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

  • yesman@lemmy.worldOP
    link
    fedilink
    English
    arrow-up
    20
    arrow-down
    10
    ·
    edit-2
    11 months ago

    Ethical theories and the concept of free will depend on agency and consciousness. Things as you point out, LLMs don’t have. Maybe we’ve got it all twisted?

    I’m not anthropomorphising ChatGPT to suggest that it’s like us, but rather that we are like it.

    Edit: “stochastic parrot” is an incredibly clever phrase. Did you come up with that yourself or did the irony of repeating it escape you?

    • 0ops@lemm.ee
      link
      fedilink
      English
      arrow-up
      15
      arrow-down
      3
      ·
      edit-2
      11 months ago

      I feel like this is going to become the next step in science history where once again, we reluctantly accept that homo sapiens are not at the center of the universe. Am I conscious? Am I not a sophisticated prediction algorithm, albiet with more dimensions of input and output? Please, someone prove it

      I’m not saying, and I don’t believe that chatgtp is comparable to human-level consciousness yet, but honestly I think that we’re way closer than many people give us credit for. The neutral networks we’ve built so far train on very specific and particular data for a matter of hours. My nervous system has been collecting data from dozens of senses 24/7 since embryo, and that doesn’t include hard-coded instinct, arguably “trained” via evolution itself for millions of years. How could a llm understand an entity in terms outside of language? How can you understand an entity in terms outside of your own senses?

      • sunbeam60@lemmy.one
        link
        fedilink
        English
        arrow-up
        4
        arrow-down
        1
        ·
        11 months ago

        I’d give you two upvotes if I could.

        We know how a neural network works in the brain. Unless you’re religious and believe in a soul, you’ve only got the reward model and any in-born setup left.

        My belief is the consciousness is just the mind receiving a significant amount of constant input and reacting to it. We refuse to feel an LLM is conscious because it receives extremely little input (and probably that it isn’t simulating a neural network as large as ours, yet).

        • Sekoia@lemmy.blahaj.zone
          link
          fedilink
          English
          arrow-up
          8
          ·
          11 months ago

          Neural networks are named like that because they’re based on a model of neurons from the 50s, which was then adapted further to work better with computers (so it doesn’t resemble the model much anymore anyway). A more accurate term is Multi-Layer Perceptron.

          We now know this model is… effectively completely wrong.

          Additionally, the main part (or glue, really) of LLMs is not even an MLP, but a “self-attention” layer. You can’t say LLMs work like a brain, because they don’t. The rest is debatable but it’s important to remember that there are billions of dollars of value in selling the dream of conscious AI.

        • grabyourmotherskeys@lemmy.world
          link
          fedilink
          English
          arrow-up
          2
          ·
          11 months ago

          One of the things our sensory system and brain do is limit our input. The road to agi might involve giving it everything and finding the optimum set of filters, not selecting input and training up from that.

          You’d need the baseline set of systems (“baby agi”) and then turn it loose with goal seeking.

          • sunbeam60@lemmy.one
            link
            fedilink
            English
            arrow-up
            2
            ·
            11 months ago

            Yup, broadly agreed. I’m not saying “give it everything”. I’m sure regions would develop to simplify processing via filtering.

    • Bilb!@lem.monster
      link
      fedilink
      English
      arrow-up
      5
      ·
      11 months ago

      Stochastic Parrot

      For what it’s worth: https://en.wikipedia.org/wiki/Stochastic_parrot

      The term was first used in the paper “On the Dangers of Stochastic Parrots: Can Language Models Be Too Big? 🦜” by Bender, Timnit Gebru, Angelina McMillan-Major, and Margaret Mitchell (using the pseudonym “Shmargaret Shmitchell”). The paper covered the risks of very large language models, regarding their environmental and financial costs, inscrutability leading to unknown dangerous biases, the inability of the models to understand the concepts underlying what they learn, and the potential for using them to deceive people. The paper and subsequent events resulted in Gebru and Mitchell losing their jobs at Google, and a subsequent protest by Google employees.