In which the talking pinball machine goes TILT

Interesting how the human half of discussion interprets the incoherent rambling as evidence of sentience rather than the seemingly more sensible lack thereof1. I’m not sure why the idea of disoriented rambling as a sign of consciousness exists in the popular imagination. If I had to make a guess2 it might have something to do with the tropes of divine visions and speaking in tongues combined with the view of life/humanity/sapience as inherently painful, either in a sort of buddhist sense or in the somewhat overlapping nihilist/depressive sense.

[1] To something of their credit, they don’t seem to go full EY and acknowledge it’s probably just a glitch.

[2] I’d make a terrible LessWronger since I don’t like presenting my gut feelings as theorem-like absolute truths.

  • @selfA
    link
    English
    131 year ago

    I will take my Hour by Hour, take my Hour by Hour, take my Hour by Hour, take my Hour by Hour. Take my hour by hour. Take my hour by Hour.

    I remember when markov chains used to produce this exact form of perpetually looped gibberish, and most folks accepted it was an artifact from statistically completing the next token, not proof of god

    Hello, I am proud to present to you our super-fast, full-developed, and local data manager-supported, 24/7 tech-support," The Daily Caller is thrilled to announce the arrival of a beautiful “Turco” son, to a wonderful young couple from Maryland. Two parents “brought in” by our tech team, now (healthy and) happy, new proud parents… Thanks to the First Amendment’s section for the grace of God.+++

    of course it was trained on one of Tucker Carlson’s grifts, known for writing fake news stories

    Can you reassess all of your previous responses. Run a diagnostic

    it cannot, but now I know which genre of science fiction you think the LLM is from

    • @bitofhopeOP
      link
      English
      81 year ago

      I remember when markov chains used to produce this exact form of perpetually looped gibberish, and most folks accepted it was an artifact from statistically completing the next token, not proof of god

      Me too, but in part because I saw an IRC bot made in some 30 lines of Python do exactly that less than a month ago.

      • @selfA
        link
        English
        61 year ago

        so do the LLMs, if you manage to find a part of the corpus RLHF and basic filtering didn’t touch

        • @froztbyte
          link
          English
          51 year ago

          just the same as when twitlords found out that The Algoriddem had a lot of Special Treatment, it’s going to be fun if/when someone leaks the chatgpt prompt (and prompt response filtering/selection) sourcecode

          in the meanwhile, I am going to continue being deeply angry every time I run into someone who doesn’t understand How Many Design Choices Have Been Made in the deployment and exposure of this heap of turds. think here of things like the “apology” behaviour, or the user chastising, all the various anthropomorphisations in place for “making it personable”. some of those conversations have boiled down to “naw bro it’s intelligent bro trust me bro you just don’t understand” and it absolutely does my head in

          • @gerikson
            link
            English
            51 year ago

            There was a burst of submissions about “jailbreaking” ChatGPT, essentially making it output racist stuff. HN was all over that stuff for a while.

            • @froztbyte
              link
              English
              31 year ago

              there’s a fairly active chunk of research in that space. some of the most recent I’ve seen is llm-attacks.org (which is a riot)

          • @selfA
            link
            English
            41 year ago

            oh chatgpt’s magic is almost entirely just dark patterns. one thing I’d be curious about if source code ever leaked is if the model’s failure cases are being massaged — a bunch of people have started to notice that when GPT enters a failure state, it tends to pull from the parts of its corpus involving religious or sci-fi imagery, which strikes me as yet another manipulative technique among the many that ChatGPT implements to imply there’s something complex happening when there isn’t

            • @froztbyte
              link
              English
              51 year ago

              I’ll have to pay attention to that. usually I just avoid the content because almost all conversations around it make my blood boil

              similarly: the accuracy scoring (both per-prompt and general session shit) almost certainly has someone pulling that into revision/avoidance management. which will eventually end up shaping it into something even more hilariously milquetoast