So this is not uninteresting:

[eppur_se_muova]

46. You might be interested in this old article, if you haven't already seen it:

Weizenbaum’s nightmares: how the inventor of the first chatbot turned against AI

Computer scientist Joseph Weizenbaum was there at the dawn of artificial intelligence – but he was also adamant that we must never confuse computers with humans
By Ben Tarnoff
Tue 25 Jul 2023 00.00 EDT
Last modified on Fri 1 Sep 2023 00.00 EDT

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.

Early in his career, Sigmund Freud noticed that his patients kept falling in love with him. It wasn’t because he was exceptionally charming or good-looking, he concluded. Instead, something more interesting was going on: transference. Briefly, transference refers to our tendency to project feelings about someone from our past on to someone in our present. While it is amplified by being in psychoanalysis, it is a feature of all relationships. When we interact with other people, we always bring a group of ghosts to the encounter. The residue of our earlier life, and above all our childhood, is the screen through which we see one another.
***
more: https://www.theguardian.com/technology/2023/jul/25/joseph-weizenbaum-inventor-eliza-chatbot-turned-against-artificial-intelligence-ai


When PCs first started moving into homes, I remember even kids could get a copy of ELIZA and run it on those simple 80's platforms. So it can't be all that complicated. I wonder how hard it would be to "blowgrade" ELIZA into a ChatDJT that gives authentic-sounding Trumpian responses ? Make it into viral shareware and see how much people get out of comparing DJT's actual pronouncements with the slop from ChatDJT -- would that discredit Turnip in some diehards' eyes ?