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.
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?