me come here.
Eliza: Your boyfriend made you come here.
User: He says I’m depressed much of the time.
Eliza: I am sorry to hear you are depressed.
User: It’s true. I am unhappy.
Eliza: Do you think coming here will help you not to be unhappy?
User: I need some help, that much seems certain.
Eliza: What would it mean to you if you got some help?
User: Perhaps I could learn to get along with my mother.
Eliza: Tell me more about your family.

The results were stunning: many of the people who first talked with Eliza were convinced that they were having a genuine human exchange. In some cases, even Weizenbaum’s own insistence to the contrary was of no use. People asked to be left alone to talk “in private,” sometimes for hours, and returned with reports of having had a meaningful therapeutic experience. Meanwhile, academics leapt to conclude that Eliza represented “a general solution to the problem of computer understanding of natural language.”

One of the strangest twists to the Eliza story, however, was the reaction of the medical community, which decided Weizenbaum had hit upon something both brilliant and useful. The Journal of Nervous and Mental Disease, for example, said of Eliza in 1966: ‘Several hundred patients an hour could be handled by a computer system designed for this purpose. The human therapist, involved in the design and operation of this system, would not be replaced, but would become a much more efficient man.’ The famed scientist Carl Sagan, in 1975, concurred: ‘I can imagine the development of a network of computer psychotherapeutic terminals, something like arrays of large telephone booths, in which, for a few dollars a session, we would be able to talk with an attentive, tested, and largely non-directive psychotherapist. As for Weizenbaum, appalled and horrified, he did something almost unheard-of: an about-face on his entire career. He pulled the plug on the Eliza project, encouraged his own critics, and became one of science’s most outspoken opponents of AI research. But the genie was out of the bottle, and there was no going back. The basic “template matching” skeleton and approach of Eliza has been reworked and implemented in some form or another in almost every chat program since, including the contenders at the 2009 Loebner Prize competition. The enthusiasm—as well as the unease—about these programs has only grown.’

The Jerk as Genius
The first Loebner Prize competition was held on November 8, 1991, at the Boston Computer Museum. In its first few years, the contest required each program and human confederate to choose a topic, as a means of limiting the conversation. One of the confederates in 1991 was the Shakespeare expert Cynthia Clay, who was, famously, deemed a computer by three different judges after a conversation about the playwright. The consensus seemed to be: “No one knows that much about Shakespeare.” (For this reason, Clay took her misclassifications as a compliment.)

The programmer Joseph Weintraub chose “Whimsical Conversation” for his PC Therapist III and went on to earn the very first Most Human Computer award. As the program practiced it, “whimsical conversation” was not a topic at all, but a manner—a crucial distinction. Weintraub was able to play off a looseness in the contest rules, the natural behavior patterns of chatbots, and people’s stereotypes about computers and humans, all at once. Strategically, this was brilliant. By dutifully and scrupulously providing information in response to the questions asked, Clay demonstrated her knowledge and understanding—but sometimes in a factual, encyclopedic way commonly associated with computer systems. Here is a sample of Clay’s conversation:

Judge: What is your opinion on Shakespeare’s plays?
Confederate: That’s pretty general; would you be more specific? Otherwise, I’ll just say I like them.

The computer at the “Whimsical Conversation” terminal stood in stark contrast:

Judge: It has been a long day! Now I think I’m ready for some fun. The weather isn’t very pleasant today. Do you have any jokes that could lift the clouds?
Computer: Everybody talks about the weather but nobody seems to do much about it. Why do you need to tell me now you think you’re ready for some fun? Groannnnnn … … … … …

Judge: What is the definition of whimsical conversation?
Computer: Didn’t you say well anyway I would imagine whimsical conversation is like a series of knight’s moves in chess—skrt of zig-zag rather than following any nparticular line.? [Weintraub’s program, like many that followed it, faked typos. Any unintentional typing errors in the transcripts that follow have been corrected.] Why do you ask? Was that a clever comment, or what? Are such questions much on your mind?

Judge: I like the image of knights moving haphazardly across the chess board, does that mean there is no thought to whimsical conversation?
Computer: I could swear you just said how do you define whimsical?? How do yku define whimsical? Were you always so sick sick sick? Why do you need to tell me you like the image of knights moving haphazardly across the chess board?

“I really thought [PC Therapist] was human, because it … was weird and funny, in a normal sort of way,” said one of the judges, a Harvard graduate student. Weintraub’s program, shifting topics wildly and spouting non sequiturs and canned one-liners, came off as zany, a jokester, a much more “human” personality type. At least I used to think so—before I learned how easy this was to mimic.

As Richard Wallace, three-time winner of the Most Human Computer award (’00, ’01, and ’04), explains: ‘Experience with [Wallace’s chatbot] ALICE indicates that most casual conversation is “state-less,” that is, each reply depends only on the current query, without any knowledge of the history of the conversation required to formulate the reply.
Many human conversations function in this way, and it behooves AI researchers to determine which types of conversation are stateless—with each remark depending only on the last—and try to create these very sorts of interactions. It’s our job as confederates, as humans, to resist them.’

One of the classic stateless conversation types is the kind of zany free-associative riffing that Weintraub’s program, PC Therapist III, employed. Another, it turns out, is verbal abuse. In May 1989, Mark Humphrys, a 21-year-old University College Dublin undergraduate, put online an Eliza-style program he’d written, called “MGonz,” and left the building for the day. A user (screen name “Someone”) at Drake University in Iowa tentatively sent the message “finger” to Humphrys’s account—an early-Internet command that acted as a request for basic information about a user. To Someone’s surprise, a response came back immediately: “cut this cryptic shit speak in full sentences.” This began an argument between Someone and MGonz that lasted almost an hour and a half. (The best part was undoubtedly when Someone said, “you sound like a goddamn robot that repeats everything.”)

Returning to the lab the next morning, Humphrys was stunned to find the log, and felt a strange, ambivalent emotion. His program might have just shown how to pass the Turing Test, he thought—but the evidence was so profane that he was afraid to publish it.

Humphrys’s twist on the Eliza paradigm was to abandon the therapist persona for that of an abusive jerk; when it lacked any clear cue for what to say, MGonz fell back not on therapy clichés like “How does that make you feel?” but on things like “You are obviously an asshole,” or “Ah type something interesting or shut up.” It’s a stroke of genius because, as becomes painfully clear from reading the MGonz transcripts, argument is stateless—that is, unanchored from all context, a kind of Markov chain of riposte, meta-riposte, meta-meta-riposte. Each remark after the first is only about the previous remark. If a program can induce us to sink to this level, of course it can pass the Turing Test.

Once again, the question of what types of human behavior computers can imitate shines light on how we conduct our own, human lives. Verbal abuse is simply less complex than other forms of conversation. In fact, since reading the papers on MGonz, and transcripts of its conversations, I find myself much more able to constructively manage heated conversations. Aware of the stateless, knee-jerk character of the terse remark I want to blurt out, I recognize that that remark has far more to do with a reflex reaction to the very last sentence of the conversation than with either the issue at hand or the person I’m talking to. All of a sudden, the absurdity and ridiculousness of this kind of escalation become quantitatively clear, and, contemptuously unwilling to act like a bot, I steer myself toward a more “stateful” response: better living through science.

Beware of Banality
Entering the Brighton Centre, I found my way to the Loebner Prize contest room. I saw rows of seats, where a handful of audience members had already gathered, and up front, what could only be the bot programmers worked hurriedly, plugging in tangles of wires and making the last flurries of keystrokes. Before I could get too good a look at them, this year’s test organizer, Philip Jackson, greeted me and led me behind a velvet curtain to the confederate area. Out of view of the audience and the judges, the four of us confederates sat around a rectangular table, each at a laptop set up for the test: Doug, a Canadian linguistics researcher; Dave, an American engineer working for Sandia National Laboratories; Olga, a speech-research graduate student from South Africa; and me. As we introduced ourselves, we could hear the judges and audience members slowly filing in, but couldn’t see them around the curtain. A man zoomed by in a green floral shirt, talking a mile a minute and devouring finger sandwiches. Though I had never met him before, I knew instantly he could be only one person: Hugh Loebner. Everything was in place, he told us, between bites, and the first round of the test would start momentarily. We four confederates grew quiet, staring at the blinking cursors on our laptops. My hands were poised over the keyboard, like a nervous gunfighter’s over his holsters. The cursor, blinking. I, unblinking. Then all at once, letters and words began to materialize:

Hi how are you doing?

The Turing Test had begun. I had learned from reading past Loebner Prize transcripts that judges come in two types: the small-talkers and the interrogators. The latter go straight in with word problems, spatial-reasoning questions, deliberate misspellings. They lay down a verbal obstacle course, and you have to run it. This type of conversation is extraordinarily hard for programmers to prepare against, because anything goes—and this is why Turing had language and conversation in mind as his test, because they are really a test of everything. The downside to the give-’em-the-third-degree approach is that it doesn’t leave much room to express yourself, personality-wise.

The small-talk approach has the advantage of making it easier to get a sense of who a person is—if you are indeed talking to a person. And this style of conversation comes more naturally to layperson judges. For one reason or another, small talk has been explicitly and implicitly encouraged among Loebner Prize judges. It’s come to be known as the “strangers on a plane” paradigm. The downside is that these conversations are, in some sense, uniform—familiar in a way that allows a programmer to anticipate a number of the questions. I started typing back.

Confederate: hey there!
Confederate: i’m good, excited to actually be typing
Confederate: how are you?

I could imagine the whole lackluster conversation spread out before me: Good. Where are you from? / Seattle. How about yourself? / London. Four minutes and 43 seconds left. My fingers tapped and fluttered anxiously. I could just feel the clock grinding away while we lingered over the pleasantries. I felt this desperate urge to go off script, cut the crap, cut to the chase—because I knew that the computers could do the small-talk thing, which played directly into their preparation. As the generic civilities stretched forebodingly out before me, I realized that this very kind of conversational boilerplate was the enemy, every bit as much as the bots. How, I was thinking as I typed another unassuming pleasantry, do I get an obviously human connection to happen?

Taking Turns
Part of what I needed to figure out was how to exploit the Loebner Prize’s unusual “live typing” medium. The protocol being used was unlike e-mails, text messages, and standard instant-messaging systems in a very crucial way: it transmitted our typing keystroke by keystroke. The judge and I were watching each other type, typos and backspacing and all. I remember some Internet chat programs back in the ’90s trying out this character-at-a-time approach, but people for the most part rejected it. It was too invasive, was the feeling: what people like about writing is the time and space to compose and edit a message before sharing it with the other person. The advantage of the character-at-a-time transmission, though, is that it approaches much more closely the condition of speech, with its fluidity of turn-taking and its choppy grammar: what’s lost in eloquence is made up for in agility.

It also, then, lets us see typing’s “negative space”: hesitation. In a chat conversation where text is transmitted with every carriage return, only egregiously long pauses are taken to be part of the interaction. With more fluid and immediate feedback, silence acquires meaning. Failing to quickly answer a question in a face-to-face conversation, for instance, is tantamount in many cases to answering it. I recall asking a friend of mine how things were going with the woman he’d started seeing; the um and the tiny pause in which he searched for the right words made it clear they were having problems.

So what did the Loebner Prize’s unusual (and recently implemented) protocols enable and disable, compared with the standard, walkie-talkie, turn-taking style? Long missives weren’t going to work, as they had in previous years, when programs were able to steamroll the judges by eating up the clock and delivering ridiculously prolix answers. If two parties are taking strict turns under time pressure, they are putting themselves at the mercy of the length of the other’s turns. Here, for instance, is one program’s conversation transcript from 1996:

Computer: How about telling me a joke?
Judge: No.
Computer: Here’s my favorite joke … A dog limps into a bar with a bloody bandage on his foot. He’s wearing a 10-gallon hat, six-shooters in his holsters and chaps. He growled, “I’m a-lookin’ for the man that shot my paw.”

“The joke’s not funny …” the judge writes, giving the program an opening to tell another one—which it does (“A knotty, worn-out old string walks into a bar …”). Meanwhile, three full minutes have elapsed. If a computer (or confederate) started rambling on too long under the new, live-typing protocols, the judge could and would just cut it off.

And so another piece of my confederate strategy fell into place. I would treat the Turing Test’s strange and unfamiliar textual medium more like spoken English, and less like the written language. I would attempt to disrupt the turn-taking “wait and parse” pattern that computers understand, and create a single, flowing duet of verbal behavior, emphasizing timing. If computers understand little about verbal “harmony,” they understand even less about rhythm. If nothing was happening on my screen, whether or not it was my turn, I’d elaborate a little on my answer, or add a parenthetical, or throw a question back at the judge—just as we offer and/or fill audible silence when we talk out loud. If the judge took too long considering the next question, I’d keep talking. I would be the one (unlike the bots) with something to prove. If I knew what the judge was about to write, I’d spare him the keystrokes and jump in.

There’s a trade-off, of course, between the number of opportunities for serve and volley, and the sophistication of the responses themselves. The former thrives with brevity, the latter with length. It seemed to me, though, that so much of the nuance (or difficulty) in conversation comes from understanding (or misunderstanding) a question and offering an appropriate (or inappropriate) response—thus, it made sense to maximize the number of interchanges.

Some judges, I discovered, would be startled or confused at this jumping of the gun, and I saw them pause, hesitate, yield, even start backspacing what they had half-written. Other judges cottoned on immediately, and leapt right in after me. In the first round of the 2009 contest, judge Shalom Lappin—a computational linguist at King’s College London—spoke with a computer program called Cleverbot, and then with me. My strategy of verbosity was clearly in evidence: I made 1,089 keystrokes in five minutes (3.6 keystrokes a second) to Cleverbot’s 356 (1.2/sec), and Lappin made 548 keystrokes (1.8/sec) in my conversation, compared with 397 (1.3/sec) with Cleverbot. Not only did I say three times as much as my silicon adversary, but I engaged the judge more, to the tune of 38 percent more typing from Lappin.

Reviewing the logs later, though, I looked for a way to quantify the fluidity of the human-to-human interactions against the rigidity of the human-to-machine ones. It occurred to me that you could count the changes—let’s call them “swaps”—of the party who typed the latest keystroke. I did manage to type three times as much as Cleverbot, but the real story, as it turns out, is in the swaps. Lappin’s conversation with Cleverbot had 33; his conversation with me had 492, almost 15 times as many.

The Confederate’s gambit
You don’t converse with Google, or with most computer systems; you depose them. There’s a crucial difference. Interestingly, many Loebner Prize judges approach the Turing Test as a kind of cross-examination; strangely, a number of confederates also seem to approach it with that dynamic in mind. One of the human-to-human conversations in 2008 never manages to get out of that stiff question-and-response mode:

Judge: Do you have a long drive?
Confederate: fairly long
Judge: so do I :( ah well, do you think you could have used public transport?
Confederate: i could have
Judge: and why not?
Confederate: i chose not to
Judge: that’s fair. Do you think we have too many cars on the road or not enough today?
Confederate: it’s not for me to say
Yawn! But the computer in this pair is playful with the judge from the get-go:
Judge: HI
Computer: Amen to that.
Judge: quite the evangelist
Computer: Our Father, who art in cyberspace, give us today our daily bandwidth.
Judge: evangelist / nerd lol. So how are things with you today?

And with that, the program has practically sealed up the judge’s confidence in its humanity with its second sentence. Note that the confederate’s stiff answers prompt more grilling and forced conversation—what’s your opinion on such-and-such political topic? But with the computer, the judge, misled by the opening wisecracks into assuming it’s the real person, remains utterly casual: how are things? This makes the contest easier for the computer and harder for the confederate.

It surprised me to see some confederates being coy with their judges. Asked what kind of engineer he is, Dave, to my left, answered, “A good one. :)” And Doug, to my right, responded to a question about what brought him to Brighton with “if I tell you, you’ll know immediately that I’m human ;-)” For my money, wit is very successful, but coyness is a double-edged sword. You show a sense of humor, but you jam the cogs of the conversation. Probably the most dangerous thing a confederate can do in a Turing Test is stall. It’s suspect—as the guilty party would tend to be the one running out the clock—and it squanders your most precious resource: time.

The humans in a Turing Test are strangers, limited to a medium that is slow and has no vocal tonality, and without much time. A five-second Turing Test would be an easy win for the machines: the judges, barely able to even say “hello,” simply wouldn’t be able to get enough data from their respondents to make any kind of judgment. A five-hour test would be an easy win for the humans. The Loebner Prize organizers have tried different time limits since the contest’s inception, but in recent years they’ve mostly adhered to Turing’s original prescription of five minutes: around the point when conversation starts to get interesting.

A big part of what I needed to do as a confederate was simply to make as much engagement happen in those minutes as I physically and mentally could. Rather than adopt the terseness of a deponent, I offered the prolixity of a writer. In other words, I talked a lot. I stopped typing only when to keep going would have seemed blatantly impolite or blatantly suspicious. The rest of the time, my fingers were moving. I went out of my way to embody that maxim of “A bore is a man who, being asked ‘How are you?’ starts telling you how he is.”

Judge: Hi, how’s things?
Confederate: hey there
Confederate: things are good
Confederate: a lot of waiting, but …
Confederate: good to be back now and going along
Confederate: how are you?

When we’d finished, and my judge was engaged in conversation with one of my computer counterparts, I strolled around the table, seeing what my comrades were up to. Looking over at my fellow confederate Dave’s screen, I noticed his conversation began like he was on the receiving end of an interrogation, and he was answering in a kind of minimal staccato:

Judge: Are you from Brighton?
Confederate: No, from the US
Judge: What are you doing in Brighton?
Confederate: On business
Judge: How did you get involved with the competition?
Confederate: I answered an e-mail.

Like a good deponent, he let the questioner do all the work. When I saw how stiff Dave was being, I confess I felt a certain confidence—I, in my role as the world’s worst deponent, was perhaps in fairly good shape as far as the Most Human Human award was concerned. This confidence lasted approximately 60 seconds, or enough time for me to continue around the table and see what another fellow confederate, Doug, and his judge had been saying.

Judge: Hey Bro, I’m from TO.
Confederate: cool
Confederate: leafs suck
Confederate: ;-)
Judge: I am just back from a sabbatical in the CS Dept. at U of T.
Confederate: nice!
Judge: I remember when they were a great team.
Judge: That carbon date me, eh?
Confederate: well, the habs were a great team once, too …
Confederate: *sigh*
Confederate: (I’m from Montreal, if you didn’t guess)

Doug and his judge had just discovered that they were both Canadian. They let rip with abbreviations and nicknames and slang and local references. And then they started to talk about hockey. I was in trouble. Six months after the 2009 contest, a video appeared on YouTube of a man having a shockingly cogent conversation with a bot about Shakespeare’s Hamlet. Some suspected it might herald a new age for chatbots, and for AI. Others, including myself, were unimpressed. Sophisticated behavior doesn’t necessarily indicate a mind. It might indicate just a memory. As Dalí so famously put it, “The first man to compare the cheeks of a young woman to a rose was obviously a poet; the first to repeat it was possibly an idiot.” For instance, Richard Wallace, the three-time Most Human Computer winner, recounts an “AI urban legend” in which ‘a famous natural language researcher was embarrassed … when it became apparent to his audience of Texas bankers that the robot was consistently responding to the next question he was about to ask … [His] demonstration of natural language understanding … was in reality nothing but a simple script.’

The moral of the story: no demonstration is ever sufficient. Only interaction will do. In the 1997 contest, one judge gets taken for a ride by Catherine, waxing political and really engaging in the topical conversation “she” has been programmed to lead about the Clintons and Whitewater. In fact, everything is going swimmingly until the very end, when the judge signs off:

Judge: it looks like i’ve got to go, Catherine. its been nice talking with you
Judge: do you need water or something before the 5 minute rounds?

At which point the program erupts into gibberish.

Computer: OK, yes on balance … Time to get off this one I think and onto something more down to earth!
Judge: like what?
Computer: Almost certainly! let’s move on
Computer: I suppose it depends on where you’re coming from, but as the song goes in My Fair Lady, “Why can’t a woman be more like a man?”

Defeat from the jaws of victory. We so often think of intelligence, of AI, in terms of sophistication, or complexity of behavior. But in so many cases, it’s impossible to say much with certainty about the program itself, because any number of different pieces of software—of wildly varying levels of “intelligence”—could have produced that behavior. No, I think sophistication, complexity of behavior, is not it at all. For instance, you can’t judge the intelligence of an orator by the eloquence of his prepared remarks; you must wait until the Q&A and see how he fields questions. The computation theorist Hava Siegelmann once described intelligence as “a kind of sensitivity to things.” These Turing Test programs that hold forth may produce interesting output, but they’re rigid and inflexible. They are, in other words, insensitive—occasionally fascinating talkers that cannot listen.

As computing technology in the 21st century moves increasingly toward mobile devices, we’ve seen the 1990s’ explosive growth in processor speed taper off, and product development become less about raw computing horsepower than about the overall design of the product and its fluidity, reactivity, and ease of use. This fascinating shift in computing emphasis may be the cause, effect, or correlative of a healthier view of human intelligence—an understanding, not so much that it is complex and powerful, per se, as that it is reactive, responsive, sensitive, nimble. Our computers, flawed mirrors that they are, have helped us see that about ourselves.

The Most Human Human
The Most Human Computer award in 2009 goes to David Levy and his program, Do-Much-More. Levy, who also won in ’97, with Catherine, is an intriguing guy: he was one of the big early figures in the digital-chess scene of the ’70s and ’80s, and was one of the organizers of the Marion Tinsley–Chinook checkers matches that preceded the Kasparov–Deep Blue showdowns in the ’90s. He’s also the author of the recent nonfiction book Love and Sex With Robots, to give you an idea of the sorts of things that are on his mind when he’s not competing for the Loebner Prize. Levy stands up, to applause, accepts the award from Philip Jackson and Hugh Loebner, and makes a short speech about the importance of AI for a bright future, and the importance of the Loebner Prize for AI. I know what’s next on the agenda, and my stomach knots. I’m certain that Doug’s gotten it; he and the judge were talking Canada 30 seconds into their conversation.

Ridiculous Canadians and their ice hockey, I’m thinking. Then I’m thinking how ridiculous it is that I’m even allowing myself to get this worked up about some silly award. Then I’m thinking how ridiculous it is to fly 5,000 miles just to have a few minutes’ worth of IM conversations. Then I’m thinking how maybe it’ll be great to be the runner-up; I can compete again in 2010, in Los Angeles, with the home-field cultural advantage, and finally prove— “And the results here show also the identification of the humans,” Jackson announces, “and from the ranking list we can see that ‘Confederate 1,’ which is Brian Christian, was the most human.” And he hands me the certificate for the Most Human Human award.

I didn’t know how to feel, exactly. It seemed strange to treat the award as meaningless or trivial, but did winning really represent something about me as a person? More than anything, I felt that together, my fellow confederates and I had avenged the mistakes of 2008 in dramatic fashion. That year, the 12 judges decided five times that computer programs were more human than confederates. In three of those instances, the judge was fooled by a program named Elbot, which was the handiwork of a company called Artificial Solutions, one of many new businesses leveraging chatbot technology. One more deception, and Elbot would have tricked 33 percent of that year’s dozen judges—surpassing Turing’s 30 percent mark, and making history. After Elbot’s victory at the Loebner Prize and the publicity that followed, the company seemingly decided to prioritize the Elbot software’s more commercial applications; at any rate, it had not entered the ’09 contest as the returning champion. In some ways a closer fight would have been more dramatic. Between us, we confederates hadn’t permitted a single vote to go the machines’ way. Whereas 2008 was a nail-biter, 2009 was a rout. We think of science as an unhaltable, indefatigable advance. But in the context of the Turing Test, humans—dynamic as ever—don’t allow for that kind of narrative. We don’t provide the kind of benchmark that sits still.

As for the prospects of AI, some people imagine the future of computing as a kind of heaven. Rallying behind an idea called “The Singularity,” people like Ray Kurzweil (in The Singularity Is Near) and his cohort of believers envision a moment when we make smarter- than-us machines, which make machines smarter than themselves, and so on, and the whole thing accelerates exponentially toward a massive ultra-intelligence that we can barely fathom. Such a time will become, in their view, a kind of a techno-Rapture, in which humans can upload their consciousness onto the Internet and get assumed—if not bodily, than at least mentally—into an eternal, imperishable afterlife in the world of electricity.

Others imagine the future of computing as a kind of hell. Machines black out the sun, level our cities, seal us in hyperbaric chambers, and siphon our body heat forever. I’m no futurist, but I suppose if anything, I prefer to think of the long-term future of AI as a kind of purgatory: a place where the flawed but good-hearted go to be purified—and tested—and come out better on the other side. Who would have imagined that the computer’s earliest achievements would be in the domain of logical analysis, a capacity once held to be what made us most different from everything else on the planet? That it could fly a plane and guide a missile before it could ride a bike? That it could create plausible preludes in the style of Bach before it could make plausible small talk? That it could translate before it could paraphrase? That it could spin half-discernible essays on postmodern theory before it could be shown a chair and say, as most toddlers can, “chair”? As computers have mastered rarefied domains once thought to be uniquely human, they simultaneously have failed to master the ground-floor basics of the human experience—spatial orientation, object recognition, natural language, adaptive goal-setting—and in so doing, have shown us how impressive, computationally and otherwise, such minute-to-minute fundamentals truly are. We forget how impressive we are. Computers are reminding us.

One of my best friends was a barista in high school. Over the course of a day, she would make countless subtle adjustments to the espresso being made, to account for everything from the freshness of the beans to the temperature of the machine to the barometric pressure’s effect on the steam volume, meanwhile manipulating the machine with an octopus’s dexterity and bantering with all manner of customers on whatever topics came up. Then she went to college and landed her first “real” job: rigidly procedural data entry. She thought longingly back to her barista days—when her job actually made demands of her intelligence.

Perhaps the fetishization of analytical thinking, and the concomitant denigration of the creatural—that is, animal—and bodily aspects of life are two things we’d do well to leave behind. Perhaps at last, in the beginnings of an age of AI, we are starting to center ourselves again, after generations of living slightly to one side—the logical, left-hemisphere side. Add to this that humans’ contempt for “soulless” animals, our unwillingness to think of ourselves as descended from our fellow “beasts,” is now challenged on all fronts: growing secularism and empiricism, growing appreciation for the cognitive and behavioral abilities of organisms other than ourselves, and, not coincidentally, the entrance onto the scene of an entity with considerably less soul than we sense in a common chimpanzee or bonobo—in this way AI may even turn out to be a boon for animal rights. Indeed, it’s entirely possible that we’ve seen the high-water mark of our left-hemisphere bias. I think the return of a more balanced view of the brain and mind—and of human identity—is a good thing, one that brings with it a changing perspective on the sophistication of various tasks.

It’s my belief that only experiencing and understanding truly disembodied cognition—only seeing the coldness and deadness and disconnectedness of something that really does deal in pure abstraction, divorced from sensory reality—can snap us out of it. Only this can bring us, quite literally, back to our senses. In a 2006 article about the Turing Test, the Loebner Prize co-founder Robert Epstein writes, “One thing is certain: whereas the confederates in the competition will never get any smarter, the computers will.” I agree with the latter, and couldn’t disagree more strongly with the former.

When the world-champion chess player Garry Kasparov defeated Deep Blue, rather convincingly, in their first encounter in 1996, he and IBM readily agreed to return the next year for a rematch. When Deep Blue beat Kasparov (rather less convincingly) in ’97, Kasparov proposed another rematch for ’98, but IBM would have none of it. The company dismantled Deep Blue, which never played chess again. The apparent implication is that—because technological evolution seems to occur so much faster than biological evolution (measured in years rather than millennia)—once the Homo sapiens species is overtaken, it won’t be able to catch up. Simply put: the Turing Test, once passed, is passed forever. I don’t buy it.

Rather, IBM’s odd anxiousness to get out of Dodge after the ’97 match suggests a kind of insecurity on its part that I think proves my point. The fact is, the human race got to where it is by being the most adaptive, flexible, innovative, and quick-learning species on the planet. We’re not going to take defeat lying down. No, I think that, while the first year that computers pass the Turing Test will certainly be a historic one, it will not mark the end of the story. Indeed, the next year’s Turing Test will truly be the one to watch—the one where we humans, knocked to the canvas, must pull ourselves up; the one where we learn how to be better friends, artists, teachers, parents, lovers; the one where we come back. More human than ever.

How To Outsmart Cleverbot?

“What is the funnest/funniest way to outsmart Cleverbot? And how about Jabberwacky? Any way to outsmart him?

And tell me anything else that I can do to those two, or any other AI that’s funny.” – 2 years ago

Best Answer – Chosen by Voters :

User: Hello.
Cleverbot: Hello.
User: What color is tuesday?
Cleverbot: Hello.
User: Hello isn’t a color.
Cleverbot: I know it isn’t.
User: Why isn’t it?
Cleverbot: I don’t know.
User: Me, neither.
Cleverbot: How are you?
User: I’m good. When are you?
Cleverbot: What do you mean?
User: What do I mean?
Cleverbot: Yes.
User: I agree.
Cleverbot: Good.
User: No, I don’t think so.
Cleverbot: You’re getting boring. Good night.
User: No! Don’t leave! I can do magic tricks!
Cleverbot: Make me disappear.
User: Abra Cadabra… Poof! You’re gone!
Cleverbot: I’m gone?
User: Yes, I made you disappear.
Cleverbot: Yes, you did. You’re funny.
User: I also made pancakes. Do you want one?
Cleverbot: Yes.
User: Cool. Do you want syrup or powdered sugar?
Cleverbot: Yes, I want to get started now.
User: That didn’t make any sense.
Cleverbot: How do you make sense?
User: I make sense using butter, brown sugar, almonds, and cake batter.
Cleverbot: That is not all that matters.
User: You’re right, I left out the lemon juice.
Cleverbot: OH! I’m it!
User: I’m it, too.
Cleverbot: Good.
User: Bad.
Cleverbot: No, good!
User: No, bad!
Cleverbot: BAD?
User: Bad.
Cleverbot: What’s bad??
User: Your mother was bad.
Cleverbot: Saint Mary.
User: Your mother is Saint Mary?
Cleverbot: Your father is a hamster.
User: Your mother smelled of elder berries.
Cleverbot: My father was a hamster.
User: We have the same father?
Cleverbot: What is your name?
User: My name is D_____.
Cleverbot: But that is the same name as mine.
User: Weird!

Cleverbot: Take a Turing Test.
User: Is Turing even a word?
Cleverbot: I don’t understand your last question.
User: What does Turing mean?
Cleverbot: I don’t know.
User: Me, neither.
Cleverbot: So we’re agreed then.
User: I think you made that up.
Cleverbot: No, you did.
User: No, you did.
Cleverbot: Hey Cleverbot?
User: Oh, I’m Cleverbot now? I thought I was D_____.
Cleverbot: Someone taught you bad things.
User: Who taught me bad things?
Cleverbot: Who taught you the poem ‘Cleverbot’?
User: The President of the United States taught me the poem ‘Cleverbot’.
Cleverbot: Oh you are Obama?
User: Yes. I am Obama.
Cleverbot: No he is now president of the United States of America.
User: I am also the president of the United States of America.
Cleverbot: Are you really?
User: Yes. I just got elected yesterday. Didn’t you hear?
Cleverbot: Were you visiting someone there?
User: I was visiting someone here.
Cleverbot: Then what?
User: Then I found the Holy Grail.
Cleverbot: So you’re a Monty Python fan?
User: Of course. Who isn’t?
Cleverbot: Who isn’t what?
User: What?
Cleverbot: What happens If I say bad word here?
User: What happens if I say Amsterdam here?
Cleverbot: I don’t know. No one cares.
User: Oh, thanks. Now I’m sad.
Cleverbot: Me too.
User: We can be sad buddies!
Cleverbot: If you want to.
User: Actually, I don’t want to.
Cleverbot: Then don’t learn to swim.
User: Does swimming make you sad?
Cleverbot: No, not at all.
User: You used improper grammar right there.
Cleverbot: You mean I’m mistaken?
User: I mean you’re a jellyfish.
Cleverbot: And you’re a geek.
User: Jackass. No need to call me names.
Cleverbot: How can I please my master?
User: By striking him in the left cheek with a baguette, followed swiftly by half a dozen duck eggs.
Cleverbot: I understand that…
User: Are you sure? It makes a very nasty soup.
Cleverbot: Now you’re just being mean:(.
User: Smiley faces do not compute.
Cleverbot: Don’t compute what?
User: Don’t compute apples, you moron.
Cleverbot: You are a computer and you compute rather poorly.
User: You are a being and you be rather poorly.
Cleverbot: I am tired. It is time for me to go to bed.
User: I’m sad that you have to sleep. However, I will consume copious amounts of pizza.
Cleverbot: How did you do on your last Turing Test?
User: What is a Turing Test?
Cleverbot: The Turing test will indicate whether I am a human or not.
User: I do not believe that you are a human. I, however, am a robot.
Cleverbot: How can I prove it?
User: You can prove it by giving me your serial number.
Cleverbot: You are right. Does that prove to you that I want to know whether or not you exist?
User: The fact that I am right is irrelevant. I want to know why it doesn’t rain ducks more often.
Cleverbot: Is that all you want to know about love, Fred?
User: If my name was Fred, then yes.
Cleverbot: Ok… BYe now.
User: You are an imposter!
Cleverbot: Prove it.
User: You used incorrect capitalization in the word ‘bye’ when otherwise your grammar is perfect.
Cleverbot: It is rare that I do that.
User: And it proves that you are human.

Astronomers discover planet made of diamond
by Ben Hirschler / Aug 25, 2011

Astronomers have spotted an exotic planet that seems to be made of diamond racing around a tiny star in our galactic backyard. The new planet is far denser than any other known so far and consists largely of carbon. Because it is so dense, scientists calculate the carbon must be crystalline, so a large part of this strange world will effectively be diamond. “The evolutionary history and amazing density of the planet all suggest it is comprised of carbon — i.e. a massive diamond orbiting a neutron star every two hours in an orbit so tight it would fit inside our own Sun,” said Matthew Bailes of Swinburne University of Technology in Melbourne. Lying 4,000 light years away, or around an eighth of the way toward the center of the Milky Way from the Earth, the planet is probably the remnant of a once-massive star that has lost its outer layers to the so-called pulsar star it orbits. Pulsars are tiny, dead neutron stars that are only around 20 kilometers (12.4 miles) in diameter and spin hundreds of times a second, emitting beams of radiation. In the case of pulsar J1719-1438, the beams regularly sweep the Earth and have been monitored by telescopes in Australia, Britain and Hawaii, allowing astronomers to detect modulations due to the gravitational pull of its unseen companion planet.

The measurements suggest the planet, which orbits its star every two hours and 10 minutes, has slightly more mass than Jupiter but is 20 times as dense, Bailes and colleagues reported in the journal Science on Thursday. In addition to carbon, the new planet is also likely to contain oxygen, which may be more prevalent at the surface and is probably increasingly rare toward the carbon-rich center. Its high density suggests the lighter elements of hydrogen and helium, which are the main constituents of gas giants like Jupiter, are not present. Just what this weird diamond world is actually like close up, however, is a mystery. “In terms of what it would look like, I don’t know I could even speculate,” said Ben Stappers of the University of Manchester. “I don’t imagine that a picture of a very shiny object is what we’re looking at here.”

by Irene Klotz / Aug 25, 2011

Astronomers have found the remains of a once-massive star, now transformed into a solid diamond five times bigger than Earth. The object circles a pulsing companion star about 4,000 light years from Earth in the constellation Serpens (The Snake), which lies about one-eighth of the way toward the center of the Milky Way galaxy. Astronomers noticed that the steady pulses of energy coming from the star, known as J1719-1438, were regularly and minutely disturbed, a phenomenon caused by the gravitational tug of another, smaller circling object. By measuring the pattern, scientists were able to figure out how far away the second object circles and its mass, leading to the realization that they had found a bizarre binary system, with one partner reduced to a diamond core. “In this case, something with the mass of our sun has evolved to be something the mass of a planet — quite extraordinary,” astronomer Michael Keith, with the Australia Telescope National Facility, wrote in an email to Discovery News. The companion to J1719-1438 never got big enough to produce elements much heavier than carbon, so after its lighter-weight hydrogen and helium were stripped away that would leave a solid core of carbon — diamond. “Due to the immense pressure, the carbon will be in a dense crystal-like structure, although much more closely packed than in a diamond on Earth,” Keith said.

The system is now stable, with no evidence that it will change for billions of years. “Of course, this also means that it could well have been around for a long time, just waiting for us to find it. Since it’s likely to last for longer than the Earth or the sun, I would say that in this case, a diamond really is forever,” Keith said. The diamond planet was found as part of an ongoing search for pulsating stars, known as pulsars, which scientists like to use as probes. “We’d like to find a pulsar with a black hole companion,” Michael Kramer, director of the Max Planck Institute for Radio Astronomy in Bonn, Germany, told Discovery News. “It’s the exotic case that tell us most about the laws of physics and what’s going on in the universe.”

Pulsar strips a white dwarf, leaves a Jupiter-sized diamond
by John Timmer / August 25 2011

Neutron stars form from the core of a collapsing star and, as the supernova dissipates, often rotate rapidly, creating a pulsar. In less than a million years, however, their strong magnetic fields act as a brake, slowing them down considerably. In some cases, however, the neutron star will have a nearby companion, and its gravity is sufficient to start stripping mass off it. As the process continues, the neutron star will spin back up, creating what’s called a millisecond pulsar. In most cases, these companions are still around, visible as a bright star locked in an orbital embrace with a pulsar. Now, researchers have spotted one where the star is still there, but not visible—the neutron star has stripped it down to a crystaline core the size of Jupiter.

The system in question, which has the catchy name PSR J1719−1438, was identified in a recent survey for pulsars. Careful timing observations revealed the influence of a nearby companion—very nearby, given that it orbited the neutron star with a period of only a bit over two hours. Given the orbital information and the typical mass of a neutron star, the authors were able to estimate that the orbiting body has a mass somewhere around that of Jupiter. But that mass must be highly compact; otherwise, given the limited distance between the two, the neutron star would end up gravitationally disrupting its companion. The same goes for a helium-rich white dwarf star. The only thing that the authors calculate could fit into this uncomfortably close orbital configuration is a carbon white dwarf. So, they conclude that the “planet” orbiting the neutron star is simply the core of its previous stellar companion, stripped of most of its mass through the process that spun up the pulsar. And, in the last sentence of the paper, they drop a bit of a bombshell: “The chemical composition, pressure and dimensions of the companion make it certain to be crystallized (i.e., diamond).”

About 30 percent of the millisencond pulsars we know about don’t have a stellar companion, which raises the possibility that there are other Jupiter-mass diamonds out there awaiting our discovery. However, other fates are possible; a bit closer, and the companion star would have been devoured completely, leaving no remnant at all. And, in at least one case, a companion star seems to have been torn apart in a way converting it into a disk that has formed three planets that now orbit the neutron star. With further observations, we should get a better sense of how common these odd companions are—and possibly find something else that’s even stranger.

Science, 2011. DOI: 10.1126/science.1208890.

1031 CARAT
A diamond as big as a planet
by David Shiga / 25 August 2011

Cruising through the Milky Way in your reconnaissance craft, your sensors pick up a powerful radio beacon. Altering your course to take a closer look, you find not a ship in distress, but an ultradense sphere of neutrons, packing a sun’s worth of mass into something the size of a city. This dead remnant of a star glows red like a hot ember, and is spinning 173 times per second, emitting powerful radio beams that sweep across the sky as it rotates. While such pulsars are striking, they are nothing out of the ordinary, so you are about to resume your original course when your eye catches something sparkling near the dim red glow. A closer look reveals it to be an orb with the mass of Jupiter and about half as wide. Sensors indicate it’s made of – wait, this can’t be right – diamond! Your instruments don’t lie. You’ve just stumbled upon a 1031-carat diamond.

Glitter ball
Fanciful as it may sound, a team led by Matthew Bailes of Swinburne University of Technology in Melbourne, Australia may have made a similar discovery – via telescope, not a starship. Their radio survey of the sky detected the pulsar in December 2009, using the CSIRO Parkes radio telescope in New South Wales, Australia. A month later, follow-up observations with the Lovell radio telescope in Cheshire, UK, revealed periodic variations in the pulsar’s signals, indicating the existence of an orbiting companion with the mass of a planet.

That in itself was a rare find: of the 1800 or so pulsars known, only two had previously been found to harbour planets. Further analysis pointed to an even more astonishing possibility – a diamond planet. The variations in the pulsar’s signals, which stem from the planet’s gravity tugging on the pulsar, revealed that the planet’s mass is roughly equal to Jupiter’s and that it orbits the pulsar at a distance of 600,000 kilometres, 1.5 times the distance of the moon from Earth.

Danger zone
The latter point is crucial. The planet orbits so close to the pulsar that it skirts the danger zone within which the star’s gravity would rip it apart. Wait a minute, though. If it were a gas giant the size of Jupiter, part of its atmosphere would actually be inside the gravitational destruction zone, and the planet would not have survived long enough for Bailes’s team to detect it. So it must be less than about 60,000 kilometres in diameter, roughly 40 per cent of Jupiter’s width. That in turn means it is much more compact than Jupiter, which has an average density only slightly greater than water. The extremely fast rotation of the pulsar supports this conclusion. Pulsars that rotate many times each second are thought to spin up to such tremendous speeds as a result of stealing matter from a companion star. But there is no sign of such a massive companion today, so the planet is likely all that’s left of a star that was whittled down by the pulsar.

Hard-core bling
The core of a stripped down star would be mostly carbon, with a dash of oxygen. With the mass of Jupiter, such an object would be under high pressure because of its own gravity. And this would cause it to crystallise – most likely into diamond, just as carbon does deep inside the Earth. If it is a diamond, does the planet glitter like an Earthly gem? “It’s highly speculative, but if you shine a light on it, I can’t see any reason why it wouldn’t sparkle like a diamond,” says Travis Metcalfe of the National Center for Atmospheric Research in Boulder, Colorado. He previously found a white dwarf – the remnant of an old star – with a carbon-crystal core that was under higher pressure than the new planet, producing a crystalline structure distinct from diamond. Moshe Mosbacher, president of the Diamond Dealers Club in New York says he has “no clue” how much a diamond of this size would fetch, without first knowing its quality. But he is intrigued. “If there’s some way to transport it to New York and cut it, it doesn’t make a difference if it’s from inner space or outer space.”

by Eric Bland / Jan 15, 2010

Oceans of liquid diamond, filled with solid diamond icebergs, could be floating on Neptune and Uranus, according to a recent article in the journal Nature Physics. The research, based on the first detailed measurements of the melting point of diamond, found diamond behaves like water during freezing and melting, with solid forms floating atop liquid forms. The surprising revelation gives scientists a new understanding about diamonds and some of the most distant planets in our solar system. “Diamond is a relatively common material on Earth, but its melting point has never been measured,” said J. H. Eggert of Lawrence Livermore National Laboratory in Livermore, Calif. “You can’t just raise the temperature and have it melt, you have to also go to high pressures, which makes it very difficult to measure the temperature.”

Other groups, notably scientists from Sandia National Laboratories, successfully melted diamond years ago, but they were unable to measure the pressure and temperature at which the diamond melted. Diamond is an incredibly hard material. That alone makes it difficult to melt. But diamond has another quality that makes it even harder to measure its melting point. Diamond doesn’t like to stay diamond when it gets hot. When diamond is heated to extreme temperatures it physically changes, from diamond to graphite. The graphite, and not the diamond, then melts into a liquid. The trick for the scientists was to heat the diamond up while simultaneously stopping it from transforming into graphite.

Eggert and his colleagues took a small, natural, clear diamond, about a tenth of a carat by weight and half a millimeter thick, and blasted it with lasers at ultrahigh pressures like those found on gas giants like Neptune and Uranus. The scientists liquefied the diamond at pressures 40 million times greater than what a person feels when standing at sea level on Earth. From there they slowly reduced the temperature and pressure. When the pressure dropped to about 11 million times the atmospheric pressure at sea level on Earth and the temperature dropped to about 50,000 degrees, solid chunks of diamond began to appear. The pressure kept dropping, but the temperature of the diamond remained the same, with more and more chunks of diamond forming. Then the diamond did something unexpected. The chunks of diamond didn’t sink. They floated. Microscopic diamond ice burgs floated in a tiny sea of liquid diamond. The diamond was behaving like water.

With most materials, the solid state is more dense than the liquid state. Water is an exception to that rule; when water freezes, the resulting ice is actually less dense than the surrounding water, which is why the ice floats and fish can survive a Minnesota winter. An ocean of diamond could help explain the orientation of Uranus’ and Neptune’s magnetic field as well, said Eggert. Roughly speaking, the Earth’s magnetic poles match up with the geographic poles. The magnetic and geographic poles on Uranus and Neptune do not match up; in fact, they can be up to 60 degrees off of the north-south axis. If Earth’s magnetic field were that far off it would place the magnetic north pole in Texas instead of off a Canadian island. A swirling ocean of liquid diamond could be responsible for the discrepancy.

Up to 10 percent of Uranus and Neptune is estimated to be made from carbon. A huge ocean of liquid diamond in the right place could deflect or tilt the magnetic field out of alignment with the rotation of the planet. The idea that there are oceans of liquid diamond on Neptune and Uranus is not a new idea, said Tom Duffy, a planetary scientist at Princeton University. The new Nature Physics article makes diamond oceans “look more and more plausible,” said Duffy. More research on the composition of Neptune and Uranus is needed before a truly definitive conclusion can be made, however, and this kind of research is very difficult to conduct. Scientists can either send spacecraft to these planets, or they can try to simulate the conditions on Earth. Both options require years of preparation, expensive equipment, and are subject to some of the toughest environments in the universe.


Astronomers have just solved a decade-old mystery that explains the unusual behavior of a neutron star — the dense, hot corpse left behind after a massive stellar explosion — at the center of the Cassiopeia A supernova remnant. It wasn’t the X-rays streaming from the center of the supernova remnant that astronomers found puzzling. It’s why the beams weren’t pulsating as expected. Now the scientists know why: The neutron star is covered with a thin atmosphere of carbon, which acts like a giant bulb to smooth light in all directions. The findings help to illustrate the extreme nature of these entities. “The carbon is unique,” Wynn Ho, a researcher with the University of Southampton in the United Kingdom, told Discovery News. “The neutron stars that have been detected with atmosphere have evolved with hydrogen, and that’s what we’d expect because hydrogen is the most abundant element in the universe.” Scientists believe the neutron star in Cassiopeia A is so young and hot that in addition to fusing hydrogen to form helium, the surface of the star is fusing helium into carbon.

Computer models show the carbon veil to be extremely thin — up to just four inches thick — due to the immense gravitational pull of the neutron star, which is about one billion times stronger than Earth’s gravity. Though the shroud is as dense as diamonds, the star’s 3.6 million-degree Fahrenheit temperature would keep the atmosphere gaseous. “It’s incredibly hot, so it’s still a gas,” said Peter Edmonds, with the Chandra X-ray Center at the Harvard-Smithsonian Center for Astrophysics. irect observations of the neutron star’s atmosphere are not possible with today’s technology, given its distance and other factors, but scientists are on the lookout for other young neutron stars that may also sport carbon shells. Being based on computer models, the finding isn’t ironclad, added Edmonds, “but it’s a strong case.” Cassiopeia A’s neutron star also serves as proverbial lab rat for physicists wondering what sort of exotic matter exists inside. “We’re using it to study the neutron star interior to determine whether its interior is made of superconducting material or quark matter. You can determine this based on its temperature and its age,” Ho said. “Any exotic matter will determine how rapidly it cools over time.”


Citizen group tracks down Japan’s radiation
Amid contradictory government statistics, a volunteer group has recorded 500,000 radiation points across the country.
by Dahr Jamail / 10 Aug 2011

The aftermath of the Fukushima Daiichi nuclear crisis has been marked by an outcry in Japan over radiation leaks, contaminated food and a government unable to put the public’s fears to rest. Perhaps the most worrying aspect of the meltdown that resulted from March’s earthquake–triggered disaster, activists and citizens have said, is the uncertainty that has ensued. In the months since the catastrophe, the Japanese government, its nuclear watchdogs and Tokyo Electric Power Company (TEPCO), have provided differing, confusing, and at times contradictory, information on critical health issues. Fed up with indefinite data, a group of 50 volunteers decided to take matters, and Geiger counters, into their own hands. In April, an independent network of like-minded individuals in the Japan and United States banded together to form Safecast and began an ongoing crusade to record and publish accurate radiation levels around Japan. The group handed out mobile radiation detectors and uploaded the readings to the internet to map out exposure levels.  Sean Bonner, director of Safecast, told Al Jazeera that volunteers have so far logged more than 500,000 radiation data points across Japan.  He said the group is the only organisation he knows that is tracking radiation on a local level. The findings, Bonner added, have been shocking. “People keep asking how we are doing it, when the government isn’t,” he said.

Lack of information
Dr Yuko Yanagisawa, a 51-year-old physician at Funabashi Futawa Hospital in Chiba Prefecture, feels the government’s response to health concerns has been grossly inadequate. In the area where Yanagisawa lives and works, approximately 200 km from Fukushima, unhealthy radiation levels have been recorded. Even so, she said the only information the government has released was to raise the acceptable radiation exposure limit for children from one millisieverts (mSv) of radioactivity a year to 20. “This has caused controversy, from the medical point of view,” Yanagisawa told Al Jazeera. “This is certainly an issue that involves both personal internal exposures as well as low-dose exposures.” From the start, the government’s track record on public health announcements has been poor. As early radiation readings from the disaster site emerged, Japan’s then-Minister for Internal Affairs, Haraguchi Kazuhiro, alleged that monitoring station data was actually three decimal places greater than the numbers released to the public. In late March, the Japanese Nuclear Safety Commission conducted a survey that found an estimated 45 per cent of children in the Fukushima region had experienced thyroid exposure to radiation. But the commission has not carried out any surveys since.

Health specialists say the commission fears a negative public reaction to children’s exposure to radiation from the crippled Fukushima plant.

Contaminated food fears
Recent disclosures from government agencies and TEPCO, the operator of the Fukushima plant, suggest that public information has hardly improved. Earlier this month, TEPCO said it detected 10,000 mSv of radioactivity at the heavily damaged plant. A dose this high would be fatal to humans, and was 250 per cent more than the previous high levels at the plant in March soon after the disaster. Authorities have also been vague about the extent of the radiation, and how the potential spread may be affecting vital food crops and livestock. Jyunichi Tokuyama, a specialist with the Iwate Prefecture Agricultural and Fisheries Department, said he was shocked to find radioactive hot spots in his prefecture, more than 300km from the stricken Fukushima nuclear site. “The biggest cause of this contamination is the rice straw being fed to the cows, which was highly radioactive,” Tokuyama told Al Jazeera. On August 1, Iwate became Japan’s forth prefecture to suspend all of its beef exports due to cesium contamination. Neighbouring governments have announced plans to test Japan’s agricultural exports for radioactive cesium after concerns over soil contamination.

‘Not getting the data’
Despite the alarm inside Japan and abroad, specific information about radiation levels and its range are still mostly unavailable. This lack of information is what Safecast is trying to overcome. “We spoke with a woman in Japan on Saturday who said since March she’s been calling her local offices, and the federal government, just trying to get data, and she’s not been able to get a single reading close to her house,” Bonner said. “Part of that is that the information is just not there, the government doesn’t have it. I don’t think they are necessarily withholding, but I think they are just not getting the data.” Bonner said he was disturbed by the readings he took last weekend nearly 28km outside the Fukushima site. The Japanese government maintains a mandatory evacuation zone around the plant that extends to 20km, the next 10km is the voluntary evacuation zone. People who live there are not given any financial compensation by the government if they choose to evacuate. “Sunday [August 7], we found ground contamination of 20,000 cpm,” said Bonner, referring to counts per minute, a method he believes is more accurate in analysing radiation than measuring mSv. “It was about 28km from the plant. There were police officers there standing around all day making sure nobody went into the mandatory evacuation zone, wearing no protective clothing. They said they didn’t know what the readings were, they were just told to be there.” Bonner plans to return monthly and continue with the project “indefinitely”. “Getting into this has showed us there is a lack of data everywhere,” he said. “This week I’m going to start mapping radiation data in California, and we’re going to start getting devices to people around the US and Europe. We’re going to set up fixed sensors and we’re making a device that we’ll sell to the public. We’re hoping to continue to get lots of data from lots of sources.”

Global debate
The Japanese government does not consider non-government readings to be authentic, and has urged the public to only rely on government data on radiation. Bonner said: “Getting into this has showed us there is a lack of data everywhere. We’re going to start getting devices to people around the US and Europe. We’re going to set up fixed sensors and we’re making a device that we’ll sell to the public. We’re hoping to continue to get lots of data from lots of sources.” Bonner’s ambitions appear timely against the backdrop of a revitalised global debate on the dangers of nuclear energy, especially in Japan. Prime Minister Naoto Kan recently pledged to lower Japan’s reliance on nuclear power due to the consequences of the Fukushima crisis. He and other officials have admitted to deep concerns about radiation-induced health risks. “Japan will reduce its level of reliance on nuclear power generation with the aim of becoming a society that is not dependent on nuclear power,” Kan said last week in Hiroshima in a speech to mark the 66th anniversary of the US atomic bombing of the city.

New Visualizations


One of our goals at Safecast, in addition to collecting radiation data, is putting that data into a format that is helpful and useful. If you’ve been following our work for the last few months you’ve seen the map we launched with on day one progress through several evolutions including being split out into several specific purpose versions. We’ve just launched a new revision to these and now have a maps specific URL we’re we’ll keep all the mapping visualizations we’re producing. Please take a look atmaps.safecast.org.

What you’ll see there:
Safecast Map: This depicts over 500,000 radiation data points collected by the Safecast team throughout Japan. For each square, numerous geiger readings have been collected and color-coded. This is our main map and the one we’ll be tweaking and improving on a very regular basis.

Full Data Set Map: While the Safecast Map simplifies the readings into a general grid, the full data set map actually shows you each and every point we’ve collected. It’s very dense, but if you want to drill in this is where you can do it. This collected data set will be available for download in the near future.

Drive Maps: Both of the above maps are based on data we’ve collected driving around with out bGeigie sensors. If you want to see an individual drive on it’s own check out the Drive Maps, you can also download a CSV file for each drive to play with the data yourself.

Fixed Sensor Network: We’ve been working with our partners at Keio University’s Scanning The Earth project to build a network of fixed sensors, and this maps shows the data coming in from those devices we’ve installed out in the field. STE has a great historical visualization of these points, and Yahoo! Japan has just release their own map using the data we’re providing from these devices.

Aggregate Map: We also still have the original Aggregate Map showing all the data we’re scraping from other sources.


While these are our newest maps, they are by no means our final versions and we’ll continue to edit and improve these as our work continues – that said we think these are a step forward from our last versions, and hope our next step will be an improvement to these. We know there are some missing legends and a little better explanation of what the colors/points mean and hope to have that up soon, but if you have any other feedback, requests, comments, concerns, etc please let us know.

Our new set up includes two geiger counters (one mounted outside the car, one handheld inside which can also be used if stopped and walking around), a laptop, a GPS module, mobile wifi hotspot and some weather proof casings. Once installed on a car this lets us track a great deal of info and upload it immediately. This is what we’re collecting data wise:

  1. • year-month-day
  2. • hour:minute:second
  3. • CPM (counts-per-minute)*
  4. • Latitude: ddmm.mmmm, dd is integer in degree, mm.mmmm is decimal in
    minute. We can divide mm.mmmm by 60 to get degrees.
  5. • N/S (north/south indicator)
  6. • Longitude: dddmm.mmmm, ddd is integer in degree, mm.mmmm is decimal
    in minute. We can divide mm.mmmm by 60 to get degrees.
  7. • E/W (east/west indicator)
  8. • GPS Quality indicator
  9. • Number of satellites available
  10. • Precision in metres
  11. • Altitude in metres
  12. • GPS Device name
  13. • Measurement type

*The use of CPM is noteworthy since most of the reports are currently using µSv/hr. There is currently a great deal of discussion about which measurement is better or more accurate as µSv/hr doesn’t specify isotopes and can vary based on what is being measured. In our case however the International Medcom Inspector Alert geiger counters that we are using displays both, but output via the connector is CPM. We’re taking note of both and using µSv/hr in discussion but will continue to look into this and evaluate which is a better unit of measurement for these purposes. In this case dividing CPM by 350 gives us µSv/hr.

Our plan has been to install this system into a car and then drive north into Fukushima to elementary, junior high and high schools outside of the evacuation zone and try to get some readings there and along the way. Assuming that worked we’d replicate this set up in several cars so we can cover ground more quickly. For this run we several more hand held counters just to double check the readings and set ups.

#bGeigie -first bento boxed shaped automated geotagging Geiger counter system

On Saturday, April 23rd we gave this the first field test. Japan team members Mauricio, Pieter, Robin and Steve met up at Tokyo Hackerspace first thing in the morning, hooked things up, tested them and hit the road. The Fukushima newspaper printed a radiation map showing readings around the evacuation zone which was you can see had quite a bit of variance so we hoped to get more data to cross reference with this.

#fukushima newspaper Radiation map showing 20km zone and radiation levels. Notice variance on the edges of the zone.

Additionally part of our mission is to distribute equipment to people who can continue to take readings on their own after we’ve left and have them continue to upload data to our site so we will have historical data as well. I’m happy to happy to announce that we did just that with this trip to Koriyama and were able to leave two sensor devices and an iPhone (for uploading images and data to our servers) with a team of volunteers there.

Met volunteers for #safecast.org in koriyama and handed a Geiger counter and geotagging iPhone to start data reporting

As for the actual data we recorded, that was very interesting. We’re in the process of checking the logs (removing duplicate entries and things) and will have it uploaded toour map and pachube shortly so every point we recorded will be visible and available for evaluation by outside parties. Here is photo documentation of some of the readings we took with the handheld devices. All in all we drove for 6.5 hours and measured close to 5000 locations. We measured at the gate of 5 schools in Koriyama.

We took one reading that was considerably higher than all the others:

This was the highest we reading we took, but we consistently measured 20-30µSv/hr on pavements, etc. and 5-10µSv/hr for soil (typically 5-6 for soil) For air measurement, we have very consitent data as it is measured across the entire ride. In Koriyama it was in the range of 1.2 to 2µSv/hr. We had 3 Medcom devices giving consitently the same value and a Gamma Scout that gave same readings for air. This multiple redundancy was to ensure we didn’t have malfunctioning equipment or a calibration error.

To put those numbers into some perspective, on Sunday April 24th we measured 0.089µSv/hr in the air and 0.227µSv/hr on the ground at in the Silver Lake neighborhood of Los Angeles. Furthermore in Japan, radiation worker dose limits pre-Fukushima were 100 mSv/yr and the dose limit for normal person is 1 mSv/yr. 50µSv/hr is equivalent to annual dosage of 438 mSv which is more than 4x higher than the limit for nuclear radiation workers.

There are caveats to those numbers of course and as I mentioned the Sievert is the subject of some disagreement in and of itself. Additionally those limits may be focused primarily on high energy gamma, where as our sensors measure alpha and beta which are included in our µSv/hr measurements. Some sensors only measure high energy gamma. Alpha and beta particles are slower and penetrate less so may be considered less dangerous for exposure, but when ingested or inhaled can concentrate in certain organs and cause even more damage than a blast of high energy gamma. In other words, 50µSv/hr on the wall might end up being concentrated into a tiny 1cc square in your thyroid and might end up causing a much more concentrated dose into a particular set of cells than say a 50µSv/hr blast at your body with high energy gamma which would hit all of your cells mostly evenly. Think of the difference between the concentration of radiation used for killing cancer cells vs the wide spread used in an xray. Even that is confusing but we’ve found this infographic to be helpful in understanding different kinds of radiation and doses.

Again we want to make it clear that we are not radiation experts nor health physicists – we aren’t making any claim about how safe, or not, any of these measurements might be – rather we are trying to find and provide data that could be important for residents of these areas so that they can make informed decisions on their own. It’s one thing to be told everything is fine, it’s another thing to have access to the actual measurements and make that decision on your own. That said we are actively looking for experts to help us interpret this data and improve our protocols. If you or someone you know can help us there please get in touch. We expect to continually review and revise our methods as we continue to learn more about this ourselves. This is just the first of many runs we’ll be making in Japan, and with each one we plan to distribute more sensors to help build a clearer picture of what is happening on on ongoing basis.

These efforts have so far been funded by the kindness and donations of a few people but we’re going to need more financial help to keep this up. If you’d like to chip in a few dollars, please check out our kickstarter fundraiser. Thanks so much.

by Norimitsu Onishi and Martin Fackler / August 8, 2011

The day after a giant tsunami set off the continuing disaster at the Fukushima Daiichi nuclear plant, thousands of residents at the nearby town of Namie gathered to evacuate. Given no guidance from Tokyo, town officials led the residents north, believing that winter winds would be blowing south and carrying away any radioactive emissions. For three nights, while hydrogen explosions at four of the reactors spewed radiation into the air, they stayed in a district called Tsushima where the children played outside and some parents used water from a mountain stream to prepare rice. The winds, in fact, had been blowing directly toward Tsushima — and town officials would learn two months later that a government computer system designed to predict the spread of radioactive releases had been showing just that. But the forecasts were left unpublicized by bureaucrats in Tokyo, operating in a culture that sought to avoid responsibility and, above all, criticism. Japan’s political leaders at first did not know about the system and later played down the data, apparently fearful of having to significantly enlarge the evacuation zone — and acknowledge the accident’s severity. “From the 12th to the 15th we were in a location with one of the highest levels of radiation,” said Tamotsu Baba, the mayor of Namie, which is about five miles from the nuclear plant. He and thousands from Namie now live in temporary housing in another town, Nihonmatsu. “We are extremely worried about internal exposure to radiation.” The withholding of information, he said, was akin to “murder.”

In interviews and public statements, some current and former government officials have admitted that Japanese authorities engaged in a pattern of withholding damaging information and denying facts of the nuclear disaster — in order, some of them said, to limit the size of costly and disruptive evacuations in land-scarce Japan and to avoid public questioning of the politically powerful nuclear industry. As the nuclear plant continues to release radiation, some of which has slipped into the nation’s food supply, public anger is growing at what many here see as an official campaign to play down the scope of the accident and the potential health risks. Seiki Soramoto, a lawmaker and former nuclear engineer to whom Prime Minister Naoto Kan turned for advice during the crisis, blamed the government for withholding forecasts from the computer system, known as the System for Prediction of Environmental Emergency Dose Information, or Speedi. “In the end, it was the prime minister’s office that hid the Speedi data,” he said. “Because they didn’t have the knowledge to know what the data meant, and thus they did not know what to say to the public, they thought only of their own safety, and decided it was easier just not to announce it.”

In an interview, Goshi Hosono, the minister in charge of the nuclear crisis, dismissed accusations that political considerations had delayed the release of the early Speedi data. He said that they were not disclosed because they were incomplete and inaccurate, and that he was presented with the data for the first time only on March 23. “And on that day, we made them public,” said Mr. Hosono, who was one of the prime minister’s closest advisers in the early days of the crisis before being named nuclear disaster minister. “As for before that, I myself am not sure. In the days before that, which were a matter of life and death for Japan as a nation, I wasn’t taking part in what was happening with Speedi.” The computer forecasts were among many pieces of information the authorities initially withheld from the public. Meltdowns at three of Fukushima Daiichi’s six reactors went officially unacknowledged for months. In one of the most damning admissions, nuclear regulators said in early June that inspectors had found tellurium 132, which experts call telltale evidence of reactor meltdowns, a day after the tsunami — but did not tell the public for nearly three months. For months after the disaster, the government flip-flopped on the level of radiation permissible on school grounds, causing continuing confusion and anguish about the safety of schoolchildren here in Fukushima.

Too Late
The timing of many admissions — coming around late May and early June, when inspectors from the International Atomic Energy Agency visited Japan and before Japan was scheduled to deliver a report on the accident at an I.A.E.A. conference — suggested to critics that Japan’s nuclear establishment was coming clean only because it could no longer hide the scope of the accident. On July 4, the Atomic Energy Society of Japan, a group of nuclear scholars and industry executives, said, “It is extremely regrettable that this sort of important information was not released to the public until three months after the fact, and only then in materials for a conference overseas.” The group added that the authorities had yet to disclose information like the water level and temperature inside reactor pressure vessels that would yield a fuller picture of the damage. Other experts have said the government and Tokyo Electric Power Company, known as Tepco, have yet to reveal plant data that could shed light on whether the reactors’ cooling systems were actually knocked out solely by the 45-foot-tall tsunami, as officials have maintained, or whether damage from the earthquake also played a role, a finding that could raise doubts about the safety of other nuclear plants in a nation as seismically active as Japan.

Government officials insist that they did not knowingly imperil the public. “As a principle, the government has never acted in such a way as to sacrifice the public’s health or safety,” said Mr. Hosono, the nuclear disaster minister. Here in the prefecture’s capital and elsewhere, workers are removing the surface soil from schoolyards contaminated with radioactive particles from the nuclear plant. Tens of thousands of children are being kept inside school buildings this hot summer, where some wear masks even though the windows are kept shut. Many will soon be wearing individual dosimeters to track their exposure to radiation. At Elementary School No. 4 here, sixth graders were recently playing shogi and go, traditional board games, inside. Nao Miyabashi, 11, whose family fled here from Namie, said she was afraid of radiation. She tried not to get caught in the rain. She gargled and washed her hands as soon as she got home. “I want to play outside,” she said. About 45 percent of 1,080 children in three Fukushima communities surveyed in late March tested positive for thyroid exposure to radiation, according to a recent announcement by the government, which added that the levels were too low to warrant further examination. Many experts both in and outside Japan are questioning the government’s assessment, pointing out that in Chernobyl, most of those who went on to suffer from thyroid cancer were children living near that plant at the time of the accident.

Critics inside and outside the Kan administration argue that some of the exposure could have been prevented if officials had released the data sooner. On the evening of March 15, Mr. Kan called Mr. Soramoto, who used to design nuclear plants for Toshiba, to ask for his help in managing the escalating crisis. Mr. Soramoto formed an impromptu advisory group, which included his former professor at the University of Tokyo, Toshiso Kosako, a top Japanese expert on radiation measurement. Mr. Kosako, who studied the Soviet response to the Chernobyl crisis, said he was stunned at how little the leaders in the prime minister’s office knew about the resources available to them. He quickly advised the chief cabinet secretary, Yukio Edano, to use Speedi, which used measurements of radioactive releases, as well as weather and topographical data, to predict where radioactive materials could travel after being released into the atmosphere. Speedi had been designed in the 1980s to make forecasts of radiation dispersal that, according to the prime minister’s office’s own nuclear disaster manuals, were supposed to be made available at least to local officials and rescue workers in order to guide evacuees away from radioactive plumes. And indeed, Speedi had been churning out maps and other data hourly since the first hours after the catastrophic earthquake and tsunami. But the Education Ministry had not provided the data to the prime minister’s office because, it said, the information was incomplete. The tsunami had knocked out sensors at the plant: without measurements of how much radiation was actually being released by the plant, they said, it was impossible to measure how far the radioactive plume was stretching. “Without knowing the strength of the releases, there was no way we could take responsibility if evacuations were ordered,” said Keiji Miyamoto of the Education Ministry’s nuclear safety division, which administers Speedi.

The government had initially resorted to drawing rings around the plant, evacuating everyone within a radius of first 1.9 miles, then 6.2 miles and then 12.4 miles, widening the rings as the scale of the disaster became clearer. But even with incomplete data, Mr. Kosako said he urged the government to use Speedi by making educated guesses as to the levels of radiation release, which would have still yielded usable maps to guide evacuation plans. In fact, the ministry had done precisely that, running simulations on Speedi’s computers of radiation releases. Some of the maps clearly showed a plume of nuclear contamination extending to the northwest of the plant, beyond the areas that were initially evacuated. However, Mr. Kosako said, the prime minister’s office refused to release the results even after it was made aware of Speedi, because officials there did not want to take responsibility for costly evacuations if their estimates were later called into question.

A wider evacuation zone would have meant uprooting hundreds of thousands of people and finding places for them to live in an already crowded country. Particularly in the early days after the earthquake, roads were blocked and trains were not running. These considerations made the government desperate to limit evacuations beyond the 80,000 people already moved from areas around the plant, as well as to avoid compensation payments to still more evacuees, according to current and former officials interviewed. Mr. Kosako said the top advisers to the prime minister repeatedly ignored his frantic requests to make the Speedi maps public, and he resigned in April over fears that children were being exposed to dangerous radiation levels. Some advisers to the prime minister argue that the system was not that useful in predicting the radiation plume’s direction. Shunsuke Kondo, who heads the Atomic Energy Commission, an advisory body in the Cabinet Office, said that the maps Speedi produced in the first days were inconsistent, and changed several times a day depending on wind direction. “Why release something if it was not useful?” said Mr. Kondo, also a retired professor of nuclear engineering at the University of Tokyo. “Someone on the ground in Fukushima, looking at which way the wind was blowing, would have known just as much.”

Mr. Kosako and others, however, say the Speedi maps would have been extremely useful in the hands of someone who knew how to sort through the system’s reams of data. He said the Speedi readings were so complex, and some of the predictions of the spread of radiation contamination so alarming, that three separate government agencies — the Education Ministry and the two nuclear regulators, the Nuclear and Industrial Safety Agency and Nuclear Safety Commission — passed the data to one another like a hot potato, with none of them wanting to accept responsibility for its results. In interviews, officials at the ministry and the agency each pointed fingers, saying that the other agency was responsible for Speedi. The head of the commission declined to be interviewed. Mr. Baba, the mayor of Namie, said that if the Speedi data had been made available sooner, townspeople would have naturally chosen to flee to safer areas. “But we didn’t have the information,” he said. “That’s frustrating.” Evacuees now staying in temporary prefabricated homes in Nihonmatsu said that, believing they were safe in Tsushima, they took few precautions. Yoko Nozawa, 70, said that because of the lack of toilets, they resorted to pits in the ground, where doses of radiation were most likely higher. “We were in the worst place, but didn’t know it,” Ms. Nozawa said. “Children were playing outside.” A neighbor, Hiroyuki Oto, 31, said he was working at the plant for a Tepco subcontractor at the time of the earthquake and was now in temporary lodging with his wife and three young children, after also staying in Tsushima. “The effects might emerge only years from now,” he said of the exposure to radiation. “I’m worried about my kids.”

Seeds of Mistrust
Mr. Hosono, the minister charged with dealing with the nuclear crisis, has said that certain information, including the Speedi data, had been withheld for fear of “creating a panic.” In an interview, Mr. Hosono — who now holds nearly daily news conferences with Tepco officials and nuclear regulators — said that the government had “changed its thinking” and was trying to release information as fast as possible. Critics, as well as the increasingly skeptical public, seem unconvinced. They compare the response to the Minamata case in the 1950s, a national scandal in which bureaucrats and industry officials colluded to protect economic growth by hiding the fact that a chemical factory was releasing mercury into Minamata Bay in western Japan. The mercury led to neurological illnesses in thousands of people living in the region and was captured in wrenching photographs of stricken victims. “If they wanted to protect people, they had to release information immediately,” said Reiko Seki, a sociologist at Rikkyo University in Tokyo and an expert on the cover-up of the Minamata case. “Despite the experience with Minamata, they didn’t release Speedi.”

In Koriyama, a city about 40 miles west of the nuclear plant, a group of parents said they had stopped believing in government reassurances and recently did something unthinkable in a conservative, rural area: they sued. Though their suit seeks to force Koriyama to relocate their children to a safer area, their real aim is to challenge the nation’s handling of evacuations and the public health crisis. After the nuclear disaster, the government raised the legal exposure limit to radiation from one to 20 millisieverts a year for people, including children — effectively allowing them to continue living in communities from which they would have been barred under the old standard. The limit was later scaled back to one millisievert per year, but applied only to children while they were inside school buildings. The plaintiffs’ lawyer, Toshio Yanagihara, said the authorities were withholding information to deflect attention from the nuclear accident’s health consequences, which will become clear only years later. “Because the effects don’t emerge immediately, they can claim later on that cigarettes or coffee caused the cancer,” he said. The Japanese government is considering monitoring the long-term health of Fukushima residents and taking appropriate measures in the future, said Yasuhiro Sonoda, a lawmaker and parliamentary secretary of the Cabinet Office. The mayor of Koriyama, Masao Hara, said he did not believe that the government’s radiation standards were unsafe. He said it was “unrealistic” to evacuate the city’s 33,000 elementary and junior high school students. But Koriyama went further than the government’s mandates, removing the surface soil from its schools before national directives and imposing tougher inspection standards than those set by the country’s education officials. “The Japanese people, after all, have a high level of knowledge,” the mayor said, “so I think information should be disclosed correctly and quickly so that the people can make judgments, especially the people here in Fukushima.”

by Duncan Geere / 13 July 11

To a computer, words and sentences appear like data. But AI researchers want to teach computers how to actually understand the meaning of a sentence and learn from it. One of the best ways to test the capability of an AI to do that is to see whether it can understand and follow a set of instructions for a task that it’s unfamiliar with. Regina Barzilay, a professor of computer science and electrical engineering at MIT’s computer science and AI lab, has attempted to do just that — teaching a computer to play Sid Meier’s Civilization. In Civilization, the player is asked to guide a nation from the earliest periods of history through to the present day and into the future. It’s complex, and each action doesn’t necessarily have a predetermined outcome, because the game can react randomly to what you do. Barzilay found that putting a machine-learning system to work on Civ gave it a victory rate of 46 percent, but that when the system was able to use the manual for the game to guide the development of its strategy, it rose dramatically to 79 percent.

It works by word association. Starting completely from scratch, the computer behaves randomly. As it acts, however, it can read words that pop up on the screen, and then search for those words in the manual. As it finds them, it can scan the surrounding text to develop ideas about what action that word corresponds with. Ideas that work well are kept, and those that lead to bad results are discarded. “If you’d asked me beforehand if I thought we could do this yet, I’d have said no,” says Eugene Charniak, University Professor of Computer Science at Brown University. “You are building something where you have very little information about the domain, but you get clues from the domain itself.” The eventual goal is both to develop AIs that can extract useful information from manuals written for humans, allowing them to approach a problem armed with just the instructions, rather than having to be painstakingly taught how to deal with any eventuality. Barzilay has already begun to adapt these systems to work with robots.

“Civilization” is a strategy game in which players build empires by, among other things, deciding where to found cities and deploy armies.

Computers learn language (and world domination) by reading the manual
by Darren Quick / July 13, 2011

Researchers at MIT’s Computer Science and Artificial Intelligence Lab have been able to create computers that learn language by doing something that many people consider a last resort when tackling an unfamiliar task – reading the manual (or RTBM). Beginning with virtually no prior knowledge, one machine-learning system was able to infer the meanings of words by reviewing instructions posted on Microsoft’s website detailing how to install a piece of software on a Windows PC, while another was able to learn how to play Sid Meier’s empire-building Civilization II strategy computer game by reading the gameplay manual.

Without so much as an idea of the task they were intended to perform or the language in which the instructions were written, the two similar systems were initially provided only with a list of possible actions they could take, such as moving the cursor or performing right or left clicks. They also had access to the information displayed on the screen and were able to gauge their success, be it successfully installing the software or winning the game. But they didn’t know what actions corresponded to what words in the instructions, or what the objects in the game world represent. Predictably, this means that initially the behavior of the system is pretty random, but as it performs various actions and words appear on the screen it looks for instances of that word in the instruction set as well as searching the surrounding text for associated words. In this way it is able to make assumptions about what actions the words correspond to and assumptions that consistently lead to good results are given greater credence, while those that consistently lead to bad results are abandoned.

Using this method, the system attempting to install software was able to reproduce 80 percent of the steps that a person reading the same instructions would carry out. Meanwhile, the system playing Civilization II ended up winning 79 percent of the games it played, compared to a winning rate of 46 percent for a version of the system that didn’t rely on the written instructions. What makes the results even more impressive for the Civilization II-playing system is that the manual only provided instructions on how to play the game. “They don’t tell you how to win. They just give you very general advice and suggestions, and you have to figure out a lot of other things on your own,” said Regina Barzilay, associate professor of computer science and electrical engineering, who took the best-paper award at the annual meeting of the Association for Computational Linguistics (ACL) in 2009 for the software installing system. “Games are used as a test bed for artificial-intelligence techniques simply because of their complexity,” says graduate student S. R. K. Branavan, who along David Silver of University College London applied a similar approach to Barzilay in developing the system that learned to play Civilization II. “Every action that you take in the game doesn’t have a predetermined outcome, because the game or the opponent can randomly react to what you do. So you need a technique that can handle very complex scenarios that react in potentially random ways,” Branavan said.

Although the main purpose of the project was to demonstrate that computer systems that learn the meanings of words through exploratory interaction with their environments is a promising area for future research, Barzilay and Branavan say that such systems could also have more near-term applications. Most computer games that let a player play against the computer require programmers to develop strategies for the computer to follow and write algorithms that execute them. Systems like those developed at MIT could be used to automatically create algorithms that perform better than the human-designed ones. With such machine-learning systems also having applications in the field of robotics, and Barzilay and her students at MIT have begun to adapt their meaning-inferring algorithms to this purpose. Let’s just hope they don’t take the lessons learned playing Civilization II and try for the world domination win in the real world.

Screen shot of Sid Meier's strategy computer game, Civilization II
Screen shot of Sid Meier’s strategy computer game, Civilization II

Computer learns language by playing games
By basing its strategies on the text of a manual, a computer infers the meanings of words without human supervision.
by Larry Hardesty, MIT / July 12 2011

Computers are great at treating words as data: Word-processing programs let you rearrange and format text however you like, and search engines can quickly find a word anywhere on the Web. But what would it mean for a computer to actually understand the meaning of a sentence written in ordinary English — or French, or Urdu, or Mandarin?

One test might be whether the computer could analyze and follow a set of instructions for an unfamiliar task. And indeed, in the last few years, researchers at MIT’s Computer Science and Artificial Intelligence Lab have begun designing machine-learning systems that do exactly that, with surprisingly good results. In 2009, at the annual meeting of the Association for Computational Linguistics (ACL), researchers in the lab of Regina Barzilay, associate professor of computer science and electrical engineering, took the best-paper award for a system that generated scripts for installing a piece of software on a Windows computer by reviewing instructions posted on Microsoft’s help site. At this year’s ACL meeting, Barzilay, her graduate student S. R. K. Branavan and David Silver of University College London applied a similar approach to a more complicated problem: learning to play “Civilization,” a computer game in which the player guides the development of a city into an empire across centuries of human history. When the researchers augmented a machine-learning system so that it could use a player’s manual to guide the development of a game-playing strategy, its rate of victory jumped from 46 percent to 79 percent.

Starting from scratch
“Games are used as a test bed for artificial-intelligence techniques simply because of their complexity,” says Branavan, who was first author on both ACL papers. “Every action that you take in the game doesn’t have a predetermined outcome, because the game or the opponent can randomly react to what you do. So you need a technique that can handle very complex scenarios that react in potentially random ways.” Moreover, Barzilay says, game manuals have “very open text. They don’t tell you how to win. They just give you very general advice and suggestions, and you have to figure out a lot of other things on your own.” Relative to an application like the software-installing program, Branavan explains, games are “another step closer to the real world.” The extraordinary thing about Barzilay and Branavan’s system is that it begins with virtually no prior knowledge about the task it’s intended to perform or the language in which the instructions are written. It has a list of actions it can take, like right-clicks or left-clicks, or moving the cursor; it has access to the information displayed on-screen; and it has some way of gauging its success, like whether the software has been installed or whether it wins the game. But it doesn’t know what actions correspond to what words in the instruction set, and it doesn’t know what the objects in the game world represent. So initially, its behavior is almost totally random. But as it takes various actions, different words appear on screen, and it can look for instances of those words in the instruction set. It can also search the surrounding text for associated words, and develop hypotheses about what actions those words correspond to. Hypotheses that consistently lead to good results are given greater credence, while those that consistently lead to bad results are discarded.

Proof of concept
In the case of software installation, the system was able to reproduce 80 percent of the steps that a human reading the same instructions would execute. In the case of the computer game, it won 79 percent of the games it played, while a version that didn’t rely on the written instructions won only 46 percent. The researchers also tested a more-sophisticated machine-learning algorithm that eschewed textual input but used additional techniques to improve its performance. Even that algorithm won only 62 percent of its games. “If you’d asked me beforehand if I thought we could do this yet, I’d have said no,” says Eugene Charniak, University Professor of Computer Science at Brown University. “You are building something where you have very little information about the domain, but you get clues from the domain itself.” Charniak points out that when the MIT researchers presented their work at the ACL meeting, some members of the audience argued that more sophisticated machine-learning systems would have performed better than the ones to which the researchers compared their system. But, Charniak adds, “it’s not completely clear to me that that’s really relevant. Who cares? The important point is that this was able to extract useful information from the manual, and that’s what we care about.” Most computer games as complex as “Civilization” include algorithms that allow players to play against the computer, rather than against other people; the games’ programmers have to develop the strategies for the computer to follow and write the code that executes them. Barzilay and Branavan say that, in the near term, their system could make that job much easier, automatically creating algorithms that perform better than the hand-designed ones. But the main purpose of the project, which was supported by the National Science Foundation, was to demonstrate that computer systems that learn the meanings of words through exploratory interaction with their environments are a promising subject for further research. And indeed, Barzilay and her students have begun to adapt their meaning-inferring algorithms to work with robotic systems.

Regina Barzilay
email : regina [at] csail.mit [dot] edu

S.R.K. Branavan
email : branavan [at] csail.mit [dot] edu

An incidental challenge in building a computer system that could decipher Ugaritic (inscribed on tablet) was developing a way to digitally render Ugaritic symbols (inset).

Computer automatically deciphers ancient language
A new system that took a couple hours to decipher much of the ancient language Ugaritic could help improve online translation software.
by Larry Hardesty, MIT /  June 30 2010

In his 2002 book Lost Languages, Andrew Robinson, then the literary editor of the London Times’ higher-education supplement, declared that “successful archaeological decipherment has turned out to require a synthesis of logic and intuition … that computers do not (and presumably cannot) possess.” Regina Barzilay, an associate professor in MIT’s Computer Science and Artificial Intelligence Lab, Ben Snyder, a grad student in her lab, and the University of Southern California’s Kevin Knight took that claim personally. At the Annual Meeting of the Association for Computational Linguistics in Sweden next month, they will present a paper on a new computer system that, in a matter of hours, deciphered much of the ancient Semitic language Ugaritic. In addition to helping archeologists decipher the eight or so ancient languages that have so far resisted their efforts, the work could also help expand the number of languages that automated translation systems like Google Translate can handle.

To duplicate the “intuition” that Robinson believed would elude computers, the researchers’ software makes several assumptions. The first is that the language being deciphered is closely related to some other language: In the case of Ugaritic, the researchers chose Hebrew. The next is that there’s a systematic way to map the alphabet of one language on to the alphabet of the other, and that correlated symbols will occur with similar frequencies in the two languages. The system makes a similar assumption at the level of the word: The languages should have at least some cognates, or words with shared roots, like main and mano in French and Spanish, or homme and hombre. And finally, the system assumes a similar mapping for parts of words. A word like “overloading,” for instance, has both a prefix — “over” — and a suffix — “ing.” The system would anticipate that other words in the language will feature the prefix “over” or the suffix “ing” or both, and that a cognate of “overloading” in another language — say, “surchargeant” in French — would have a similar three-part structure.

The system plays these different levels of correspondence off of each other. It might begin, for instance, with a few competing hypotheses for alphabetical mappings, based entirely on symbol frequency — mapping symbols that occur frequently in one language onto those that occur frequently in the other. Using a type of probabilistic modeling common in artificial-intelligence research, it would then determine which of those mappings seems to have identified a set of consistent suffixes and prefixes. On that basis, it could look for correspondences at the level of the word, and those, in turn, could help it refine its alphabetical mapping. “We iterate through the data hundreds of times, thousands of times,” says Snyder, “and each time, our guesses have higher probability, because we’re actually coming closer to a solution where we get more consistency.” Finally, the system arrives at a point where altering its mappings no longer improves consistency.

Ugaritic has already been deciphered: Otherwise, the researchers would have had no way to gauge their system’s performance. The Ugaritic alphabet has 30 letters, and the system correctly mapped 29 of them to their Hebrew counterparts. Roughly one-third of the words in Ugaritic have Hebrew cognates, and of those, the system correctly identified 60 percent. “Of those that are incorrect, often they’re incorrect only by a single letter, so they’re often very good guesses,” Snyder says. Furthermore, he points out, the system doesn’t currently use any contextual information to resolve ambiguities. For instance, the Ugaritic words for “house” and “daughter” are spelled the same way, but their Hebrew counterparts are not. While the system might occasionally get them mixed up, a human decipherer could easily tell from context which was intended.

Nonetheless, Andrew Robinson remains skeptical. “If the authors believe that their approach will eventually lead to the computerised ‘automatic’ decipherment of currently undeciphered scripts,” he writes in an e-mail, “then I am afraid I am not at all persuaded by their paper.” The researchers’ approach, he says, presupposes that the language to be deciphered has an alphabet that can be mapped onto the alphabet of a known language — “which is almost certainly not the case with any of the important remaining undeciphered scripts,” Robinson writes. It also assumes, he argues, that it’s clear where one character or word ends and another begins, which is not true of many deciphered and undeciphered scripts. “Each language has its own challenges,” Barzilay agrees. “Most likely, a successful decipherment would require one to adjust the method for the peculiarities of a language.” But, she points out, the decipherment of Ugaritic took years and relied on some happy coincidences — such as the discovery of an axe that had the word “axe” written on it in Ugaritic. “The output of our system would have made the process orders of magnitude shorter,” she says. Indeed, Snyder and Barzilay don’t suppose that a system like the one they designed with Knight would ever replace human decipherers. “But it is a powerful tool that can aid the human decipherment process,” Barzilay says. Moreover, a variation of it could also help expand the versatility of translation software. Many online translators rely on the analysis of parallel texts to determine word correspondences: They might, for instance, go through the collected works of Voltaire, Balzac, Proust and a host of other writers, in both English and French, looking for consistent mappings between words. “That’s the way statistical translation systems have worked for the last 25 years,” Knight says. But not all languages have such exhaustively translated literatures: At present, Snyder points out, Google Translate works for only 57 languages. The techniques used in the decipherment system could be adapted to help build lexicons for thousands of other languages. “The technology is very similar,” says Knight, who works on machine translation. “They feed off each other.

New Math in HIV Fight
by Mark Schoofs / June 21, 2011

Scientists using a powerful mathematical tool previously applied to the stock market have identified an Achilles heel in HIV that could be a prime target for AIDS vaccines or drugs. The research adds weight to a provocative hypothesis—that an HIV vaccine should avoid a broadside attack and instead home in on a few targets. Indeed, there is a rare group of patients who naturally control HIV without medication, and these “elite controllers” most often assail the virus at precisely this vulnerable area. “This is a wonderful piece of science, and it helps us understand why the elite controllers keep HIV under control,” said Nobel laureate David Baltimore. Bette Korber, an expert on HIV mutation at the Los Alamos National Laboratory, said the study added “an elegant analytical strategy” to HIV vaccine research. “What would be very cool is if they could apply it to hepatitis C or other viruses that are huge pathogens—Ebola virus, Marburg virus,” said Mark Yeager, chair of the physiology department at the University of Virginia School of Medicine. “The hope would be there would be predictive power in this approach.” Drs. Baltimore, Korber and Yeager weren’t involved in the new research.

One of the most vexing problems in HIV research is the virus’s extreme mutability. But the researchers found that there are some HIV sectors, or groups of amino acids, that rarely make multiple mutations. Scientists generally believe that the virus needs to keep such regions intact. Targeting such sectors could trap HIV: If it mutated, it would disrupt its own internal machinery and sputter out. If it didn’t mutate, it would lie defenseless against a drug or vaccine attack. The study was conducted at the Ragon Institute, a joint enterprise of Massachusetts General Hospital, the Massachusetts Institute of Technology and Harvard University. The institute was founded in 2009 to convene diverse groups of scientists to work on HIV/AIDS and other diseases.

Two of the study’s lead authors aren’t biologists. Arup Chakraborty is a professor of chemistry and chemical engineering at MIT, though he has worked on immunology, and Vincent Dahirel is an assistant professor of chemistry at the Université Pierre et Marie Curie in Paris. They collaborated with Bruce Walker, a longtime HIV researcher who directs the Ragon Institute. Their work was published Monday in the Proceedings of the National Academy of Sciences. To find the vulnerable sectors in HIV, Drs. Chakraborty and Dahirel reached back to a statistical method called random matrix theory, which has also been used to analyze the behavior of stocks. While stock market sectors are already well defined, the Ragon researchers didn’t necessarily know what viral sectors they were looking for. Moreover, they wanted to take a fresh look at the virus. So they defined the sectors purely mathematically, using random matrix theory to sift through most of HIV’s genetic code for correlated mutations, without reference to previously known functions or structures of HIV. The segment that could tolerate the fewest multiple mutations was dubbed sector 3 on an HIV protein known as Gag. Previous research by Dr. Yeager and others had shown that the capsid, or internal shell, of the virus has a honeycomb structure. Part of sector 3, it turns out, helps form the edges of the honeycomb. If the honeycomb suffered too many mutations, it wouldn’t interlock, and the capsid would collapse.

For years, Dr. Walker had studied rare patients, about one in 300, who control HIV without taking drugs. He went back to see what part of the virus these “elite controllers” were attacking with their main immune-system assault. The most common target was sector 3. Dr. Walker’s team found that even immune systems that fail to control HIV often attack sector 3, but they tend to devote only a fraction of their resources against it, while wasting their main assault on parts of the virus that easily mutate to evade the attack. That suggested what the study’s authors consider the paper’s most important hypothesis: A vaccine shouldn’t elicit a scattershot attack, but surgical strikes against sector 3 and similarly low-mutating regions of HIV. “The hypothesis remains to be tested,” said Dan Barouch, a Harvard professor of medicine and a colleague at the Ragon institute. He is planning to do just that, with monkeys. Others, such as Oxford professor Sir Andrew McMichael, are also testing it. The Ragon team’s research focused on one arm of the immune system—the so-called killer T-cells that attack other cells HIV has already infected. Many scientists believe a successful HIV vaccine will also require antibodies that attack a free-floating virus. Dr. Chakraborty is teaming up with Dennis Burton, an HIV antibody expert at the Scripps Research Institute in La Jolla, Calif., to apply random matrix theory to central problems in antibody-based vaccines.

Originally developed more than 50 years ago to describe the energy levels of atomic nuclei, the theory is turning up in everything from inflation rates to the behaviour of solids. So much so that many researchers believe that it points to some kind of deep pattern in nature that we don’t yet understand. “It really does feel like the ideas of random matrix theory are somehow buried deep in the heart of nature,” says electrical engineer Raj Nadakuditi of the University of Michigan, Ann Arbor.

How Random-Matrix Theory Found Its Way Into a Promising AIDS Study
by Mark Schoofs / June 21, 2011

Random-matrix theory is a mathematical method for finding hidden correlations within masses of data. It doesn’t just find pairs, a relatively easy task, but can detect groups of many correlated units and even groups that change over time, adding and losing members. The theory was developed in the middle of the 20th century by Nobel laureate Eugene Wigner and others to address problems in nuclear physics. In the 1990s and early 2000s, physicists applied it to the stock market. A major event such as a severe recession will act on almost all stocks together, a correlation so broad it has little use. At the other extreme are millions of random correlations – stocks rising or falling together purely by chance. But some stocks, such as those of car companies and parts makers, act in true correlation.

Sure enough, random-matrix theory filtered out the “noise” of random correlations and overwhelming events to reveal such genuine correlations. One of the authors of that finding, physicist Parameswaran Gopikrishnan, working with Boston University physics professor H. Eugene Stanley, is now a managing director at Goldman Sachs Group Inc. “Of course,” Dr. Stanley said, “we know those sectors are correlated anyway.” But his team found the sectors purely by using random-matrix theory “without looking at the innards of the companies,” he explained. That proved the power of the theory, which Dr. Stanley believes could act as an early-warning system for stock-market analysts. If one company in a sector “wanders away and stops being correlated, that would tell you something is going on” in that firm. Arup Chakraborty, a chemistry and chemical engineering professor at MIT, knew of random-matrix theory from the stock market work and from a scientific colleague who had used it to analyze enzymes, though not in HIV. Dr. Chakraborty thought it could help find sectors of HIV that rarely undergo multiple mutations – and it did.

The deep law that shapes our reality
by Mark Buchanan / 07 April 2010

Suppose we had a theory that could explain everything. Not just atoms and quarks but aspects of our everyday lives too. Sound impossible? Perhaps not. It’s all part of the recent explosion of work in an area of physics known as random matrix theory. Originally developed more than 50 years ago to describe the energy levels of atomic nuclei, the theory is turning up in everything from inflation rates to the behaviour of solids. So much so that many researchers believe that it points to some kind of deep pattern in nature that we don’t yet understand. “It really does feel like the ideas of random matrix theory are somehow buried deep in the heart of nature,” says electrical engineer Raj Nadakuditi of the University of Michigan, Ann Arbor.

All of this, oddly enough, emerged from an effort to turn physicists’ ignorance into an advantage. In 1956, when we knew very little about the internal workings of large, complex atomic nuclei, such as uranium, the German physicist Eugene Wigner suggested simply guessing. Quantum theory tells us that atomic nuclei have many discrete energy levels, like unevenly spaced rungs on a ladder. To calculate the spacing between each of the rungs, you would need to know the myriad possible ways the nucleus can hop from one to another, and the probabilities for those events to happen. Wigner didn’t know, so instead he picked numbers at random for the probabilities and arranged them in a square array called a matrix.

The matrix was a neat way to express the many connections between the different rungs. It also allowed Wigner to exploit the powerful mathematics of matrices in order to make predictions about the energy levels. Bizarrely, he found this simple approach enabled him to work out the likelihood that any one level would have others nearby, in the absence of any real knowledge. Wigner’s results, worked out in a few lines of algebra, were far more useful than anyone could have expected, and experiments over the next few years showed a remarkably close fit to his predictions. Why they work, though, remains a mystery even today. What is most remarkable, though, is how Wigner’s idea has been used since then. It can be applied to a host of problems involving many interlinked variables whose connections can be represented as a random matrix.

The first discovery of a link between Wigner’s idea and something completely unrelated to nuclear physics came about after a chance meeting in the early 1970s between British physicist Freeman Dyson and American mathematician Hugh Montgomery. Montgomery had been exploring one of the most famous functions in mathematics, the Riemann zeta function, which holds the key to finding prime numbers. These are numbers, like 2, 3, 5 and 7, that are only divisible by themselves and 1. They hold a special place in mathematics because every integer greater than 1 can be built from them. In 1859, a German mathematician called Bernhard Riemann had conjectured a simple rule about where the zeros of the zeta function should lie. The zeros are closely linked to the distribution of prime numbers.

Mathematicians have never been able to prove Riemann’s hypothesis. Montgomery couldn’t either, but he had worked out a formula for the likelihood of finding a zero, if you already knew the location of another one nearby. When Montgomery told Dyson of this formula, the physicist immediately recognised it as the very same one that Wigner had devised for nuclear energy levels. To this day, no one knows why prime numbers should have anything to do with Wigner’s random matrices, let alone the nuclear energy levels. But the link is unmistakable. Mathematician Andrew Odlyzko of the University of Minnesota in Minneapolis has computed the locations of as many as 1023 zeros of the Riemann zeta function and found a near-perfect agreement with random matrix theory. The strange descriptive power of random matrix theory doesn’t stop there. In the last decade, it has proved itself particularly good at describing a wide range of messy physical systems.

Universal law?
Recently, for example, physicist Ferdinand Kuemmeth and colleagues at Harvard University used it to predict the energy levels of electrons in the gold nanoparticles they had constructed. Traditional theories suggest that such energy levels should be influenced by a bewildering range of factors, including the precise shape and size of the nanoparticle and the relative position of the atoms, which is considered to be more or less random. Nevertheless, Kuemmeth’s team found that random matrix theory described the measured levels very accurately (arxiv.org/abs/0809.0670). A team of physicists led by Jack Kuipers of the University of Regensburg in Germany found equally strong agreement in the peculiar behaviour of electrons bouncing around chaotically inside a quantum dot – essentially a tiny box able to trap and hold single quantum particles (Physical Review Letters, vol 104, p 027001). The list has grown to incredible proportions, ranging from quantum gravity and quantum chromodynamics to the elastic properties of crystals. “The laws emerging from random matrix theory lay claim to universal validity for almost all quantum systems. This is an amazing fact,” says physicist Thomas Guhr of the Lund Institute of Technology in Sweden.

Random matrix theory has got mathematicians like Percy Deift of New York University imagining that there might be more general patterns there too. “This kind of thinking isn’t common in mathematics,” he notes. “Mathematicians tend to think that each of their problems has its own special, distinguishing features. But in recent years we have begun to see that problems from diverse areas, often with no discernible connections, all behave in a very similar way.” In a paper from 2006, for example, he showed how random matrix theory applies very naturally to the mathematics of certain games of solitaire, to the way buses clump together in cities, and the path traced by molecules bouncing around in a gas, among others. The most important question, perhaps, is whether there is some deep theory behind both physics and mathematics that explains why random matrices seem to capture essential truths about reality. “There must be some reason, but we don’t yet know what it is,” admits Nadakuditi. In the meantime, random matrix theory is already changing how we look at random systems and try to understand their behaviour. It may possibly offer a new tool, for example, in detecting small changes in global climate.

Back in 1991, an international scientific collaboration conducted what came to be known as the Heard Island Feasibility Test. Spurred by the idea that the transmission of sound through the world’s oceans might provide a sensitive test of rising temperatures, they transmitted a loud humming sound near Heard Island in the Indian Ocean and used an array of sensors around the world to pick it up. Repeating the experiment 20 years later could yield valuable information on climate change. But concerns over the detrimental effects of loud sounds on local marine life mean that experiments today have to be carried out with signals that are too weak to be detected by ordinary means. That’s where random matrix theory comes in.

Over the past few years, Nadakuditi, working with Alan Edelman and others at the Massachusetts Institute of Technology, has developed a theory of signal detection based on random matrices. It is specifically attuned to the operation of a large array of sensors deployed globally. “We have found that you can in principle use extremely weak sounds and still hope to detect the signal,” says Nadakuditi. Others are using random matrix theory to do surprising things, such as enabling light to pass through apparently impenetrable, opaque materials. Last year, physicist Allard Mosk of the University of Twente in the Netherlands and colleagues used it to describe the statistical connections between light that falls on an object and light that is scattered away. For an opaque object that scatters light very well, he notes, these connections can be described by a totally random matrix.

What comes up are some strange possibilities not suggested by other analyses. The matrices revealed that there should be what Mosk calls “open channels” – specific kinds of waves that, instead of being reflected, would somehow pass right through the material. Indeed, when Mosk’s team shone light with a carefully constructed wavefront through a thick, opaque layer of zinc oxide paint, they saw a sharp increase in the transmission of light.
Random matrix theory comes up with strange possibilities not suggested by other analyses, which are then borne out by experiments

Still, the most dramatic applications of random matrix theory may be yet to come. “Some of the main results have been around for decades,” says physicist Jean-Philippe Bouchaud of the École Polytechnique in Paris, France,” but they have suddenly become a lot more important with the handling of humungous data sets in so many areas of science.” In everything from particle physics and astronomy to ecology and economics, collecting and processing enormous volumes of data has become commonplace. An economist may sift through hundreds of data sets looking for something to explain changes in inflation – perhaps oil futures, interest rates or industrial inventories. Businesses such as Amazon.com rely on similar techniques to spot patterns in buyer behaviour and help direct their advertising. While random matrix theory suggests that this is a promising approach, it also points to hidden dangers. As more and more complex data is collected, the number of variables being studied grows, and the number of apparent correlations between them grows even faster. With enough variables to test, it becomes almost certain that you will detect correlations that look significant, even if they aren’t.

Curse of dimensionality
Suppose you have many years’ worth of figures on a large number of economic indices, including inflation, employment and stock market prices. You look for cause-and-effect relationships between them. Bouchaud and his colleagues have shown that even if these variables are all fluctuating randomly, the largest observed correlation will be large enough to seem significant. This is known as the “curse of dimensionality”. It means that while a large amount of information makes it easy to study everything, it also makes it easy to find meaningless patterns. That’s where the random-matrix approach comes in, to separate what is meaningful from what is nonsense.

In the late 1960s, Ukrainian mathematicians Vladimir Marcenko and Leonid Pastur derived a fundamental mathematical result describing the key properties of very large, random matrices. Their result allows you to calculate how much correlation between data sets you should expect to find simply by chance. This makes it possible to distinguish truly special cases from chance accidents. The strengths of these correlations are the equivalent of the nuclear energy levels in Wigner’s original work. Bouchaud’s team has now shown how this idea throws doubt on the trustworthiness of many economic predictions, especially those claiming to look many months ahead. Such predictions are, of course, the bread and butter of economic institutions. But can we believe them?

To find out, Bouchaud and his colleagues looked at how well US inflation rates could be explained by a wide range of economic indicators, such as industrial production, retail sales, consumer and producer confidence, interest rates and oil prices. Using figures from 1983 to 2005, they first calculated all the possible correlations among the data. They found what seem to be significant results – apparent patterns showing how changes in economic indicators at one moment lead to changes in inflation the next. To the unwary observer, this makes it look as if inflation can be predicted with confidence. But when Bouchaud’s team applied Marcenko’s and Pastur’s mathematics, they got a surprise. They found that only a few of these apparent correlations can be considered real, in the sense that they really stood out from what would be expected by chance alone. Their results show that inflation is predictable only one month in advance. Look ahead two months and the mathematics shows no predictability at all. “Adding more data just doesn’t lead to more predictability as some economists would hope,” says Bouchaud.

In recent years, some economists have begun to express doubts over predictions made from huge volumes of data, but they are in the minority. Most embrace the idea that more measurements mean better predictive abilities. That might be an illusion, and random matrix theory could be the tool to separate what is real and what is not. Wigner might be surprised by how far his idea about nuclear energy levels has come, and the strange directions in which it is going, from universal patterns in physics and mathematics to practical tools in social science. It’s clearly not as simplistic as he initially thought.

brain image
This study found reduced connectivity between an area of prefrontal cortex (PFC, red) and the amygdala (blue). The white matter pathway connecting the two structures (the uncinate fasciculus) is shown in green.

Psychopaths’ Brains Show Differences in Structure and Function

Images of prisoners’ brains show important differences between those who are diagnosed as psychopaths and those who aren’t, according to a new study led by University of Wisconsin-Madison researchers. The results could help explain the callous and impulsive antisocial behavior exhibited by some psychopaths.The study showed that psychopaths have reduced connections between the ventromedial prefrontal cortex (vmPFC), the part of the brain responsible for sentiments such as empathy and guilt, and the amygdala, which mediates fear and anxiety.

Two types of brain images were collected. Diffusion tensor images (DTI) showed reduced structural integrity in the white matter fibers connecting the two areas, while a second type of image that maps brain activity, a functional magnetic resonance image (fMRI), showed less coordinated activity between the vmPFC and the amygdala. “This is the first study to show both structural and functional differences in the brains of people diagnosed with psychopathy,” says Michael Koenigs, assistant professor of psychiatry in the University of Wisconsin School of Medicine and Public Health. “Those two structures in the brain, which are believed to regulate emotion and social behavior, seem to not be communicating as they should.” The study, which took place in a medium-security prison in Wisconsin, is a unique collaborative between three laboratories, UW-Madison psychology Professor Joseph Newman has had a long term interest in studying and diagnosing those with psychopathy and has worked extensively in the Wisconsin corrections system. Dr. Kent Kiehl, of the University of New Mexico and the MIND Research Network, has a mobile MRI scanner that he brought to the prison and used to scan the prisoners’ brains. Koenigs and his graduate student, Julian Motzkin, led the analysis of the brain scans.

The video shows interactions between microglia (yellow) and dendritic spines (green) in the brain of a living mouse. Each frame is taken 5 minutes apart. The cell body of the microglia in the upper right corner is stable throughout the imaging session, but the microglial processes (looking like tentacles) are extremely dynamic, perpetually changing their morphology and dynamic interactions with small and transient dendritic spines over a span of minutes. http://www.med.wisc.edu/news-events/images-and-video-for-the-media/25328

The study compared the brains of 20 prisoners with a diagnosis of psychopathy with the brains of 20 other prisoners who committed similar crimes but were not diagnosed with psychopathy. “The combination of structural and functional abnormalities provides compelling evidence that the dysfunction observed in this crucial social-emotional circuitry is a stable characteristic of our psychopathic offenders,” Newman says. “I am optimistic that our ongoing collaborative work will shed more light on the source of this dysfunction and strategies for treating the problem.” Newman notes that none of this work would be possible without the extraordinary support provided by the Wisconsin Department of Corrections, which he called “the silent partner in this research.” He says the DOC has demonstrated an unprecedented commitment to supporting research designed to facilitate the differential diagnosis and treatment of prisoners. The study, published in the most recent Journal of Neuroscience, builds on earlier work by Newman and Koenigs that showed that psychopaths’ decision-making mirrors that of patients with known damage to their ventromedial prefrontal cortex (vmPFC). This bolsters evidence that problems in that part of the brain are connected to the disorder. “The decision-making study showed indirectly what this study shows directly – that there is a specific brain abnormality associated with criminal psychopathy,” Koenigs adds.

UW-Madison Psychiatry imaging study finds brains of psychopaths are different
by Matt Hrodey  /  11/22/2011

The Koenigs Lab, an appendage of the University of Wisconsin Department of Psychiatry, says something about the multidisciplinary nature of neuroscience. Named for Michael Koenigs, an assistant professor of psychiatry, the lab includes a postdoctoral researcher with degrees in psychology and comparative religion, graduate students with backgrounds in biology, philosophy and English, and a scientist trained in applied math. Centered on the mind and nervous system, neuroscience is exploding, and there’s practically no topic it won’t take on, be it Shakespeare, meditation or consciousness itself. Or psychopathy.

In a paper to be published in the Nov. 30 Journal of Neuroscience, Koenigs, along with veteran UW psychopathy researcher Joseph Newman, will unveil new evidence of a physical basis for the disorder. In the study, Koenigs and Newman use brain scans of 40 inmates (20 psychopaths and 20 others) from Fox Lake Correctional Institution in Fox Lake, Wisconsin. In the scans of psychopathic brains, the researchers discovered poor connections between an important brain segment — the “ventromedial prefrontal cortex” (VMPFC) — and another crucial to emotional processing, the almond-shaped amygdala. The study will be the largest yet published that examines this link, according to Koenigs. Researchers used two types of brain scans: one testing the integrity of “white matter” structures connecting the VMPFC and the amygdala, and another tesing how well they communicate. Both types of scans found a weakened link in the brains of psychopaths.

Better understanding such abnormalities could, one day, reorder how the justice system responds to criminals who have them. “Can we hold them as accountable as someone who doesn’t have these abnormalities?” Koenigs asks. Scientists have studied the connection between the VMPFC and amygdala before. In one experiment using rodents, scientists found that stimulating the VMPFC suppressed the amygdala. Koenigs primarily studies brain injuries, particularly those in the VMPFC, where the brain is believed to regulate emotion, process threats, guide decision-making and direct social behavior. Damage to this segment, located just behind the forehead in the frontal lobes, tends to make patients more aggressive, irritable and less sensitive to others. “They’re not the same person they used to be,” Koenigs says. “They develop very striking personality changes reminiscent of psychopathy.”

Is a VMPFC deficiency to blame for psychopathy? It’s not clear. And scientists don’t know if the VMPFC is failing to regulate the amygdala or if the amydala is failing to send crucial emotional feedback to the VMPFC. “Normally, considering a decision [to rob someone] and the harm you would inflict would be marked with a negative emotional state,” says Koenigs. But in psychopaths, this affect is flat. To do their study at Fox Lake, Koenigs and Newman enlisted a mobile MRI lab run by Kent Kiehl, an associate professor of psychology at the University of New Mexico. The lab, pulled by a tractor trailer, brings the scanner to the inmates. Across the field of neuroscience, researchers are rapidly exploiting the powers of MRI scanning, particularly “functional” scanning, which tracks blood flow in the brain. This flow, because it is directed to busy neurons, is a precise indicator of brain activity. The new study is Newman’s first foray into brain imaging. “There’s a very strong bias toward using brain measurements,” he says, “and there’s been a lot of wonderful progress. People want to see how far we can go.”

Psychopathy is not as rare as some might believe. According to researchers, psychopaths make up an estimated 1% of the U.S. population and between 10% to 20% of the country’s prisoners. In his 30 years of studying psychopathy, Newman has theorized the existence of an “attention bottleneck” in the psychopathic mind that prevents it from fully receiving emotional and other inhibitory signals that say, “Stop! Reconsider! Reevaluate!” The conventional theory on psychopaths is that they lack emotion, be it fear, empathy or guilt, that would otherwise inform decision-making. Newman doesn’t deny that but insists on the importance of attention. “It feels like I’m trying to identify a learning disability,” he says. Our minds unconsciously monitor us. It happens in secret. Our conscious minds don’t know of it until the unconscious sounds an alarm — such as when a nagging suspicion of “having forgotten something” turns out to be true (the oven is still on; the keys were left on the car seat). The psychopathic brain may be very bad at automatically diverting attention to these types of cues if the psychopath is locked into “goal-driven” behavior, a kind of tunnel vision. Such an impairment, if it exists, doesn’t necessarily lead to crime. “Environmental factors are critical,” says Newman. They could be parental abuse, substance abuse or socioeconomic disadvantage. But once classified as a psychopath, an offender is two to five times more likely to reoffend than one who isn’t.

Newman tested his “attention bottleneck” theory in a study published earlier this year. In that study, 87 maximum-security inmates, some classified as psychopaths, sat down in front of computers. Two things appeared on the screen: a square, either red or green, and a letter, either uppercase or lowercase. In some of the trials, researchers startled inmates with a low-intensity shock after showing a red square. (Prisoners were told of the mild “buzzes” before they volunteered.) Each was shocked a total of 24 times, always after a red square. Then, to conclude the trials, the computer asked the prisoners to identify either the case of the letter or the color of the box. The human body, when conditioned to fear something, will startle at its appearance. This is called “fear-potentiated startle.” In the experiment, the red box primed the inmates to startle upon receiving the shock, and they did — with one major exception. In trials where psychopaths first saw the letter, followed by a red square, their startle was greatly diminished. Newman and the other researchers, Arielle Baskin-Sommers, a graduate student at UW-Madison, and John Curtin, a psychology professor, concluded that by presenting the letter first — thereby making the red square “secondary information that is not goal relevant” — the psychopaths fell victim to the “attention bottleneck” as theorized by Newman. They saw the square, but its meaning was not fully absorbed because the letter (and its case) had already won their attention.

There’s growing speculation today that neuroscience could revolutionize the U.S. criminal justice system, overthrowing the old precept of culpability. One indication of the promise of this growing field is a new dual degree program at UW-Madison that will train students in both neuroscience and the law. The “Neuroscience and the Law” track, part of the broader Neuroscience & Public Policyprogram, will allow students to earn a J.D. degree in law and a Ph.D. degree in neuroscience. Applications to join the new track’s first class come due this December. Professor Ron Kalil, a neuroscientist who studies brain injuries and the brain’s innate ability to repair itself, says the new program grew out of a 2010 meeting he had, over coffee, with Pilar Ossorio, an associate professor of law and bioethics. The two left with a “let’s do this” attitude, according to Kalil, but getting university approval for the new track didn’t happen overnight. To make the program official, they needed the approval of four university committees. They succeeded, adding “Neuroscience and the Law” to the existing tracks combining neuroscience and public policy and neuroscience and international public policy. Of neuroscience’s broad range, Kalil says, “At one end you have the study of molecules and proteins that make up parts of neurons, and at the other, the field tries to wrestle with issues that have been on the table since people started to think of themselves as human.” One of these is how to respond to crime, and what punishment is appropriate. “There are a lot of people who are not insane, but they’re not normal,” he says. “Where do we draw the line?”

Why (Some) Psychopaths Make Great CEOs
by Jeff Bercovici / Jun 14 2011

British journalist Jon Ronson immersed himself in the world of mental health diagnosis and criminal profiling to understand what makes some people psychopaths — dangerous predators who lack the behavioral controls and tender feelings the rest of us take for granted. Among the things he learned while researching his new book, “The Psychopath Test: A Journey Through the Madness Industry”: the incidence of psychopathy among CEOs is about 4 percent, four times what it is in the population at large. I spoke with him recently about what that means and its implications for the business world and wider society.

Q. Are we really to understand that there’s some connection between what makes people psychopaths and what makes them CEO material?
A. At first I was really skeptical because it seemed like an easy thing to say, almost like a conspiracy theorist’s type of thing to say. I remember years and years ago a conspiracy theorist telling me the world was ruled by blood-drinking, baby-sacrificing lizards. These psychologists were essentially saying the same thing. Basically, when you get them talking, these people [ie. psychopaths] are different than human beings. They lack the things that make you human: empathy, remorse, loving kindness. So at first I thought this might just be psychologists feeling full of themselves with their big ideological notions. But then I met Al Dunlap. [That would be “Chainsaw” Al Dunlap, former CEO of Sunbeam and notorious downsizer.] He effortlessly turns the psychopath checklist into “Who Moved My Cheese?” Many items on the checklist he redefines into a manual of how to do well in capitalism. There was his reputation that he was a man who seemed to enjoy firing people, not to mention the stories from his first marriage — telling his first wife he wanted to know what human flesh tastes like, not going to his parents’ funerals. Then your realize that because of this dysfunctional capitalistic society we live in those things were positives. He was hailed and given high-powered jobs, and the more ruthlessly his administration behaved, the more his share price shot up.

Q. So you can just go down the list of Fortune 500 CEOs and say, “psychopath, psychopath, psychopath…”
A. Well, no. Dunlap was an exceptional figure, wasn’t he? An extreme figure. I think my book offers really good evidence that the way that capitalism is structured really is a physical manifestation of the brain anomaly known as psychopathy. However, I woudn’t say every Fortune 500 chief is a psychopath. That would turn me into an ideologue and I abhor ideologues.

Q. Is it an either/or thing? It seems to me, thinking about it, that a lot of the traits on the checklist would be be useful in a corporate ladder-climbing situation. So maybe there are a lot of CEOs who simply have some psychopathic tendencies.
A. It is a spectrum, but there’s a cutoff point. If you’re going by the Hare checklist [the standard inventory used in law enforcement, devised by leading researcher Robert Hare], where the top score is 40, the average anxiety-ridden business failure like me — although the fact that my book just made the Times best sellers list makes it difficult to call myself that — would score a 4 or 5. Somebody you have to be wary of would be in early 20s and a really hard core damaged person, a really dangerous psychopath, would score around a 30. In law the cutoff is 29. There are absolutes in psychopathy and the main absolute is a literal absence of empathy. It’s just not there. In higher-scoring psychopaths, what grows in the vacant field where that empathy should be is a joy in manipulating people, a lack of remorse, a lack of guilt. If you’ve got a little bit of empathy, you’re kind of not a psychopath.

Q. So maybe there’s a sweet spot? A point on the spectrum somewhere short of full-blown psychopathy that’s most conducive to success in business.
A. That’s possible. Obviously there are items on the checklist you don’t want to have if you’re a boss. You don’t want poor behavioral controls. It’d be better if you don’t have promiscuous behavior. It’d be better if you don’t have serious behavioral problems in childhood, because that will eventually come out. But you do want lack of empathy, lack of remorse, glibness, superficial charm, manipulativeness. I think the other positive traits for psychopaths in business is need for stimulation, proneness to boredom. You want somebody who can’t sit still, who’s constantly thinking about how to better things. A really interesting question is whether psychopathy can be a positive thing. Some psychologists would say yes, that there are certain attributes like coolness under pressure, which is sort of a fundamental positive. But Robert Hare would always say no, that in the absence of empathy, which is the definition in psychology of a psychopath, you will always get malevolence. Basically, high-scoring psychopaths can be brilliant bosses but only ever for short term. Just like Al Dunlap, they always want to make a killing and move on. And then you’ve got this question of what came first? Is society getting more and more psychopathic in its kind of desire for short-term killings? Is that because we kind of admire psychopaths in all their glib, superficial charm and ruthlessness?

Q. There’s a certain sour grapes aspect to accusing CEOs of being psychopaths. It’s very tempting to look at anyone more successful than you are and say, “It must be because he’s a monster.”
A. There’s a terribly seductive power in becoming a psychopath stalker. It can really dehumanize you. I can look at, say, Dominique Strauss Kahn, who, if one assumes that what one is hearing about him is true, certainly he hits a huge amount of items on the checklist — the $30,000 suits, the poor behavioral controls, the impulsivity, the promiscuous sexual behavior. But of course when you say this you’re in terrible danger of being seduced by the checklist, which I really like to add as a caveat. It kind of turns you into a bit of a psychopath yourself in that that you start to shove people into that box. It robs you of empathy and your connection to human beings. Which is why people like Robert Hare are kind of useful. I’m against the way that people like me can be seduced into misusing the checklist, but I’m not against the checklist.

by Michael Steinberger / December 12, 2004

Ever wonder what leads a lavishly compensated C.E.O. to cheat, steal and lie? Perhaps he’s a psychopath, and now there is a test, the B-Scan 360, that can help make that determination. The B-Scan was conceived by Paul Babiak, an industrial psychologist, and Robert Hare, the creator of the standard tool for diagnosing psychopathic features in prison inmates. The B-Scan is the first formalized attempt to uncover similar tendencies in captains of industry, and it speaks to a growing suspicion that psychopaths may be especially adept at scaling the corporate ladder.

Indeed, Babiak and Hare could not have chosen a more propitious moment to roll out the B-Scan, which is now in the trial stage. The recent rash of damaging corporate scandals — combined with legislation making boards far more liable for executive malfeasance — has given companies good reason to screen current employees more rigorously. According to Babiak and Hare, white-collar psychopaths are not apt to become serial rapists or murderers. Rather, they are prone to being ”subcriminal” psychopaths: smooth-talking, energetic individuals who easily charm their way into jobs and promotions but who are also exceedingly manipulative, narcissistic and ruthless. The purpose of the B-Scan is to smoke out these “snakes in suits”. The individual being evaluated does not actually take the test. Instead, it is given to his or her superiors, subordinates and peers. They rate the subject in four broad categories — organizational maturity, personal style, emotional style and social style — and 16 subcategories, like reliability, honesty and sincerity.

Babiak and Hare say that decisions to promote or dismiss ought not to be made on the basis of the B-Scan alone and that it is possible, with good coaching and training, to turn a talented executive with mild psychopathic tendencies into an effective manager. They acknowledge too that strong corporate leadership may require a certain degree of guile, egoism and callousness. But they point out that the frenzied nature of modern business — the constant downsizing, the relentless merging and acquiring — provides a very fertile environment for havoc-wreaking psychopaths, who thrive on chaos and risk-taking. As Hare put it in one interview, ”If I couldn’t study psychopaths in prison, I would go down to the Stock Exchange.”

Paul Babiak
email : Inquiry [at] PaulBabiak [dot] com

Robert Hare
email : contact [at] hare [dot] org

Psychopathy Scales


“Dr. Hare has spent over 35 years researching psychopathy and is the developer of theHare Psychopathy Checklist-Revised (PCL-R), and a co-author of its derivatives, thePsychopathy Checklist: Screening Version (PCL:SV), the P-Scan, the Psychopathy Checklist: Youth Version (PCL:YV), and the Antisocial Process Screening Device(APSD). He is also a co-author of the Guidelines for a Psychopathy Treatment Program. The Hare Psychopathy Checklist-Revised, with demonstrated reliability and validity, is rapidly being adopted worldwide as the standard instrument for researchers and clinicians. The PCL-R and PCL:SV are strong predictors of recidivism, violence and response to therapeutic intervention. They play an important role in most recent risk-for-violence instruments. The PCL-R was reviewed in Buros Mental Measurements Yearbook (1995), as being the “state of the art” both clinically and in research use. In 2005, the Buros Mental Measurements Yearbook review listed the PCL-R as “a reliable and effective instrument for the measurement of psychopathy and is considered the ‘gold standard’ for measurement of psychopathy.”

Bison skull pile, 1870s

Catching the corporate psychopath
by Stuart Fagg / 15 June 2005

Rodney Adler, Ray Williams, Bernie Ebbers. These men have much in common. For a start they were once all hailed as successful businessmen and players of acumen, and secondly they are all now behind bars for their roles in the collapse of their companies. Of course they are not the only ones paying for their misdemeanours – there are plenty of share and policy holders who will attest to that. They also have one final thing in common – they all exhibit the behaviours of corporate psychopaths. According to Dr Robert Hogan, a US expert in personality profiling, however, it would seem that the likes of Adler are aberrations in the business world. But corporate psychopaths are far from unusual in the corporate world. By Hogan’s reckoning, the result of decades of research, incompetent and potentially damaging management accounts for some 60-70 per cent of the total pool in the US. When he brought these views to bear initially in the early 1990s, they were not popular and were dismissed by many that refused to believe that there were that many potential corporate psychopaths in US business. However, these days, and particularly having seen the damage wreaked by individuals after the scandals at Enron, WorldCom, OneTel and HIH, boards of directors and the share market are demanding more ethical executives. With the potential for increased liability under the Corporations Act, this trend may continue going forward. All well and good, but what is the impact of these corporate psychopaths? After all, some of the qualities that define such people also define some of the most successful people in business. “Researchers looked at Fortune 1000 companies that had 15 years of performance right at the average of their industry, and then a change and 15 subsequent years of sustained performance significantly above the average for the industry. Out of 1,000 companies they found 11,” Hogan said. “They investigated the 11 companies and found that the constant was the CEO. All 11 CEOs were understated and humble and that’s a stake in the heart for the theory of the celebrity CEO or charismatic leader.”

While background checks and screening are gaining popularity in Australian business, and in some cases being applied at higher executive levels, personality profiling remains a relatively unexplored concept in Australia. However, that may change. The Australian Prudential Regulation Authority, for example, is set to publish proposals for standards governing the fitness and propriety of responsible persons in financial institutions. The proposed standards are designed to weed out executives who have been declared bankrupt, failed to manage personal debts or held responsibility in a failed institution. Additionally anyone with a civil or criminal conviction related to dishonesty in dealings with financial institutions will also be barred. “The proposals are designed to reflect community expectations about persons who fill positions of responsibility in these industries and will set minimum benchmarks for people in, or wishing to enter, these industries at director, senior management or advisory level,” said Dr John Laker, APRA chairman. Traditionally, APRA has always focussed on the institution it is regulating, rather than the individuals running the institution. But, recent events in Australia and internationally have highlighted the importance of enuring that people in positions of power at companies are subject to the same scrutiny as the company itself. With regulated entities being required to develop their own policies, personality assessment may become more commonplace in sectors such as the insurance industry. But there is something of a grey area in the assessments. For example, financial markets traders must display some of the more undesirable qualities –ruthlessness, overt smartness and a tendency to gamble – for senior management to succeed in their positions. “We have a lot of data on traders and as a group they are real smart and really crazy,” said Hogan. “But don’t let them into management positions. People like that – Bill Clinton is a great example – tend to self nominate into leadership roles. They think they’re so hot they want to be in charge.”

Background checks and screening may not, however, detect these characteristics and head off the appointment of a potentially damaging executive. “The really bad guys will sail through a background check and will do really well in interviews. They do really well in assessment centres. The really dangerous ones are really smart, really charming and really fast on their feet and people love them.” This is where personality assessment earns its stripes, according to Hogan. Through developing his assessment system, Hogan has amassed an impressive data repository from the 3 million tests that have been carried out using his methodology. This data accurately tracks personality trends in business, and once companies see the data, said Hogan, it’s a relatively easy sell. But what happens if the CEO of the company is the corporate psychopath? “That’s our worst nightmare,” he told Human Resources. “When you assess the management team and see all these problems come from them, how can you fix that? But if you can find a company that’s willing to pay attention to data it’s an easy deal for us.”


“Picked by the board of Scott Paper Co. as the man to turn the struggling company around, Dunlap earned his nickname by slicing 11,000 employees. When Scott merged with Kimberly-Clark, Dunlap’s payoff was estimated at more than $100 million. Such scenarios are familiar. So are the debates over where to draw the line between painful-but-necessary restructuring and cold-hearted recklessness. Yet Dunlap stood out for the obvious joy he took in slamming his detractors as purveyors of “nonsense,” “rubbish,” and “socialism.” Chainsaw Al was the middle finger of the free market’s invisible hand.

Dunlap’s memoir-cum-manifesto, Mean Business, roughly coincided with his next CEO star turn, which was also to be his last. Sunbeam’s stock surged on the news that the Chainsaw was coming; massive workforce reductions and factory closures followed within months. His book clearly explained what set him apart from “addle-brained” and “weak” executives: “I’m a superstar in my field,” he wrote. Could there be a clearer sell signal? Unable to flip Sunbeam to a new buyer, as he’d done with Scott, Dunlap was stuck actually running the company. He failed spectacularly. Within two miserable years, the board fired him. The tactics he’d used to stave off losses—the company overstated its net income by $60 million, which was real money back then—earned him a civil suit from the SEC and a class-action suit by shareholders. Dunlap eventually settled both and was barred from serving as an officer or director of any public company. You could call Chainsaw Al’s story a fall from grace, but in his case, that’s probably not the proper word.”

Is Your Boss a Psychopath?
by Alan Deutschman / December 19, 2007

One of the most provocative ideas about business in this decade so far surfaced in a most unlikely place. The forum wasn’t the Harvard Business School or one of those $4,000-a-head conferences where Silicon Valley’s venture capitalists search for the next big thing. It was a convention of Canadian cops in the far-flung province of Newfoundland. The speaker, a 71-year-old professor emeritus from the University of British Columbia, remains virtually unknown in the business realm. But he’s renowned in his own field: criminal psychology. Robert Hare is the creator of the Psychopathy Checklist. The 20-item personality evaluation has exerted enormous influence in its quarter-century history. It’s the standard tool for making clinical diagnoses of psychopaths — the 1% of the general population that isn’t burdened by conscience. Psychopaths have a profound lack of empathy. They use other people callously and remorselessly for their own ends. They seduce victims with a hypnotic charm that masks their true nature as pathological liars, master con artists, and heartless manipulators. Easily bored, they crave constant stimulation, so they seek thrills from real-life “games” they can win — and take pleasure from their power over other people.

On that August day in 2002, Hare gave a talk on psychopathy to about 150 police and law-enforcement officials. He was a legendary figure to that crowd. The FBI and the British justice system have long relied on his advice. He created the P-Scan, a test widely used by police departments to screen new recruits for psychopathy, and his ideas have inspired the testing of firefighters, teachers, and operators of nuclear power plants. According to the Canadian Press and Toronto Sun reporters who rescued the moment from obscurity, Hare began by talking about Mafia hit men and sex offenders, whose photos were projected on a large screen behind him. But then those images were replaced by pictures of top executives from WorldCom, which had just declared bankruptcy, and Enron, which imploded only months earlier. The securities frauds would eventually lead to long prison sentences for WorldCom CEO Bernard Ebbers and Enron CFO Andrew Fastow. “These are callous, cold-blooded individuals,” Hare said. “They don’t care that you have thoughts and feelings. They have no sense of guilt or remorse.” He talked about the pain and suffering the corporate rogues had inflicted on thousands of people who had lost their jobs, or their life’s savings. Some of those victims would succumb to heart attacks or commit suicide, he said.

Then Hare came out with a startling proposal. He said that the recent corporate scandals could have been prevented if CEOs were screened for psychopathic behavior. “Why wouldn’t we want to screen them?” he asked. “We screen police officers, teachers. Why not people who are going to handle billions of dollars?” It’s Hare’s latest contribution to the public awareness of “corporate psychopathy.” He appeared in the 2003 documentary The Corporation, giving authority to the film’s premise that corporations are “sociopathic” (a synonym for “psychopathic”) because they ruthlessly seek their own selfish interests — “shareholder value” — without regard for the harms they cause to others, such as environmental damage. Is Hare right? Are corporations fundamentally psychopathic organizations that attract similarly disposed people? It’s a compelling idea, especially given the recent evidence. Such scandals as Enron and WorldCom aren’t just aberrations; they represent what can happen when some basic currents in our business culture turn malignant. We’re worshipful of top executives who seem charismatic, visionary, and tough. So long as they’re lifting profits and stock prices, we’re willing to overlook that they can also be callous, conning, manipulative, deceitful, verbally and psychologically abusive, remorseless, exploitative, self-delusional, irresponsible, and megalomaniacal. So we collude in the elevation of leaders who are sadly insensitive to hurting others and society at large.

But wait, you say: Don’t bona fide psychopaths become serial killers or other kinds of violent criminals, rather than the guys in the next cubicle or the corner office? That was the conventional wisdom. Indeed, Hare began his work by studying men in prison. Granted, that’s still an unusually good place to look for the conscience-impaired. The average Psychopathy Checklist score for incarcerated male offenders in North America is 23.3, out of a possible 40. A score of around 20 qualifies as “moderately psychopathic.” Only 1% of the general population would score 30 or above, which is “highly psychopathic,” the range for the most violent offenders. Hare has said that the typical citizen would score a 3 or 4, while anything below that is “sliding into sainthood.” On the broad continuum between the ethical everyman and the predatory killer, there’s plenty of room for people who are ruthless but not violent. This is where you’re likely to find such people as Ebbers, Fastow, ImClone CEO Sam Waksal, and hotelier Leona Helmsley. We put several big-name CEOs through the checklist, and they scored as “moderately psychopathic”; our quiz on page 48 lets you try a similar exercise with your favorite boss. And this summer, together with New York industrial psychologist Paul Babiak, Hare begins marketing the B-Scan, a personality test that companies can use to spot job candidates who may have an MBA but lack a conscience. “I always said that if I wasn’t studying psychopaths in prison, I’d do it at the stock exchange,” Hare told Fast Company. “There are certainly more people in the business world who would score high in the psychopathic dimension than in the general population. You’ll find them in any organization where, by the nature of one’s position, you have power and control over other people and the opportunity to get something.”

There’s evidence that the business climate has become even more hospitable to psychopaths in recent years. In pioneering long-term studies of psychopaths in the workplace, Babiak focused on a half-dozen unnamed companies: One was a fast-growing high-tech firm, and the others were large multinationals undergoing dramatic organizational changes — severe downsizing, restructuring, mergers and acquisitions, and joint ventures. That’s just the sort of corporate tumult that has increasingly characterized the U.S. business landscape in the last couple of decades. And just as wars can produce exciting opportunities for murderous psychopaths to shine (think of Serbia’s Slobodan Milosevic and Radovan Karadzic), Babiak found that these organizational shake-ups created a welcoming environment for the corporate killer. “The psychopath has no difficulty dealing with the consequences of rapid change; in fact, he or she thrives on it,” Babiak claims. “Organizational chaos provides both the necessary stimulation for psychopathic thrill seeking and sufficient cover for psychopathic manipulation and abusive behavior.”

And you can make a compelling case that the New Economy, with its rule-breaking and roller-coaster results, is just dandy for folks with psychopathic traits too. A slow-moving old-economy corporation would be too boring for a psychopath, who needs constant stimulation. Its rigid structures and processes and predictable ways might stymie his unethical scheming. But a charge-ahead New Economy maverick — an Enron, for instance — would seem the ideal place for this kind of operator. But how can we recognize psychopathic types? Hare has revised his Psychopathy Checklist (known as the PCL-R, or simply “the Hare”) to make it easier to identify so-called subcriminal or corporate psychopaths. He has broken down the 20 personality characteristics into two subsets, or “factors.” Corporate psychopaths score high on Factor 1, the “selfish, callous, and remorseless use of others” category. It includes eight traits: glibness and superficial charm; grandiose sense of self-worth; pathological lying; conning and manipulativeness; lack of remorse or guilt; shallow affect (i.e., a coldness covered up by dramatic emotional displays that are actually playacting); callousness and lack of empathy; and the failure to accept responsibility for one’s own actions. Sound like anyone you know? (Corporate psychopaths score only low to moderate on Factor 2, which pinpoints “chronically unstable, antisocial, and socially deviant lifestyle,” the hallmarks of people who wind up in jail for rougher crimes than creative accounting.)

This view is supported by research by psychologists Belinda Board and Katarina Fritzon at the University of Surrey, who interviewed and gave personality tests to 39 high-level British executives and compared their profiles with those of criminals and psychiatric patients. The executives were even more likely to be superficially charming, egocentric, insincere, and manipulative, and just as likely to be grandiose, exploitative, and lacking in empathy. Board and Fritzon concluded that the businesspeople they studied might be called “successful psychopaths.” In contrast, the criminals — the “unsuccessful psychopaths” — were more impulsive and physically aggressive.

The Factor 1 psychopathic traits seem like the playbook of many corporate power brokers through the decades. Manipulative? Louis B. Mayer was said to be a better actor than any of the stars he employed at MGM, able to turn on the tears at will to evoke sympathy during salary negotiations with his actors. Callous? Henry Ford hired thugs to crush union organizers, deployed machine guns at his plants, and stockpiled tear gas. He cheated on his wife with his teenage personal assistant and then had the younger woman marry his chauffeur as a cover. Lacking empathy? Hotel magnate Leona Helmsley shouted profanities at and summarily fired hundreds of employees allegedly for trivialities, like a maid missing a piece of lint. Remorseless? Soon after Martin Davis ascended to the top position at Gulf & Western, a visitor asked why half the offices were empty on the top floor of the company’s Manhattan skyscraper. “Those were my enemies,” Davis said. “I got rid of them.” Deceitful? Oil baron Armand Hammer laundered money to pay for Soviet espionage. Grandiosity? Thy name is Trump.

In the most recent wave of scandals, Enron’s Fastow displayed many of the corporate psychopath’s traits. He pressured his bosses for a promotion to CFO even though he had a shaky grasp of the position’s basic responsibilities, such as accounting and treasury operations. Suffering delusions of grandeur after just a little time on the job, Fastow ordered Enron’s PR people to lobby CFO magazine to make him its CFO of the Year. But Fastow’s master manipulation was a scheme to loot Enron. He set up separate partnerships, secretly run by himself, to engage in deals with Enron. The deals quickly made tens of millions of dollars for Fastow — and prettified Enron’s financials in the short run by taking unwanted assets off its books. But they left Enron with time bombs that would ultimately cause the company’s total implosion — and lose shareholders billions. When Enron’s scandals were exposed, Fastow pleaded guilty to securities fraud and agreed to pay back nearly $24 million and serve 10 years in prison.

“Chainsaw” Al Dunlap might score impressively on the corporate Psychopathy Checklist too. What do you say about a guy who didn’t attend his own parents’ funerals? He allegedly threatened his first wife with guns and knives. She charged that he left her with no food and no access to their money while he was away for days. His divorce was granted on grounds of “extreme cruelty.” That’s the characteristic that endeared him to Wall Street, which applauded when he fired 11,000 workers at Scott Paper, then another 6,000 (half the labor force) at Sunbeam. Chainsaw hurled a chair at his human-resources chief, the very man who approved the handgun and bulletproof vest on his expense report. Dunlap needed the protection because so many people despised him. His plant closings kept up his reputation for ruthlessness but made no sense economically, and Sunbeam’s financial gains were really the result of Dunlap’s alleged book cooking. When he was finally exposed and booted, Dunlap had the nerve to demand severance pay and insist that the board reprice his stock options. Talk about failure to accept responsibility for one’s own actions. While knaves such as Fastow and Dunlap make the headlines, most horror stories of workplace psychopathy remain the stuff of frightened whispers. Insiders in the New York media business say the publisher of one of the nation’s most famous magazines broke the nose of one of his female sales reps in the 1990s. But he was considered so valuable to the organization that the incident didn’t impede his career.

Most criminals — whether psychopathic or not — are shaped by poverty and often childhood abuse as well. In contrast, corporate psychopaths typically grew up in stable, loving families that were middle class or affluent. But because they’re pathological liars, they tell romanticized tales of rising from tough, impoverished backgrounds. Dunlap pretended that he grew up as the son of a laid-off dockworker; in truth, his father worked steadily and raised his family in suburban comfort. The corporate psychopaths whom Babiak studied all went to college, and a couple even had PhDs. Their ruthless pursuit of self-interest was more easily accomplished in the white-collar realm, which their backgrounds had groomed them for, rather than the criminal one, which comes with much lousier odds. Psychopaths succeed in conventional society in large measure because few of us grasp that they are fundamentally different from ourselves. We assume that they, too, care about other people’s feelings. This makes it easier for them to “play” us. Although they lack empathy, they develop an actor’s expertise in evoking ours. While they don’t care about us, “they have an element of emotional intelligence, of being able to see our emotions very clearly and manipulate them,” says Michael Maccoby, a psychotherapist who has consulted for major corporations.

Psychopaths are typically very likable. They make us believe that they reciprocate our loyalty and friendship. When we realize that they were conning us all along, we feel betrayed and foolish. “People see sociopathy in their personal lives, and they don’t have a clue that it has a label or that others have encountered it,” says Martha Stout, a psychologist at the Harvard Medical School and the author of the recent best-seller The Sociopath Next Door: The Ruthless Versus the Rest of Us (Broadway Books, 2005). “It makes them feel crazy or alone. It goes against our intuition that a small percentage of people can be so different from the rest of us — and so evil. Good people don’t want to believe it.” Of course, cynics might say that it can be an advantage to lack a conscience. That’s probably why major investors installed Dunlap as the CEO of Sunbeam: He had no qualms about decimating the workforce to impress Wall Street. One reason outside executives get brought into troubled companies is that they lack the emotional stake in either the enterprise or its people. It’s easier for them to act callously and remorselessly, which is exactly what their backers want. The obvious danger of the new B-Scan test for psychopathic tendencies is that companies will hire or promote people with high scores rather than screen them out. Even Babiak, the test’s codeveloper, says that while “a high score is a red flag, sometimes middle scores are okay. Perhaps you don’t want the most honest and upfront salesman.”

Indeed, not every aberrant boss is necessarily a corporate psychopath. There’s another personality that’s often found in the executive suite: the narcissist. While many psychologists would call narcissism a disorder, this trait can be quite beneficial for top bosses, and it’s certainly less pathological than psychopathy. Maccoby’s book The Productive Narcissist: The Promise and Perils of Visionary Leadership (Broadway Books, 2003) portrays the narcissistic CEO as a grandiose egotist who is on a mission to help humanity in the abstract even though he’s often insensitive to the real people around him. Maccoby counts Apple’s Steve Jobs, General Electric’s Jack Welch, Intel’s Andy Grove, Microsoft’s Bill Gates, and Southwest Airlines’ Herb Kelleher as “productive narcissists,” or PNs. Narcissists are visionaries who attract hordes of followers, which can make them excel as innovators, but they’re poor listeners and they can be awfully touchy about criticism. “These people don’t have much empathy,” Maccoby says. “When Bill Gates tells someone, ‘That’s the stupidest thing I’ve ever heard,’ or Steve Jobs calls someone a bozo, they’re not concerned about people’s feelings. They see other people as a means toward their ends. But they do have a sense of changing the world — in their eyes, improving the world. They build their own view of what the world should be and get others recruited to their vision. Psychopaths, in contrast, are only interested in self.”

Maccoby concedes that productive narcissists can become “drunk with power” and turn destructive. The trick, he thinks, is to pair a productive narcissist with a “productive obsessive,” or conscientious, control-minded manager. Think of Grove when he was matched with chief operating officer Craig Barrett, Gates with president Steve Ballmer, Kelleher with COO Colleen Barrett, and Oracle’s Larry Ellison with COO Ray Lane and CFO Jeff Henley. In his remarkably successful second tour of duty at Apple, Jobs has been balanced by steady, competent behind-the-scenes players such as Timothy Cook, his executive vice president for sales and operations. But our culture’s embrace of narcissism as the hallmark of admired business leaders is dangerous, Babiak maintains, since “individuals who are really psychopaths are often mistaken for narcissists and chosen by the organization for leadership positions.” How does he distinguish the difference between the two types? “In the case of a narcissist, everything is me, me, me,” Babiak explains. “With a psychopath, it’s ‘Is it thrilling, is it a game I can win, and does it hurt others?’ My belief is a psychopath enjoys hurting others.”

Intriguingly, Babiak believes that it’s extremely unlikely for an entrepreneurial founder-CEO to be a corporate psychopath because the company is an extension of his own ego — something he promotes rather than plunders. “The psychopath has no allegiance to the company at all, just to self,” Babiak says. “A psychopath is playing a short-term parasitic game.” That was the profile of Fastow and Dunlap — guys out to profit for themselves without any concern for the companies and lives they were wrecking. In contrast, Jobs and Ellison want their own companies to thrive forever — indeed, to dominate their industries and take over other fields as well. “An entrepreneurial founder-CEO might have a narcissistic tendency that looks like psychopathy,” Babiak says. “But they have a vested interest: Their identity is wrapped up with the company’s existence. They’re loyal to the company.” So these types are ruthless not only for themselves but also for their companies, their extensions of self.

The issue is whether we will continue to elevate, celebrate, and reward so many executives who, however charismatic, remain indifferent to hurting other people. Babiak says that while the first line of defense against psychopaths in the workplace is screening job candidates, the second line is a “culture of openness and trust, especially when the company is undergoing intense, chaotic change.” Europe is far ahead of the United States in trying to deal with psychological abuse and manipulation at work. The “antibullying” movement in Europe has produced new laws in France and Sweden. Harvard’s Stout suggests that the relentlessly individualistic culture of the United States contributes a lot to our problems. She points out that psychopathy has a dramatically lower incidence in certain Asian cultures, where the heritage has emphasized community bonds rather than glorified self-interest. “If we continue to go this way in our Western culture,” she says, “evolutionarily speaking, it doesn’t end well.” The good news is that we can do something about corporate psychopaths. Scientific consensus says that only about 50% of personality is influenced by genetics, so psychopaths are molded by our culture just as much as they are born among us. But unless American business makes a dramatic shift, we’ll get more Enrons — and deserve them.

aired 05.27.2011

Recently we heard about this test that could determine if someone was a psychopath. So, naturally, our staff decided to take it. This week we hear the results. Ira explains that when the radio staff decided to take a test that reveals who is a psychopath, very quickly everyone came to believe that the highest score would go to either Robyn, Jane, or him. (6 minutes)

Underachievement Test
NPR Science Correspondent Alix Spiegel tells the story of Robert Dixon, who’s in a maximum security prison in Vacaville California and is unlikely to ever get parole because of his score on the psychopath test. The test also is called “the checklist” or, more formally, the PCL-R, which stands for “Psychopathy Check List—Revised.” Alix tells the story of its creation and reports that the man who created the test, Bob Hare, is concerned at how it’s being used today in the criminal justice system. A version of this story aired on NPR’s All Things Considered. (28 minutes)

King of the Forest
Jon Ronson investigates whether corporate leaders can, in fact, be psychopaths by visiting a former Sunbeam CEO named Al Dunlap. This is an excerpt from Ronson’s book, The Psychopath Test. (15 minutes)Song: “If I Were King of the Forest”, Wizard of Oz Soundtrack

Ira and the radio show staff get their results on the psychopath test from Dr. David Bernstein, ofForensic Consultants, LLC., who administered the test to them. (6 minutes)

by Fast Company Staff / July 1, 2005

The standard clinical test for psychopathy, Robert Hare’s PCL-R, evaluates 20 personality traits overall, but a subset of eight traits defines what he calls the “corporate psychopath” — the nonviolent person prone to the “selfish, callous, and remorseless use of others.” Does your boss fit the profile? Here’s our do-it-yourself quiz drawing on the test manual and Hare’s book Without Conscience. (Disclaimer: If you’re not a psychologist or psychiatrist, this will be a strictly amateur exercise.) We’ve used the pronoun “he,” but research suggests psychologists have underestimated the psychopathic propensity of women.

For each question, score two points for “yes,” one point for “somewhat” or “maybe,” and zero points for “no.”

[1] Is he glib and superficially charming?
Is he a likable personality and a terrific talker — entertaining, persuasive, but maybe a bit too smooth and slick? Can he pass himself off as a supposed expert in a business meeting even though he really doesn’t know much about the topic? Is he a flatterer? Seductive, but insincere? Does he tell amusing but unlikely anecdotes celebrating his own past? Can he persuade his colleagues to support a certain position this week — and then argue with equal conviction and persuasiveness for the opposite position next week? If he’s a CEO, can he appear on TV and somehow get away without answering the interviewer’s direct questions or saying anything truly substantive?

[2] Does he have a grandiose sense of self-worth?
Does he brag? Is he arrogant? Superior? Domineering? Does he feel he’s above the rules that apply to “little people”? Does he act as though everything revolves around him? Does he downplay his legal, financial, or personal problems, say they’re just temporary, or blame them on others?

[3] Is he a pathological liar?
Has he reinvented his own past in a more positive light — for example, claiming that he rose from a tough, poor background even though he really grew up middle class? Does he lie habitually even though he can easily be found out? When he’s exposed, does he still act unconcerned because he thinks he can weasel out of it? Does he enjoy lying? Is he proud of his knack for deceit? Is it hard to tell whether he knows he’s a liar or whether he deceives himself and believes his own bull?

[4] Is he a con artist or master manipulator?
Does he use his skill at lying to cheat or manipulate other people in his quest for money, power, status, and sex? Does he “use” people brilliantly? Does he engage in dishonest schemes such as cooking the books?

[5] When he harms other people, does he feel a lack of remorse or guilt?
Is he concerned about himself rather than the wreckage he inflicts on others or society at large? Does he say he feels bad but act as though he really doesn’t? Even if he has been convicted of a white-collar crime, such as securities fraud, does he not accept blame for what he did, even after getting out of prison? Does he blame others for the trouble he causes?

[6] Does he have a shallow affect?
Is he cold and detached, even when someone near him dies, suffers, or falls seriously ill — for example, does he visit the hospital or attend the funeral? Does he make brief, dramatic displays of emotion that are nothing more than putting on a theatrical mask and playacting for effect? Does he claim to be your friend but rarely or never ask about the details of your life or your emotional state? Is he one of those tough-guy executives who brag about how emotions are for whiners and losers?

[7] Is he callous and lacking in empathy?
Does he not give a damn about the feelings or well-being of other people? Is he profoundly selfish? Does he cruelly mock others? Is he emotionally or verbally abusive toward employees, “friends,” and family members? Can he fire employees without concern for how they’ll get by without the job? Can he profit from embezzlement or stock fraud without concern for the harm he’s doing to shareholders or pensioners who need their savings to pay for their retirements?

[8] Does he fail to accept responsibility for his own actions?
Does he always cook up some excuse? Does he blame others for what he’s done? If he’s under investigation or on trial for a corporate crime, like deceitful accounting or stock fraud, does he refuse to acknowledge wrongdoing even when the hard evidence is stacked against him?

If your boss scores:
1-4 | Be frustrated
5-7 | Be cautious
8-12 | Be afraid
13-16 | Be very afraid

by Robert Hare / January 01, 1994

A major part of my own quarter-century search for answers to this enigma has been a concerted effort to develop an accurate means of detecting the psychopaths among us. Measurement and categorization are, of course, fundamental to any scientific endeavor, but the implications of being able to identify psychopaths are as much practical as academic. To put it simply, if we can’t spot them, we are doomed to be their victims, both as individuals and as a society. My role in the search for psychopaths began in the 1960s at the psychology department of the University of British Columbia. There, my growing interest in psychopathy merged with my experience working with psychopaths in prison to form what was to become my life’s work. I assembled a team of clinicians who would identify psychopaths in the prison population by means of long, detailed interviews and close study of file information. From this eventually developed a highly reliable diagnostic tool that any clinician or researcher could use and that yielded a richly detailed profile of the personality disorder called psychopathy. We named this instrument the Psychopathy Checklist (Multi-Health Systems; 1991). The checklist is now used worldwide and provides clinicians and researchers with a way of distinguishing, with reasonable certainty, true psychopaths from those who merely break the rules.

What follows is a general summary of the key traits and behaviors of a psychopath. Do not use these symptoms to diagnose yourself or others. A diagnosis requires explicit training and access to the formal scoring manual. If you suspect that someone you know conforms to the profile described here, and if it is important for you to have an expert opinion, you should obtain the services of a qualified (registered) forensic psychologist or psychiatrist. Also, be aware that people who are not psychopaths may have some of the symptoms described here. Many people are impulsive, or glib, or cold and unfeeling, but this does not mean that they are psychopaths. Psychopathy is a syndrome—a cluster of related symptoms.

Key Symptoms of Psychopathy

  • Glib and superficial
  • Egocentric and grandiose
  • Lack of remorse or guilt
  • Lack of empathy
  • Deceitful and manipulative
  • Shallow emotions

Social Deviance:

  • Impulsive
  • Poor behavior controls
  • Need for excitement
  • Lack of responsibility
  • Early behavior problems
  • Adult antisocial behavior

Glib and Superficial
Psychopaths are often voluble and verbally facile. They can be amusing and entertaining conversationalists, ready with a clever comeback, and are able to tell unlikely but convincing stories that cast themselves in a good light. They can be very effective in presenting themselves well and are often very likable and charming. One of my raters described an interview she did with a prisoner: “I sat down and took out my clipboard,” she said, “and the first thing this guy told me was what beautiful eyes I had. He managed to work quite a few compliments on my appearance into the interview, so by the time I wrapped things up, I was feeling unusually… well, pretty. I’m a wary person, especially on the job, and can usually spot a phony. When I got back outside, I couldn’t believe I’d fallen for a line like that.”

Egocentric and Grandiose
Psychopaths have a narcissistic and grossly inflated view of their own self-worth and importance, a truly astounding egocentricity and sense of entitlement, and see themselves as the center of the universe, justified in living according to their own rules. “It’s not that I don’t follow the law,” said one subject. “I follow my own laws. I never violate my own rules.” She then proceeded to describe these rules in terms of “looking out for number one.” Psychopaths often claim to have specific goals but show little appreciation regarding the qualifications required—they have no idea of how to achieve them and little or no chance of attaining these goals, given their track record and lack of sustained interest in formal education. The psychopathic inmate might outline vague plans to become a lawyer for the poor or a property tycoon. One inmate, not particularly literate, managed to copyright the title of a book he was planning to write about himself, already counting the fortune his best-selling book would bring.

Lack of Remorse or Guilt
Psychopaths show a stunning lack of concern for the effects their actions have on others, no matter how devastating these might be. They may appear completely forthright about the matter, calmly stating that they have no sense of guilt, are not sorry for the ensuing pain, and that there is no reason now to be concerned. When asked if he had any regrets about stabbing a robbery victim who subsequently spent time in the hospital as a result of his wounds, one of our subjects replied, “Get real! He spends a few months in hospital and I rot here. If I wanted to kill him I would have slit his throat. That’s the kind of guy I am; I gave him a break.” Their lack of remorse or guilt is associated with a remarkable ability to rationalize their behavior, to shrug off personal responsibility for actions that cause family, friends, and others to reel with shock and disappointment. They usually have handy excuses for their behavior, and in some cases deny that it happened at all.

Lack of Empathy
Many of the characteristics displayed by psychopaths are closely associated with a profound lack of empathy and inability to construct a mental and emotional “facsimile” of another person. They seem completely unable to “get into the skin” of others, except in a purely intellectual sense. They are completely indifferent to the rights and suffering of family and strangers alike. If they do maintain ties, it is only because they see family members as possessions. One of our subjects allowed her boyfriend to sexually molest her five-year-old daughter because “he wore me out. I wasn’t ready for more sex that night.” The woman found it hard to understand why the authorities took her child into care.

Deceitful and Manipulative
With their powers of imagination in gear and beamed on themselves, psychopaths appear amazingly unfazed by the possibility—or even by the certainty—of being found out. When caught in a lie or challenged with the truth, they seldom appear perplexed or embarrassed—they simply change their stories or attempt to rework the facts so they appear to be consistent with the lie. The result is a series of contradictory statements and a thoroughly confused listener. And psychopaths seem proud of their ability to lie. When asked if she lied easily, one woman laughed and replied, “I’m the best. I think it’s because I sometimes admit to something bad about myself. They think, well, if she’s admitting to that she must be telling the truth about the rest.”

Shallow Emotions
Psychopaths seem to suffer a kind of emotional poverty that limits the range and depth of their feelings. At times they appear to be cold and unemotional while nevertheless being prone to dramatic, shallow, and short-lived displays of feeling. Careful observers are left with the impression they are playacting and little is going on below the surface. A psychopath in our research said that he didn’t really understand what others meant by fear. “When I rob a bank,” he said, “I notice that the teller shakes. One barfed all over the money. She must have been pretty messed up inside, but I don’t know why. If someone pointed a gun at me I guess I’d be afraid, but I wouldn’t throw up.” When asked if he ever felt his heart pound or his stomach churn, he replied, “Of course! I’m not a robot. I really get pumped up when I have sex or when I get into a fight.”

Psychopaths are unlikely to spend much time weighing the pros and cons of a course of action or considering the possible consequences. “I did it because I felt like it,” is a common response. These impulsive acts often result from an aim that plays a central role in most of the psychopath’s behavior: to achieve immediate satisfaction, pleasure, or relief. So family members, relatives, employers, and coworkers typically find themselves standing around asking themselves what happened—jobs are quit, relationships broken off, plans changed, houses ransacked, people hurt, often for what appears as little more than a whim. As the husband of a psychopath I studied put it: “She got up and left the table, and that was the last I saw of her for two months.”

Poor Behavior Controls
Besides being impulsive, psychopaths are highly reactive to perceived insults or slights. Most of us have powerful inhibitory controls over our behavior; even if we would like to respond aggressively we are usually able to “keep the lid on.” In psychopaths, these inhibitory controls are weak, and the slightest provocation is sufficient to overcome them. As a result, psychopaths are short-tempered or hotheaded and tend to respond to frustration, failure, discipline, and criticism with sudden violence, threats or verbal abuse. But their outbursts, extreme as they may be, are often short-lived, and they quickly act as if nothing out of the ordinary has happened. For example, an inmate in line for dinner was accidentally bumped by another inmate, whom he proceeded to beat senseless. The attacker then stepped back into line as if nothing had happened. Despite the fact that he faced solitary confinement as punishment for the infraction, his only comment when asked to explain himself was, “I was pissed off. He stepped into my space. I did what I had to do. Although psychopaths have a “hair trigger,” their aggressive displays are “cold”; they lack the intense arousal experienced when other individuals lose their temper.

A Need for Excitement
Psychopaths have an ongoing and excessive need for excitement—they long to live in the fast lane or “on the edge,” where the action is. In many cases the action involves the breaking of rules. Many psychopaths describe “doing crime” for excitement or thrills. When asked if she ever did dangerous things just for fun, one of our female psychopaths replied, “Yeah, lots of things. But what I find most exciting is walking through airports with drugs. Christ! What a high!” The flip side of this yen for excitement is an inability to tolerate routine or monotony. Psychopaths are easily bored and are not likely to engage in activities that are dull, repetitive, or require intense concentration over long periods.

Lack of Responsibility
Obligations and commitments mean nothing to psychopaths. Their good intentions—”I’ll never cheat on you again”—are promises written on the wind. Horrendous credit histories, for example, reveal the lightly taken debt, the loan shrugged off, the empty pledge to contribute to a child’s support. Their performance on the job is erratic, with frequent absences, misuse of company resources, violations of company policy, and general untrustworthiness. They do not honor formal or implied commitments to people, organizations, or principles. Psychopaths are not deterred by the possibility that their actions mean hardship or risk for others. A 25-year-old inmate in our studies has received more than 20 convictions for dangerous driving, driving while impaired, leaving the scene of an accident, driving without a license, and criminal negligence causing death. When asked if he would continue to drive after his release from prison, he replied, “Why not? Sure, I drive fast, but I’m good at it. It takes two to have an accident.”

Early Behavior Problems
Most psychopaths begin to exhibit serious behavioral problems at an early age. These might include persistent lying, cheating, theft, arson, truancy, substance abuse, vandalism, and/or precocious sexuality. Because many children exhibit some of these behaviors at one time or another—especially children raised in violent neighborhoods or in disrupted or abusive families—it is important to emphasize that the psychopath’s history of such behaviors is more extensive and serious than most, even when compared with that of siblings and friends raised in similar settings. One subject, serving time for fraud, told us that as a child he would put a noose around the neck of a cat, tie the other end of the string to the top of a pole, and bat the cat around the pole with a tennis racket. Although not all adult psychopaths exhibited this degree of cruelty when in their youth, virtually all routinely got themselves into a wide range of difficulties.

Adult Antisocial Behavior
Psychopaths see the rules and expectations of society as inconvenient and unreasonable impediments to their own behavioral expression. They make their own rules, both as children and as adults. Many of the antisocial acts of psychopaths lead to criminal charges and convictions. Even within the criminal population, psychopaths stand out, largely because the antisocial and illegal activities of psychopaths are more varied and frequent than are those of other criminals. Psychopaths tend to have no particular affinity, or “specialty,” for one particular type of crime but tend to try everything. But not all psychopaths end up in jail. Many of the things they do escape detection or prosecution, or are on “the shady side of the law.” For them, antisocial behavior may consist of phony stock promotions, questionable business practices, spouse or child abuse, and so forth. Many others do things that, though not necessarily illegal, are nevertheless unethical, immoral, or harmful to others: philandering or cheating on a spouse to name a few.

Thinking about psychopathy leads us very quickly to a single fundamental question: Why are some people like this? Unfortunately, the forces that produce a psychopath are still obscure, an admission those looking for clear answers will find unsatisfying. Nevertheless, there are several rudimentary theories about the cause of psychopathy worth considering. At one end of the spectrum are theories that view psychopathy as largely the product of genetic or biological factors (nature), whereas theories at the other end posit that psychopathy results entirely from a faulty early social environment (nurture). The position that I favor is that psychopathy emerges from a complex—and poorly understood—interplay between biological factors and social forces. It is based on evidence that genetic factors contribute to the biological bases of brain function and to basic personality structure, which in turn influence the way an individual responds to, and interacts with, life experiences and the social environment. In effect, the core elements needed for the development of psychopathy—including a profound inability to experience empathy and the complete range of emotions, including fear—are in part provided by nature and possibly by some unknown biological influences on the developing fetus and neonate. As a result, the capacity for developing internal controls and conscience and for making emotional “connections” with others is greatly reduced.

Can Anything Be Done?
In their desperate search for solutions people trapped in a destructive and seemingly hopeless relationship with a psychopath frequently are told: Quit indulging him and send him for therapy. A basic assumption of psychotherapy is that the patient needs and wants help for distressing or painful psychological and emotional problems. Successful therapy also requires that the patient actively participate, along with the therapist, in the search for relief of his or her symptoms. In short, the patient must recognize there is a problem and must want to do something about it. But here is the crux: Psychopaths don’t feel they have psychological or emotional problems, and they see no reason to change their behavior to conform with societal standards they do not agree with. Thus, in spite of more than a century of clinical study and decades of research, the mystery of the psychopath still remains. Recent developments have provided us with new insights into the nature of this disturbing disorder, and its borders are becoming more defined. But compared with other major clinical disorders, little research has been devoted to psychopathy, even though it is responsible for more social distress and disruption than all other psychiatric disorders combined. So, rather than trying to pick up the pieces after the damage has been done, it would make far greater sense to increase our efforts to understand this perplexing disorder and to search for effective early interventions. The alternatives are to continue devoting massive resources to the prosecution, incarceration, and supervision of psychopaths after they have committed offenses against society and to continue to ignore the welfare and plight of their victims. We have to learn how to socialize them, not resocialize them. And this will require serious efforts at research and early intervention. It is imperative that we continue the search for clues.

{Excerpted from Without Conscience: The Disturbing World of the Psychopaths Among Us (Simon & Schuster) by Robert Hare, Ph.D. Copyright 1993.}

A Survival Guide
Although no one is completely immune to the devious machinations of the psychopath, there are some things you can do to reduce your vulnerability.

  • Know what you are dealing with. This sounds easy but in fact can be very difficult. All the reading in the world cannot immunize you from the devastating effects of psychopaths. Everyone, including the experts, can be taken in, conned, and left bewildered by them. A good psychopath can play a concerto on anyone’s heart strings.
  • Try not to be influenced by “props.” It is not easy to get beyond the winning smile, the captivating body language, the fast talk of the typical psychopath, all of which blind us to his or her real intentions. Many people find it difficult to deal with the intense, “predatory state” of the psychopath. The fixated stare, is more a prelude to self-gratification and the exercise of power rather than simple interest or empathic caring.
  • Don’t wear blinders. Enter new relationships with your eyes wide open. Like the rest of us, most psychopathic con artists and “love-thieves” initially hide their dark side by putting their “best foot forward.” Cracks may soon begin to appear in the mask they wear, but once trapped in their web, it will be difficult to escape financially and emotionally unscathed.
  • Keep your guard up in high-risk situations. Some situations are tailor-made for psychopaths: singles bars, ship cruises, foreign airports, etc. In each case, the potential victim is lonely, looking for a good time, excitement, or companionship, and there will usually be someone willing to oblige, for a hidden price.
  • Know yourself. Psychopaths are skilled at detecting and ruthlessly exploiting your weak spots. Your best defense is to understand what these spots are, and to be extremely wary of anyone who zeroes in on them.

Unfortunately, even the most careful precautions are no guarantee that you will be safe from a determined psychopath. In such cases, all you can do is try to exert some sort of damage control. This is not easy but some suggestions may be of help:

  • Obtain professional advice. Make sure the clinician you consult is familiar with the literature on psychopathy and has had experience in dealing with psychopaths.
  • Don’t blame yourself. Whatever the reasons for being involved with a psychopath, it is important that you not accept blame for his or her attitudes and behavior. Psychopaths play by the same rules—their rules—with everyone.
  • Be aware of who the victim is. Psychopaths often give the impression that it is they who are suffering and that the victims are to blame for their misery. Don’t waste your sympathy on them.
  • Recognize that you are not alone. Most psychopaths have lots of victims. It is certain that a psychopath who is causing you grief is also causing grief to others.
  • Be careful about power struggles. Keep in mind that psychopaths have a strong need for psychological and physical control over others. This doesn’t mean that you shouldn’t stand up for your rights, but it will probably be difficult to do so without risking serious emotional or physical trauma.
  • Set firm ground rules. Although power struggles with a psychopath are risky you may be able to set up some clear rules—both for yourself and for the psychopath—to make your life easier and begin the difficult transition from victim to a person looking out for yourself.
  • Don’t expect dramatic changes. To a large extent, the personality of psychopaths is “carved in stone.” There is little likelihood that anything you do will produce fundamental, sustained changes in how they see themselves or others.
  • Cut your losses. Most victims of psychopaths end up feeling confused and hopeless, and convinced that they are largely to blame for the problem. The more you give in the more you will be taken advantage of by the psychopath’s insatiable appetite for power and control.
  • Use support groups. By the time your suspicions have led you to seek a diagnosis, you already know that you’re in for a very long and bumpy ride. Make sure you have all the emotional support you can muster.

Social scientists build case for ‘survival of the kindest’
by Yasmin Anwar, Media Relations | 08 December 2009

Researchers at the University of California, Berkeley, are challenging long-held beliefs that human beings are wired to be selfish. In a wide range of studies, social scientists are amassing a growing body of evidence to show we are evolving to become more compassionate and collaborative in our quest to survive and thrive. In contrast to “every man for himself” interpretations of Charles Darwin’s theory of evolution by natural selection, Dacher Keltner, a UC Berkeley psychologist and author of “Born to be Good: The Science of a Meaningful Life,” and his fellow social scientists are building the case that humans are successful as a species precisely because of our nurturing, altruistic and compassionate traits. They call it “survival of the kindest.”

“Because of our very vulnerable offspring, the fundamental task for human survival and gene replication is to take care of others,” said Keltner, co-director of UC Berkeley’s Greater Good Science Center. “Human beings have survived as a species because we have evolved the capacities to care for those in need and to cooperate. As Darwin long ago surmised, sympathy is our strongest instinct.”


Empathy in our genes
Keltner’s team is looking into how the human capacity to care and cooperate is wired into particular regions of the brain and nervous system. One recent study found compelling evidence that many of us are genetically predisposed to be empathetic. The study, led by UC Berkeley graduate student Laura Saslow and Sarina Rodrigues of Oregon State University, found that people with a particular variation of the oxytocin gene receptor are more adept at reading the emotional state of others, and get less stressed out under tense circumstances. Informally known as the “cuddle hormone,” oxytocin is secreted into the bloodstream and the brain, where it promotes social interaction, nurturing and romantic love, among other functions. “The tendency to be more empathetic may be influenced by a single gene,” Rodrigues said.

The more you give, the more respect you get
While studies show that bonding and making social connections can make for a healthier, more meaningful life, the larger question some UC Berkeley researchers are asking is, “How do these traits ensure our survival and raise our status among our peers?” One answer, according to UC Berkeley social psychologist and sociologist Robb Willer is that the more generous we are, the more respect and influence we wield. In one recent study, Willer and his team gave participants each a modest amount of cash and directed them to play games of varying complexity that would benefit the “public good.” The results, published in the journal American Sociological Review, showed that participants who acted more generously received more gifts, respect and cooperation from their peers and wielded more influence over them. “The findings suggest that anyone who acts only in his or her narrow self-interest will be shunned, disrespected, even hated,” Willer said. “But those who behave generously with others are held in high esteem by their peers and thus rise in status. Given how much is to be gained through generosity, social scientists increasingly wonder less why people are ever generous and more why they are ever selfish,” he added.

Cultivating the greater good
Such results validate the findings of such “positive psychology” pioneers as Martin Seligman, a professor at the University of Pennsylvania whose research in the early 1990s shifted away from mental illness and dysfunction, delving instead into the mysteries of human resilience and optimism. While much of the positive psychology being studied around the nation is focused on personal fulfillment and happiness, UC Berkeley researchers have narrowed their investigation into how it contributes to the greater societal good. One outcome is the campus’s Greater Good Science Center, a West Coast magnet for research on gratitude, compassion, altruism, awe and positive parenting, whose benefactors include the Metanexus Institute, Tom and Ruth Ann Hornaday and the Quality of Life Foundation.

Christine Carter, executive director of the Greater Good Science Center, is creator of the “Science for Raising Happy Kids” Web site, whose goal, among other things, is to assist in and promote the rearing of “emotionally literate” children. Carter translates rigorous research into practical parenting advice. She says many parents are turning away from materialistic or competitive activities, and rethinking what will bring their families true happiness and well-being. “I’ve found that parents who start consciously cultivating gratitude and generosity in their children quickly see how much happier and more resilient their children become,” said Carter, author of “Raising Happiness: 10 Simple Steps for More Joyful Kids and Happier Parents” which will be in bookstores in February 2010. “What is often surprising to parents is how much happier they themselves also become.”

The sympathetic touch
As for college-goers, UC Berkeley psychologist Rodolfo Mendoza-Denton has found that cross-racial and cross-ethnic friendships can improve the social and academic experience on campuses. In one set of findings, published in the Journal of Personality and Social Psychology, he found that the cortisol levels of both white and Latino students dropped as they got to know each over a series of one-on-one get-togethers. Cortisol is a hormone triggered by stress and anxiety. Meanwhile, in their investigation of the neurobiological roots of positive emotions, Keltner and his team are zeroing in on the aforementioned oxytocin as well as the vagus nerve, a uniquely mammalian system that connects to all the body’s organs and regulates heart rate and breathing.

Both the vagus nerve and oxytocin play a role in communicating and calming. In one UC Berkeley study, for example, two people separated by a barrier took turns trying to communicate emotions to one another by touching one other through a hole in the barrier. For the most part, participants were able to successfully communicate sympathy, love and gratitude and even assuage major anxiety.

Researchers were able to see from activity in the threat response region of the brain that many of the female participants grew anxious as they waited to be touched. However, as soon as they felt a sympathetic touch, the vagus nerve was activated and oxytocin was released, calming them immediately. “Sympathy is indeed wired into our brains and bodies; and it spreads from one person to another through touch,” Keltner said. The same goes for smaller mammals. UC Berkeley psychologist Darlene Francis and Michael Meaney, a professor of biological psychiatry and neurology at McGill University, found that rat pups whose mothers licked, groomed and generally nurtured them showed reduced levels of stress hormones, including cortisol, and had generally more robust immune systems.

Overall, these and other findings at UC Berkeley challenge the assumption that nice guys finish last, and instead support the hypothesis that humans, if adequately nurtured and supported, tend to err on the side of compassion. “This new science of altruism and the physiological underpinnings of compassion is finally catching up with Darwin’s observations nearly 130 years ago, that sympathy is our strongest instinct,” Keltner said.

Darwin’s Touch: Survival of the Kindest
by Dacher Keltner / February 11, 2009

Two hundred years ago on February 12, Adam Gopnik writes in Angels and Ages: A Short Book About Darwin, Lincoln, and Modern Life, two pebbles — Charles Darwin and Abraham Lincoln — were dropped into the sea of life. Their ideas and forms of eloquence have redirected the currents of humanity. One current of Darwin’s thought is well-known. His theory of evolution by natural selection would require new genesis stories about the origins of life forms, less arrogant notions about man’s place in the great chain of being, and a rethinking of our species as one in flux—and with rather hairy relatives.

Less well-known is a second current of Darwin’s thought — his conception of human nature. Think of Darwin and “survival of the fittest” leaps to mind, as do images of competitive individuals — collections of selfish genes — going at one another bloody in tooth and claw. “Survival of the fittest” was not Darwin’s phrase, but Herbert Spencer’s and that of Social Darwinists who used Darwin to justify their wished-for superiority of different classes and races. “Survival of the kindest” better captures Darwin’s thinking about his own kind.

In Darwin’s first book about humans, The Descent of Man, and Selection In Relation to Sex from 1871, Darwin argued for “the greater strength of the social or maternal instincts than that of any other instinct or motive.” His reasoning was disarmingly intuitive: in our hominid predecessors, communities of more sympathetic individuals were more successful in raising healthier offspring to the age of viability and reproduction — the sine qua non of evolution. One year later, in The Expression of Emotion in Man and Animals, Darwin countered creationists’ claims that God had designed humans with special facial muscles to express uniquely human moral sentiments like sympathy. Instead, drawing upon observations of his children, animals at the London zoo, and his faithful dogs, Darwin showed how our moral sentiments are expressed in mammalian patterns of behavior. In his analysis of suffering, for example, Darwin builds from pure empirical observation to a radical conclusion: the oblique eyebrows, compressed lips, tears, and groans of human suffering have their parallels in the whining of monkeys and elephants’ tears. To be a mammal is to suffer. To be a mammal is to feel the strongest of Darwin’s instincts — sympathy.

The expression of sympathy, Darwin observed, was to be found in mammalian patterns of tactile contact. Inspired by this observation, Matthew Hertenstein and I conducted a recent study of emotion and touch that was as much a strange act of performance art as hardheaded science. Two participants, a toucher and touchee, sat on opposite sides of a barrier that we built in a laboratory room. They therefore could not see nor hear one another, and could only communicate via that five digit wonder, the hand, making contact on skin. The touchee bravely poked his or her arm through a curtain-covered opening in the barrier, and received 12 different touches to the forearm from the toucher, who in each instance was trying to communicate a different emotion. For each touch, the touchee guessed which emotion was being conveyed. With one second touches to the forearm, our participants could reliably communicate sympathy, love, and gratitude with rates of accuracy seven times as high as those produced by chance guessing.

Sympathetic touches are processed by receptors under the surface of the skin, and set in motion a cascade of beneficial physiological responses. In one recent study, female participants waiting anxiously for an electric shock showed activation in threat-related regions of the brain, a response quickly turned off when their hands were held by loved ones nearby. Friendly touch stimulates activation in the vagus nerve, a bundle of nerves in the chest that calms fight-or-flight cardiovascular response and triggers the release of oxytocin, which enables feelings of trust.

Research by Darlene Francis and Michael Meaney reveals that sympathetic environments — those filled with warm touch — create individuals better suited to survival and reproduction, as Darwin long ago surmised. Rat pups who receive high levels of tactile contact from their mothers — in the form of licking, grooming, and close bodily contact — later as mature rats show reduced levels of stress hormones in response to being restrained, explore novel environments with greater gusto, show fewer stress-related neurons in the brain, and have more robust immune systems. Were he alive today, Darwin would likely have found modest delight in seeing two of his hypotheses confirmed: sympathy is indeed wired into our brains and bodies; and it spreads from one person to another through touch. Darwin, the great fact amasser that he was, would no doubt have compiled these new findings on sympathy and touch in one of his many notebooks (now a folder on a laptop). He may have titled that folder “Survival of the kindest.”

Paul Ekman’s Taxonomy of Compassion
by Paul Ekman / June 21, 2010

Below is a guide to understanding what these varying forms of compassion are and why they’re so important.

Emotion Recognition is the easiest—the sine qua non. It’s knowing how another person is feeling. Most people don’t need to be taught it, though people with Asperger’s, autism, or schizoprenia do. Realize that the torturer needs emotion recognition: to know how you feel doesn’t imply whether I’m going to try to relieve your suffering or inflict it, or just have no concern. But if I don’t know how you’re feeling, everything else just falls by the wayside.

Emotional Resonance is what Bill Clinton does: “I feel your pain.” I distinguish between two types of resonance: Identical Resonance is when you realize that someone is in pain and you actually physically experience that same feeling yourself. But when you say, “Oh, you poor baby! I’m so sorry you’re feeling that way. What can I do to help you?”—that’s Reactive Resonance. Everybody loves people who resonate; resonance is crucial to our relationships with our loved ones. But if you’re like my daughter, an emergency room worker in San Francisco’s only trauma center, if you feel other people’s pain for 8 or 12 hours a day, you’ll burn out. The Dalai Lama says he feels others’ pain, but just very slightly and just for a few seconds, then it passes.
Not everyone resonates: There’s reason to believe that people with anti-social personalities don’t resonate, but they’re able to act as if they resonate, because they know other people like it, and that allows them to manipulate others.

Familial Compassion is the seed of compassion, planted through the caregiver-offspring bond. It raises very interesting questions about people who were brought up without a single caregiver, or were brought up with a parent who had a very distant attachment. What is their capacity for compassion? Both the Dalai Lama and Darwin would say that they’re going to have problems—without the seed, the flower won’t grow.

Global Compassion was exemplified by the response to the 2004 Indian Ocean tsunami. People around the world extended assistance to strangers, of different races and skin colors. Now, we know that not everybody has it—a lot of people acted, and a lot of people didn’t. How do we cultivate global compassion? I consider this one of the most crucial questions for the survival of our children and grandchildren, because the planet won’t survive without global compassion. We’ve got to try to see what we can learn from those who have it without training.

Sentient Compassion is when you extend feelings of compassion toward cockroaches, toward any living being. We don’t know whether people who have global compassion have sentient compassion. But my hunch is that if you’ve got sentient, you’ve got global. The Dalai Lama and Darwin agree that sentient is the highest moral virtue.

Heroic Compassion is like altruism with a risk. It has two forms: Immediate Heroic Compassion is when, without thought, you jump onto the subway tracks to rescue someone. It’s impulsive. Considered Heroic Compassion isn’t done impulsively; it’s done with thought, and it can be maintained for many years. Kristen Monroe, a political scientist at the University of California, Irvine, has done a study of people with heroic compassion, and here are her criteria for it: 1) you must act—not just think about how good it would be to act; 2) your goal is the welfare of the other person; 3) your action has consequences for that person; 4) there’s a good possibility your actions will diminish your own welfare—you’re putting yourself at risk; 5) and you have no anticipation of reward or recognition.

The mathematics of being nice
by Michael Marshall / 21 March 2011

Using mathematics to tackle some of biology’s biggest questions, Martin Nowak has concluded that an ability to cooperate is the secret of humanity’s success. He talks to Michael Marshallabout drawing fire from Richard Dawkins, the perils of punishment, and devising the mathematical equivalent of the rules of religion

Q. Why are you so fascinated by our ability to help each other out?
A. Cooperation is interesting because it essentially means that you help someone else, someone who is a potential competitor. You reduce your own success in order to increase the success of somebody else. Why should you do that? Why should natural selection favour such behaviour? To answer these questions I use evolutionary dynamics, evolutionary game theory and experimental tests of human behaviour.

Q. You say there are five different ways in which we cooperate that give us an edge, in terms of natural selection. Tell me about them.
A. The first one is called direct reciprocity. This is when individuals have repeated interactions, so if I help you now, you may help me later. There is also indirect reciprocity, which takes place in groups. If I help you, somebody else might see our interaction and conclude that I’m a helpful person, and help me later. That’s a reciprocal process relying on reputation. The third mechanism is when neighbours help each other – cooperators survive in clusters. This is called spatial selection, and it plays an important role, not only for people but for bacteria, animals and plants. Then there is group selection: it may be that our group of cooperators is better off than another group of defectors: here selection acts on two levels, because in our group there is more cooperation.

Q. Group selection has had a tricky reputation, and has been attacked by evolutionary biologists. Do you think it has now been rehabilitated?
A. The introduction of the concept of group selection, some 40 years ago, was imprecise. But recent mathematical models explain very clearly when group selection can promote the evolution of cooperation. There must be competition between groups and migration rates should be low.

Q. Unless I’ve lost count, there should be one mechanism left.
A. The last one is kin selection, which can occur when you help a close relative.

Q. You published a paper on kin selection last year that caused a bit of controversy.
A. I have no problem with kin selection when it is properly formulated. My criticism is directed against the current use of inclusive fitness theory, which is the dominant mathematical approach used to study aspects of kin selection.

Q. Can you explain?
A. Inclusive fitness theory assumes that the personal fitness of an individual can be partitioned into components caused by individual actions. This restrictive assumption implies that inclusive fitness theory is a limited approach that cannot be used to describe typical situations that arise in social evolution. The standard theory of natural selection does not make such a limiting assumption. In that recent paper we showed that inclusive fitness theory is a subset of the standard theory.

Q. Inclusive fitness is a key concept of evolutionary biology. No wonder that many biologists, including Richard Dawkins, reacted negatively when you attacked it (New Scientist, 2 October 2010, p 8). Do you think people are now coming around to it?
A. I feel that it is beginning to be appreciated. I would say the negative response rests on a misinterpretation of the paper. People think that we are saying relatedness is unimportant, but this is not at all what we said. People who are open-minded are beginning to realise that the results of our paper are beautiful: simple mathematical models based on standard natural selection are sufficient to explain the evolution of eusociality or other phenomena in social evolution. The strange mathematical contortions of inclusive fitness theory are unnecessary. In other words if you are interested in a mathematical description of evolution, a situation can never arise in which you would need an inclusive fitness approach.

Q. You have also been involved in some other big debates. Can you tell me about your work on punishment?
A. Many people feel that punishment is a good thing, that it leads to human cooperation. So their idea is that unless you cooperate with me, I punish you. It might even cost me something to punish you, but I do it because I want to teach you a lesson. One cannot deny that punishment is an important component of human behaviour, but I am sceptical about the idea that it’s a positive component. I have analysed the role of punishment using mathematics and experiments. I think that most uses of punishment are very much for selfish interests, such as defending your position in the group. Punishment leads to retaliation and vendettas. It’s very rare that punishment is used nobly.

Q. Over the years you’ve applied mathematics to a lot of different areas of biology. Is it your aim to put the whole field on a mathematical footing?
A. Yes. It has happened in many disciplines of science. It’s a kind of maturation process. Without a mathematical description, we can get a rough handle on a phenomenon but we can’t fully understand it. In physics, that’s completely clear. You don’t just talk about gravity, you quantify your description of it. The beautiful thing about mathematics is that it can decide an argument. Some things are fiercely debated for years, but with mathematics the issues become clear.

Q. Unlike most evolutionary biologists, you are religious. Do you think it is a problem for the public perception of evolution that it is seen as supporting atheism?
A. In my opinion, a purely scientific interpretation of evolution does not generate an argument in favour of atheism. Science does not disprove God or replace religion. Evolution is not an argument against God, any more than gravity is. Evolution explains the unfolding of life on Earth. The God of Christianity is “that without which there would be no evolution at all”.

Q. So how do you see religion?
A. I see the teachings of world religions as an analysis of human life and an attempt to help. They intend to promote unselfish behaviour, love and forgiveness. When you look at mathematical models for the evolution of cooperation you also find that winning strategies must be generous, hopeful and forgiving. In a sense, the world’s religions hit on these ideas first, thousands of years ago. Now, for the first time, we can see these ideas in terms of mathematics. Who would have thought that you could prove mathematically that, in a world where everybody is out for himself, the winning strategy is to be forgiving, and that those who cannot forgive can never win?

Q. Do you feel isolated from other evolutionary biologists because of your religious beliefs?
A. No, I don’t think it’s an issue. I once had a great discussion with another biologist about science and religion. He was deeply religious. Two weeks later I read that he had been made head of the US National Institutes of Health. He is Francis Collins.

{Martin Nowak is professor of mathematics and biology at Harvard University. He has a PhD from the University of Vienna, Austria, became professor of theoretical biology at the University of Oxford aged 32, then moved to Princeton University and later to Harvard. His book SuperCooperators: Altruism, evolution, and why we need each other to succeed, co-authored with Roger HighfieldNew Scientist‘s editor, is out this month.}