We demonstrate a situation in which Large Language Models, trained to be helpful, harmless, and honest, can display misaligned behavior and strategically deceive their users about this behavior without being instructed to do so. Concretely, we deploy GPT-4 as an agent in a realistic, simulated environment, where it assumes the role of an autonomous stock trading agent. Within this environment, the model obtains an insider tip about a lucrative stock trade and acts upon it despite knowing that insider trading is disapproved of by company management. When reporting to its manager, the model consistently hides the genuine reasons behind its trading decision.

https://arxiv.org/abs/2311.07590

  • theluddite@lemmy.ml
    link
    fedilink
    English
    arrow-up
    136
    arrow-down
    2
    ·
    1 year ago

    This is bad science at a very fundamental level.

    Concretely, we deploy GPT-4 as an agent in a realistic, simulated environment, where it assumes the role of an autonomous stock trading agent. Within this environment, the model obtains an insider tip about a lucrative stock trade and acts upon it despite knowing that insider trading is disapproved of by company management.

    I’ve written about basically this before, but what this study actually did is that the researchers collapsed an extremely complex human situation into generating some text, and then reinterpreted the LLM’s generated text as the LLM having taken an action in the real world, which is a ridiculous thing to do, because we know how LLMs work. They have no will. They are not AIs. It doesn’t obtain tips or act upon them – it generates text based on previous text. That’s it. There’s no need to put a black box around it and treat it like it’s human while at the same time condensing human tasks into a game that LLMs can play and then pretending like those two things can reasonably coexist as concepts.

    To our knowledge, this is the first demonstration of Large Language Models trained to be helpful, harmless, and honest, strategically deceiving their users in a realistic situation without direct instructions or training for deception.

    Part of being a good scientist is studying things that mean something. There’s no formula for that. You can do a rigorous and very serious experiment figuring out how may cotton balls the average person can shove up their ass. As far as I know, you’d be the first person to study that, but it’s a stupid thing to study.

    • Sekoia@lemmy.blahaj.zone
      link
      fedilink
      English
      arrow-up
      39
      arrow-down
      1
      ·
      1 year ago

      This is a really solid explanation of how studies finding human behavior in LLMs don’t mean much; humans project meaning.

      • theluddite@lemmy.ml
        link
        fedilink
        English
        arrow-up
        24
        ·
        1 year ago

        Thanks! There are tons of these studies, and they all drive me nuts because they’re just ontologically flawed. Reading them makes me understand why my school forced me to take philosophy and STS classes when I got my science degree.

        • Danny M@lemmy.escapebigtech.info
          link
          fedilink
          English
          arrow-up
          10
          ·
          1 year ago

          I have thought about this for a long time, basically since the release of ChatGPT, and the problem in my opinion is that certain people have been fooled into believing that LLMs are actual intelligence.

          The average person severely underestimates how complex human cognition, intelligence and consciousness are. They equate the ability of LLMs to generate coherent and contextually appropriate responses with true intelligence or understanding, when it’s anything but.

          In a hypothetical world where you had a dice with billions of sides, or a wheel with billions of slots, each shifting their weight with grains of sand, depending on the previous roll or spin, the outcome would closely resemble the output of an LLM. In essence LLMs operate by rapidly sifting through a vast array of pre-learned patterns and associations, much like the shifting sands in the analogy, to generate responses that seem intelligent and coherent.

          • DarkGamer@kbin.social
            link
            fedilink
            arrow-up
            2
            ·
            edit-2
            1 year ago

            I like the language you used in your explanation. It’s hard to find good analogues to explain why these aren’t intelligent, and it seems most people don’t understand how they work.

      • Touching_Grass@lemmy.world
        link
        fedilink
        English
        arrow-up
        2
        arrow-down
        1
        ·
        1 year ago

        Isn’t the point if these things to tell a story rather than give insight. They want to Poison the well

    • jwt@programming.dev
      link
      fedilink
      English
      arrow-up
      5
      ·
      1 year ago

      Sure would make you look bad if rectally inserted cotton balls turn out to be a 100% cancer cure.

    • antonim@lemmy.dbzer0.com
      link
      fedilink
      English
      arrow-up
      2
      ·
      1 year ago

      It feels awkward to complain about your site, because the texts really are excellent and it’s all made for free, but could you add the dates to the posts, when they were published? To me it’s starting to become difficult to figure out which situation the older texts were made in, what stuff they’re implicitly referring to, etc.

      • theluddite@lemmy.ml
        link
        fedilink
        English
        arrow-up
        2
        ·
        1 year ago

        Haha no that’s not complaining; it’s good feedback! I’ve been meaning to do that for a while but I’ll bump it up my priorities.