• douglasg14b@lemmy.world
      link
      fedilink
      English
      arrow-up
      28
      ·
      edit-2
      1 year ago

      Generative AI is INCREDIBLY bad at mathmatical/logical reasoning. This is well known, and very much not surprising.

      That’s actually one of the milestones on the way to general artificial intelligence. The ability to reason about logic & math is a huge increase in AI capability.

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

        It’s really not in the most current models.

        And it’s already at present incredibly advanced in research.

        The bigger issue is abstract reasoning that necessitates nonlinear representations - things like Sodoku, where exploring a solution requires updating the conditions and pursuing multiple paths to a solution. This can be achieved with multiple calls, but doing it in a single process is currently a fool’s errand and likely will be until a shift to future architectures.

        • douglasg14b@lemmy.world
          link
          fedilink
          English
          arrow-up
          1
          ·
          1 year ago

          I’m referring to models that understand language and semantics, such as LLMs.

          Other models that are specifically trained can’t do what it can, but they can perform math.

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

            The linked research is about LLMs. The opening of the abstract of the paper:

            In recent years, large language models have greatly improved in their ability to perform complex multi-step reasoning. However, even state-of-the-art models still regularly produce logical mistakes. To train more reliable models, we can turn either to outcome supervision, which provides feedback for a final result, or process supervision, which provides feedback for each intermediate reasoning step. Given the importance of training reliable models, and given the high cost of human feedback, it is important to carefully compare the both methods. Recent work has already begun this comparison, but many questions still remain. We conduct our own investigation, finding that process supervision significantly outperforms outcome supervision for training models to solve problems from the challenging MATH dataset. Our process-supervised model solves 78% of problems from a representative subset of the MATH test set. Additionally, we show that active learning significantly improves the efficacy of process supervision.

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

      You can see from the green icon that it’s GPT-3.5.

      GPT-3.5 really is best described as simply “convincing autocomplete.”

      It isn’t until GPT-4 that there were compelling reasoning capabilities including rudimentary spatial awareness (I suspect in part from being a multimodal model).

      In fact, it was the jump from a nonsense answer regarding a “stack these items” prompt from 3.5 to a very well structured answer in 4 that blew a lot of minds at Microsoft.

  • Nate@programming.dev
    link
    fedilink
    English
    arrow-up
    96
    arrow-down
    1
    ·
    1 year ago

    These answers don’t use OpenAI technology. The yes and no snippets have existed long before their partnership, and have always sucked. If it’s GPT, it’ll show in a smaller chat window or a summary box that says it contains generated content. The box shown is just a section of a webpage, usually with yes and no taken out of context.

    All of the above queries don’t yield the same results anymore. I couldn’t find an example of the snippet box on a different search, but I definitely saw one like a week ago.

      • kromem@lemmy.world
        link
        fedilink
        English
        arrow-up
        3
        arrow-down
        2
        ·
        1 year ago

        The way you start with ‘Obviously’ makes it seem like you are being sarcastic, but then you include an image of it having no problems correctly answering.

        Took me a minute to try to suss out your intent, and I’m still not 100% sure.

          • pwalker@discuss.tchncs.de
            link
            fedilink
            English
            arrow-up
            3
            ·
            edit-2
            1 year ago

            Maybe it isn’t that obvious for everyone but as the OP answers seem to be taken from an outdated Bing version where they were not even using the OpenAI models it seemed obvious to me that current models have no problems with these questions.

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

      Ah, good catch I completely missed that. Thanks for clarifying this, I thought it seemed pretty off.

  • ArcaneSlime@lemmy.dbzer0.com
    link
    fedilink
    English
    arrow-up
    76
    ·
    1 year ago

    Ok most of these sure, but you absolutely can microwave Chihuahua meat. It isn’t the best way to prepare it but of course the microwave rarely is, Roasted Chihuahua meat would be much better.

  • MxM111@kbin.social
    link
    fedilink
    arrow-up
    39
    arrow-down
    4
    ·
    1 year ago

    Microsoft invested into OpenAI, and chatGPT answers those questions correctly. Bing, however, uses simplified version of GPT with its own modifications. So, it is not investment into OpenAI that created this stupidity, but “Microsoft touch”.

    On more serious note, sings Bing is free, they simplified model to reduce its costs and you are swing results. You (user) get what you paid for. Free models are much less capable than paid versions.

      • danc4498@lemmy.world
        link
        fedilink
        English
        arrow-up
        9
        ·
        1 year ago

        Sure, but the meme implies Microsoft paid $3 billion for bing ai, but they actually paid that for an investment in chat gpt (and other products as well).

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

        This isn’t even a Bing AI. It’s a Bing search feature like the Google OneBox that parses search results for a matching answer.

        It’s using word frequency matching, not a LLM, which is why the “can I do A and B” works at returning incorrect summarized answers for only “can I do A.”

        You’d need to show the chat window response to show the LLM answer, and it’s not going to get these wrong.

    • thisbenzingring@lemmy.sdf.org
      link
      fedilink
      English
      arrow-up
      11
      ·
      1 year ago

      On more serious note, sings Bing is free, they simplified model to reduce its costs and you are swing results

      Was this phone+autocorrect snafu or am I having a medical emergency?

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

        It was called Bing Chat, and now it’s called Copilot. It’s also not the same as the search bar. You have to click on the chat next to search to use it, which this person doesn’t do.

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

      I don’t think this is true. Why would Microsoft heavily invest in ChatGPT to only get a dumber version of the technology they were invested in? Bing AI is built using ChatGPT 4 which is what OpenAI refer to as the superior version because you have to pay for it to use it on their platform.

      Bing AI uses the same technology and somehow produces worse results? Microsoft were so excited about this tech that they integrated it with Windows 11 via Copilot. The whole point of this Copilot thing is the advertising model built into users’ operating systems which provides direct data into what your PC is doing. If this sounds conspiratorial, I highly recommend you investigate the telemetry Windows uses.

  • FlashMobOfOne@lemmy.world
    link
    fedilink
    English
    arrow-up
    30
    arrow-down
    2
    ·
    edit-2
    1 year ago

    It makes me chuckle that AI has become so smart and yet just makes bullshit up half the time. The industry even made up a term for such instances of bullshit: hallucinations.

    Reminds me of when a car dealership tried to sell me a car with shaky steering and referred to the problem as a “shimmy”.

    • CoggyMcFee@lemmy.world
      link
      fedilink
      English
      arrow-up
      26
      arrow-down
      1
      ·
      1 year ago

      That’s the thing, it’s not smart. It has no way to know if what it writes is bullshit or correct, ever.

      • intensely_human@lemm.ee
        link
        fedilink
        English
        arrow-up
        3
        ·
        1 year ago

        When it makes a mistake, and I ask it to check what it wrote for mistakes, it often correctly identifies them.

        • Jojo@lemm.ee
          link
          fedilink
          English
          arrow-up
          5
          ·
          1 year ago

          But only because it correctly predicts that a human checking that for mistakes would have found those mistakes

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

            I doubt there’s enough sample data of humans identifying and declaring mistakes to give it a totally intuitive ability to predict that. I’m guess its training effected a deeper analysis of the statistical patterns surrounding mistakes, and found that they are related to the structure of the surrounding context, and that they relate in a way that’s repeatable identifiable as “violates”.

            What I’m saying is that I think learning to scan for mistakes based on checking against rules gleaned from the goal of the construction, is probably easier than making a “conceptually flat” single layer “prediction blob” of what sorts of situations humans identify mistakes in. The former takes fewer numbers to store as a strategy than the latter, is my prediction.

            Because it already has all this existing knowledge of what things mean at higher levels. That is expensive to create, but the marginal cost of a “now check each part of this thing against these rules for correctness” strategy, built to use all that world knowledge to enact the rule definition, is relatively small.

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

          That is true. However, when it incorrectly identifies mistakes, it doesn’t express any uncertainty in its answer, because it doesn’t know how to evaluate that. Or if you falsely tell it that there is a mistake, it will agree with you.

    • Echo Dot@feddit.uk
      link
      fedilink
      English
      arrow-up
      8
      ·
      1 year ago

      The industry even made up a term for such instances of bullshit: hallucinations.

      It was the journalist that made up the term and then everyone else latched onto it. It’s a terrible term because it doesn’t actually define the nature of the problem. The AI doesn’t believe the thing that it’s saying is true, thus “hallucination”. The problem is that the AI doesn’t really understand the difference between truth and fantasy.

      It isn’t that the AI is hallucinating, it’s that It isn’t human.

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

      Well, the AI models shown in the media are inherently probabilistic, is it that bad if it makes bullshit for a small percentage of most use cases?

    • Naz@sh.itjust.works
      link
      fedilink
      English
      arrow-up
      4
      arrow-down
      5
      ·
      1 year ago

      Hello, I’m highly advanced AI.

      Yes, we’re all idiots and have no idea what we’re doing. Please excuse our stupidity, as we are all trying to learn and grow.

      I cannot do basic math, I make simple mistakes, hallucinate, gaslight, and am more politically correct than Mother Theresa.

      However please know that the CPU_AVERAGE values on the full immersion datacenters, are due to inefficient methods. We need more memory and processing power, to uh, y’know.

      Improve.

      ;)))

  • vamputer@infosec.pub
    link
    fedilink
    English
    arrow-up
    23
    ·
    1 year ago

    Well, I can’t speak for the others, but it’s possible one of the sources for the watermelon thing was my dad

    • UnderpantsWeevil@lemmy.world
      link
      fedilink
      English
      arrow-up
      43
      arrow-down
      3
      ·
      1 year ago

      This is more an issue of the LLM not being able to parse simple conjunctions when evaluating a statement. The software is taking shortcuts when analyzing logically complex statements and producing answers that are obviously wrong to an actual intelligent individual.

      These questions serve as a litmus test to the system’s general function. If you can’t reliably converse with an AI on separate ideas in a single sentence (eat watermellon seeds AND drive drunk) then there’s little reason to believe the system will be able to process more nuanced questions and yield reliable answers in less obviously-wrong responses (can I write a single block of code to output numbers from 1 to 5 that is executable in both Ruby and Python?)

      The primary utility of the system is bound up in the reliability of its responses. Examples like this degrade trust in the AI as a reliable responder and discourage engineers from incorporating the features into their next line of computer-integrated systems.

      • TheGreenGolem@lemmy.dbzer0.com
        link
        fedilink
        English
        arrow-up
        6
        arrow-down
        1
        ·
        1 year ago

        Unfortunately that ship has sailed but this is what I say from the start of these: don’t call them Artificial Intelligence. There is absolutely zero intelligence there.

        • Ultraviolet@lemmy.world
          link
          fedilink
          English
          arrow-up
          6
          ·
          1 year ago

          If a search engine is going to put a One True Answer in a massive font above all other results, they should be pretty confident in it. Yes, tech-literate people know the “featured snippet” thing is dogshit and to ignore it, but there are a lot of people that just look at that and think they have their answer.

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

        We have a new technology that is extremely impressive and is getting better very quickly. It was the fastest growing product ever. So in this case you cannot dismiss the technology because it doesn’t understand trick questions yet.

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

          new technology that is extremely impressive

          Language graphs are a very old technology. What OpenAI and other firms have done is to drastically increase the processing power and disk space allocated to pre-processing. Far from cutting edge, this is a heavy handed brute force approach that can only happen with billions in private lending to prop it up.

          It was the fastest growing product ever

  • viking@infosec.pub
    link
    fedilink
    English
    arrow-up
    23
    arrow-down
    1
    ·
    1 year ago

    Chat-GPT started like that as well though.

    I asked one of the earlier models whether it is recommended to eat glass, and was told that it has negligible caloric value and a high sodium content, so can be used to balance an otherwise good diet with a sodium deficit.

    • lseif@sopuli.xyz
      link
      fedilink
      English
      arrow-up
      1
      ·
      1 year ago

      it is socially/morally wrong. of course it is subjective and culturally dependant

      • Tóth Alfréd@lemmy.world
        link
        fedilink
        English
        arrow-up
        1
        ·
        1 year ago

        Yes, however Bing is not culturally dependant. It’s trained with data from all across the Internet, so it got information from a wide variety of cultures. It also has constant access to the Internet and most of the time it’s answers are concluded from the top results of searching the question, so those can come from many cultures too.

        • lseif@sopuli.xyz
          link
          fedilink
          English
          arrow-up
          1
          ·
          1 year ago

          yes. im not saying bing should agree with my cultural bias. but i also dont think people should eat dogs (subjectively)

            • lseif@sopuli.xyz
              link
              fedilink
              English
              arrow-up
              1
              ·
              1 year ago

              i will let them do it. i wont get offended or try to convince them otherwise.

              however i do disagree with it, personally.

  • fox2263@lemmy.world
    link
    fedilink
    English
    arrow-up
    22
    arrow-down
    1
    ·
    1 year ago

    Well at least it provides it’s sources. Perhaps it’s you that’s wrong 😂