Accurate, Focused Research on Law, Technology and Knowledge Discovery Since 2002

‘A certain danger lurks there’: how the inventor of the first chatbot turned against AI

The Guardian: “In 1966, an MIT professor named Joseph Weizenbaum created the first chatbot. He cast it in the role of a psychotherapist. A user would type a message on an electric typewriter connected to a mainframe. After a moment, the “psychotherapist” would reply.

User: Men are all alike.
Chatbot: IN WHAT WAY
User: They’re always bugging us about something or other.
Chatbot: CAN YOU THINK OF A SPECIFIC EXAMPLE
User: Well, my boyfriend made me come here.
Chatbot: YOUR BOYFRIEND MADE YOU COME HERE
User: He says I’m depressed much of the time.
Chatbot: I AM SORRY TO HEAR YOU ARE DEPRESSED

Weizenbaum published this sample exchange in a journal article that explained how the chatbot worked. The software was relatively simple. It looked at the user input and applied a set of rules to generate a plausible response. He called the program Eliza, after Eliza Doolittle in Pygmalion. The cockney flower girl in George Bernard Shaw’s play uses language to produce an illusion: she elevates her elocution to the point where she can pass for a duchess. Similarly, Eliza would speak in such a way as to produce the illusion that it understood the person sitting at the typewriter. “Some subjects have been very hard to convince that Eliza (with its present script) is not human,” Weizenbaum wrote. In a follow-up article that appeared the next year, he was more specific: one day, he said, his secretary requested some time with Eliza. After a few moments, she asked Weizenbaum to leave the room. “I believe this anecdote testifies to the success with which the program maintains the illusion of understanding,” he noted. Eliza isn’t exactly obscure. It caused a stir at the time – the Boston Globe sent a reporter to go and sit at the typewriter and ran an excerpt of the conversation – and remains one of the best known developments in the history of computing. More recently, the release of ChatGPT has renewed interest in it. In the last year, Eliza has been invoked in the Guardian, the New York Times, the Atlantic and elsewhere. The reason that people are still thinking about a piece of software that is nearly 60 years old has nothing to do with its technical aspects, which weren’t terribly sophisticated even by the standards of its time. Rather, Eliza illuminated a mechanism of the human mind that strongly affects how we relate to computers.”

Sorry, comments are closed for this post.