“Notably, O3-MINI, despite being one of the best reasoning models, frequently skipped essential proof steps by labeling them as “trivial”, even when their validity was crucial.”

  • Pennomi@lemmy.world
    link
    fedilink
    English
    arrow-up
    0
    ·
    10 hours ago

    LLMs are a lot more sophisticated than we initially thought, read the study yourself.

    Essentially they do not simply predict the next token, when scientists trace the activated neurons, they find that these models plan ahead throughout inference, and then lie about those plans when asked to say how they came to a conclusion.

    • swlabr@awful.systems
      link
      fedilink
      English
      arrow-up
      0
      ·
      9 hours ago

      You didn’t link to the study; you linked to the PR release for the study. This is the study.

      Note that the paper hasn’t been published anywhere other than on Anthropic’s online journal. Also, what the paper is doing is essentially a tea leaf reading. They take a look at the swill of tokens, point at some clusters, and say, “there’s a dog!” or “that’s a bird!” or “bitcoin is going up this year!”. It’s all rubbish dawg

      • Pennomi@lemmy.world
        link
        fedilink
        English
        arrow-up
        0
        ·
        8 hours ago

        Fair enough, you’re the only person with a reasonable argument, as nobody else can seem to do anything other than name calling.

        Linking to the actual papers and pointing out they haven’t been published to a third party journal is far more productive than whatever anti-scientific bullshit the other commenters are doing.

        We should be people of science, not reactionaries.

        • self@awful.systems
          link
          fedilink
          English
          arrow-up
          0
          ·
          5 hours ago

          you got banned before I got to you, but holy fuck are you intolerable

          We should be people of science, not reactionaries.

          which we should do by parroting press releases and cherry picking which papers count as science, of course

          but heaven forbid anyone is rude when they rightly tell you to go fuck yourself

        • Soyweiser@awful.systems
          link
          fedilink
          English
          arrow-up
          0
          ·
          8 hours ago

          reactionaries

          So, how does any of this relate to wanting to go back to an imagined status quo ante? (yes, I refuse to use reactionary in any other way than to describe politcal movements. Conservatives do not can fruits).

          • froztbyte@awful.systems
            link
            fedilink
            English
            arrow-up
            0
            ·
            4 hours ago

            nah I think it just sits weirdly with people (I can see what you mean but also why it would strike someone as frustrating)

        • scruiser@awful.systems
          link
          fedilink
          English
          arrow-up
          0
          ·
          edit-2
          8 hours ago

          This isn’t debate club or men of science hour, this is a forum for making fun of idiocy around technology. If you don’t like that you can leave (or post a few more times for us to laugh at before you’re banned).

          As to the particular paper that got linked, we’ve seen people hyping LLMs misrepresent their research as much more exciting than it actually is (all the research advertising deceptive LLMs for example) many many times already, so most of us weren’t going to waste time to track down the actual paper (and not just the marketing release) to pick apart the methods. You could say (raises sunglasses) our priors on it being bullshit were too strong.

        • froztbyte@awful.systems
          link
          fedilink
          English
          arrow-up
          0
          ·
          edit-2
          8 hours ago

          your argument would be immensely helped if you posted science instead of corporate marketing brochures

      • swlabr@awful.systems
        link
        fedilink
        English
        arrow-up
        0
        ·
        9 hours ago

        It’s an anti-fun version of listening to dark side of the moon while watching the wizard of oz.

    • V0ldek@awful.systems
      link
      fedilink
      English
      arrow-up
      0
      ·
      edit-2
      9 hours ago

      read the study yourself

      • > ask the commenter if it’s a study or a self-interested blog post
      • > they don’t understand
      • > pull out illustrated diagram explaining that something hosted exclusively on the website of the for-profit business all authors are affiliated with is not the same as a peer-reviewed study published in a real venue
      • > they laugh and say “it’s a good study sir”
      • > click the link
      • > it’s a blog post
      • Soyweiser@awful.systems
        link
        fedilink
        English
        arrow-up
        0
        ·
        8 hours ago

        I wonder if they already made up terms like ‘bloggophobic’ or ‘peer review elitist’ in that ‘rightwinger tries to use leftwing language’ way.

    • vane@lemmy.world
      link
      fedilink
      English
      arrow-up
      0
      ·
      9 hours ago

      This study is bullshit, because they only trace evaluations and not trace training process that align tokens with probabilities.

        • vane@lemmy.world
          link
          fedilink
          English
          arrow-up
          0
          ·
          9 hours ago

          Well, every civilisation needs it’s prophets. Our civilisation built prophet machines that will kill us. We just didn’t get to the killing step yet.

          • froztbyte@awful.systems
            link
            fedilink
            English
            arrow-up
            0
            ·
            9 hours ago

            yeah but see, these grifters all heard it as “every civilisation needs its profits”. just a shame they suck at that too

            • vane@lemmy.world
              link
              fedilink
              English
              arrow-up
              0
              ·
              8 hours ago

              No prophet worked for free and they were always near the rullers and near big money. The story repeats itself, just the times are different and we can instant message with each other.

    • bitofhope@awful.systems
      link
      fedilink
      English
      arrow-up
      0
      ·
      10 hours ago

      Essentially they do not simply predict the next token

      looks inside

      it’s predicting the next token

      • froztbyte@awful.systems
        link
        fedilink
        English
        arrow-up
        0
        ·
        10 hours ago

        every time I read these posters it’s in that type of the Everyman characters in the discworld that say some utter lunatic shit and follow it up with “it’s just [logical/natural/obvious/…]”

      • Pennomi@lemmy.world
        link
        fedilink
        English
        arrow-up
        0
        ·
        10 hours ago

        Read the paper, it’s not simply predicting the next token. For instance, when writing a rhyming couplet, it first plans ahead on what the rhyme is, and then fills in the rest of the sentence.

        The researchers were surprised by this too, they expected it to be the other way around.

        • bitofhope@awful.systems
          link
          fedilink
          English
          arrow-up
          0
          ·
          9 hours ago

          Oh, sorry, I got so absorbed into reading the riveting material about features predicting state name tokens to predict state capital tokens I missed that we were quibbling over the word “next”. Alright they can predict tokens out of order, too. Very impressive I guess.

        • froztbyte@awful.systems
          link
          fedilink
          English
          arrow-up
          0
          ·
          edit-2
          9 hours ago

          first plans ahead

          predict

          to declare or tell in advance; prophesy; foretell;

          ahead

          Strongest matches: advanced; along; before; earlier; forward

          stop prompting LLMs and go read some books, it’ll do you a world of good

        • froztbyte@awful.systems
          link
          fedilink
          English
          arrow-up
          0
          ·
          10 hours ago

          pray forgive, fair poster, for the shame I have cast upon myself in the action of doubting the Most Serious Article so affine to yourself - clearly a person of taste and wit, and I deserve the ire and muck resultant

          wait… wait, no, sorry! got those the wrong way around. happens all the time - guess I tried too hard to think like you.