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

  • AWittyUsername@lemmy.world
    link
    fedilink
    English
    arrow-up
    62
    ·
    1 year ago

    I’ve never had ChatGPT just say “actually I don’t know the answer” it just gives me confidently correct wrong information instead.

    • canihasaccount@lemmy.world
      link
      fedilink
      English
      arrow-up
      23
      ·
      edit-2
      1 year ago

      GPT-4 will. For example, I asked it the following:

      What is the neighborhood stranger model of fluid mechanics?

      It responded:

      The “neighborhood stranger model” of fluid mechanics is not a recognized term or concept within the field of fluid mechanics, as of my last update in April 2023.

      Now, obviously, this is a made-up term, but GPT-4 didn’t confidently give an incorrect answer. Other LLMs will. For example, Bard says,

      The neighborhood stranger model of fluid mechanics is a simplified model that describes the behavior of fluids at a very small scale. In this model, fluid particles are represented as points, and their interactions are only considered with other particles that are within a certain “neighborhood” of them. This neighborhood is typically assumed to be a sphere or a cube, and the size of the neighborhood is determined by the length scale of the phenomena being studied.

      • butterflyattack@lemmy.world
        link
        fedilink
        English
        arrow-up
        7
        ·
        1 year ago

        Interestingly, the answer from bard sounds like it could be true. I don’t know shit about fluid dynamics but it seems pretty plausible.

        • Socsa@sh.itjust.works
          link
          fedilink
          English
          arrow-up
          3
          ·
          1 year ago

          Because it is describing a real numerical solver method which is reasonably well stated by that particular made up phrase. In a way, I can see how there is value to this, since in engineering and science there are often a lot of names for the same underlying model. It would be nice if it did both tbh - admit that it doesn’t recognize the specific language, while providing a real, adjacent terminology. Like, if I slightly misremember a technical term, it should be able to figure out what I actually meant by it.

    • CoggyMcFee@lemmy.world
      link
      fedilink
      English
      arrow-up
      21
      ·
      edit-2
      1 year ago

      That is, I guess, because it doesn’t actually know anything, even things it’s accurate about, so it has no way to determine if it knows the answer or not.

    • EnderMB@lemmy.world
      link
      fedilink
      English
      arrow-up
      12
      ·
      1 year ago

      Funny enough, that’s one of the reasons why big companies that heavily use AI didn’t initially invest heavily into LLM’s. They are known to hallucinate, and often hilariously badly, so it was hard for the likes of Google and co to put their rep behind something that’ll be very wrong.

      As it turns out, people don’t care if your AI is racist, uses heavily amounts of PII, teaches you to make napalm, or gives you incorrect health advice for serious illnesses - if it can write a doc really well, then all is forgiven.

      In many ways, it’s actually quite funny to project meaning and intent on AI, because it’s essentially a reflection of what it was trained on - our words. What’s not so funny is that the projection isn’t particularly nice…

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

        What’s not so funny is that you look at that reflection and see just the most unlikeable cunt you’ve ever laid eyes on, and like a turd falling from on high upon your dinner plate, now you’ve got to figure out what to do with this shit. (pro tip: blame capitalism)

    • I fucking love when my students bring “chat” in as their tutor and show me the logic they followed… Bro, ChatGPT knows the correct answer, but you asked a bad question and it gave you its best guess hidden as a factual statement.

      To be fair, I spend a lot of time teaching my students how to use LLMs to get the best results while avoiding “leading the witness.”

      • merc@sh.itjust.works
        link
        fedilink
        English
        arrow-up
        10
        ·
        1 year ago

        ChatGPT knows the correct answer

        It doesn’t “know” the correct answer. It may have been trained on text which contains the answer, and you may be able to coax it into generating a version of that text. But, it will just as happily generate something that sounds somewhat like what it was trained on, with words that are almost as probable as the originals, but with completely different meanings.

    • SasquatchBanana@lemmy.world
      link
      fedilink
      English
      arrow-up
      4
      ·
      1 year ago

      The only times I’ve seen this is when it says their information is from like 2019 so they don’t know. But this is very fringe things.

    • June@lemm.ee
      link
      fedilink
      English
      arrow-up
      2
      ·
      1 year ago

      I’ve had it tell me that it cant find anything about a question. But it’s usually when I ask for sources, frame the question as ‘is there anything online’, or otherwise ask it to do some research. If I just ask it a naked question it’ll always give an answer.

    • cannache@slrpnk.net
      link
      fedilink
      English
      arrow-up
      1
      ·
      1 year ago

      Well that’s a surprise. Never used one so far as I know so I wouldn’t know much but from what I’ve seen, having done my research, it’s kinda helpful but not exactly the best tool for every job, I still prefer just manually going through things but hey I wouldn’t know much since perhaps I just haven’t come across using it in my line of work yet