In honor of Weizenbaum's Centenary, I asked ChatGPT to program ELIZA

  Now for some real User power.

What's really going to get spooky is someday some ChatGPT descendant is going to write a better ChatGPT and where does that sequence end?

For pre-formatted code leave two spaces at the start of the line.

  Like this.

One observation Bob Bryla made was, count the number of words that begin with 'N' and treat each as a logical-negation. With a very small dictionary of additional negation words (e.g. can't) and a whitelist (e.g. nice) you could tell the sense of a statement or question pretty accurately.

Nope, never, not, nada, na, nobody and on and on.

"Some of ELIZA's responses were so convincing that Weizenbaum and several others have anecdotes of users becoming emotionally attached to the program, occasionally forgetting that they were conversing with a computer.[3] Weizenbaum's own secretary reportedly asked Weizenbaum to leave the room so that she and ELIZA could have a real conversation. Weizenbaum was surprised by this, later writing: "I had not realized ... that extremely short exposures to a relatively simple computer program could induce powerful delusional thinking in quite normal people."

Wikipedia states that a version of ELIZA is still available in emacs under m-x doctor or something similar. Not being an emacs user, I haven't verified that, but I thought it was interesting.

    https://corecursive.com/eliza-with-jeff-shrager/

  // A list of ELIZA's responses 
  const responses = {"I feel": 
                        [ "Why do you feel {0}?", 
                          "What do you think is causing you to feel {0}?", 
                          "Do you often feel {0}?", 
                          "How do you normally deal with feeling {0}?" ],
                     "I want": 
                        [ "Why do you want {0}?", 
                          "What led you to want this?", 
                          "Do you often find yourself wanting {0}?", 
                          "How do you think getting what you want will make you feel?" ], 
                     "I need": 
                        [ "Why do you feel like you need {0}?", 
                          "What led you to feel like you need this?", 
                          "Do you often find yourself feeling like you need {0}?", 
                          "How do you think getting what you need will make you feel?" ] };

  // A list of keywords 
  const keywords = Object.keys(responses);

  // A function that generates a response 
  function generateResponse(input) { 
  
      // Check if the input contains any of the keywords 
      for (let i = 0; i < keywords.length; i++) { 
          if (input.includes(keywords[i])) { 
              // If the input contains a keyword, return a random response 
              // that includes the remainder of the input, with personal 
              // pronouns conjugated correctly 
              const response = responses[keywords[i]][Math.floor(Math.random() * responses[keywords[i]].length)]; 

              return response.replace("{0}", input.substring(keywords[i].length + 1)); 
          } 
      } 
  }
  
  // Test the function 
  console.log(generateResponse("I feel sad")); 
  console.log(generateResponse("I want a new car")); 
  console.log(generateResponse("I need some help"));

> Weizenbaum, for his part, turned away from his own project’s expanding implications. He objected to the idea that something as subtle, intimate, and human as therapy could be reduced to code. He began to argue that fields requiring human compassion and understanding shouldn’t be automated. And he also worried about the same future that Alan Turing had described — one where chatbots regularly fooled people into thinking they were human. – https://99percentinvisible.org/episode/the-eliza-effect/

Out of curiosity, I today asked it to program the ELIZA in MAD-SLIP, the original (and now completely dead and obscure) language that ELIZA was originally written in. My expectation was that it would have no idea what MAD-SLIP is, or maybe would barely have an idea, and in any case would have no chance of doing what I asked and that it would, very reasonably, balk.

Instead, to my shock it made up a completely bogus meaning for the acronym: "Matched Activated Decomposition by Syntactic and Lexical Interchange Program", and actually wrote an ELIZA in this non-existing language, which was in reality just Python code using the rexexp (re) package, and was perfectly fine as far as it went.

Even scarier than confabulating a non-exisistent programming language, it confabulated a citation for it, claiming that it is described in Weizenbaum's Computer Power and Human Reason, which is utterly false!

Sigh. I fear that ChatGPT is merely bringing Weizenbaum's worst fears into reality! A seemingly authoritative AI that simply makes s#!t up! I'm feeling a bit like taking up arms at the moment.