I was trying to do a memory test to see how far back 3.5 could recall information from previous prompts, but it really doesn’t seem to like making pseudorandom seeds. 😆

        • Reil@beehaw.org
          link
          fedilink
          English
          arrow-up
          1
          ·
          1 year ago

          Yeah, between the image compression and resolution, a lot of things that should be ‘gaps’ in the letters are closing up. Like, the ‘s’ in ‘psuedorandom’ or ‘set’ looks like a squished-up ‘g’.

          I can read individual words as I’m looking at them, but I’ve lost the ability to scan the line and parse words in my peripheral vision.

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

          Its in settings. Funny enough this has been an option on almost all browsers since the beginning (ie. Netscape Navigator, as well as IE3)

  • Glide@lemmy.ca
    link
    fedilink
    arrow-up
    7
    ·
    edit-2
    1 year ago

    I regularly use ChatGPT to generate questions for junior high worksheets. You would be surprised how easily it fucks up “generate 20 multiple choice and 10 short answer questions”. Most frequently at about 12-13 multiple choice it gives up and moves on. When I point out its flaw and ask it to finish generating the multiple choice, it continues to find new and unique ways to fuck up coming up with the remaining questions.

    I would say it gives me simple count and recall errors in about 60% of my attempts to use it.

    • DdCno1@beehaw.org
      link
      fedilink
      arrow-up
      15
      ·
      1 year ago

      Consider keeping school the one place in a child’s life where they aren’t bombarded with AI-generated content.

      • NecroMemories@beehaw.org
        link
        fedilink
        arrow-up
        9
        ·
        edit-2
        1 year ago

        In a learning age band so bespoke, and education professionals so highly paid and resourced, I can’t imagine why this would be an attractive option.

        Maybe we let professionals decide what tool is best for their field

        • Glide@lemmy.ca
          link
          fedilink
          arrow-up
          3
          ·
          1 year ago

          Maybe we let professionals decide what tool is best for their field

          Hey, really appreciated. Having random potentially uneducated, inexperienced people chime in on what they think I’m doing wrong in my classroom based on the tiniest snippet of information really shouldn’t matter, but it’s disheartening nontheless.

          While I take their point, I also wouldn’t walk into a garage and tell someone what they’re doing wrong with a vehicle, or tell a doctor I ran into on the streets that they’re misdiagnosing people based on a comment I overheard. Yet, because I work with children, I get this all the time. So, again, appreciated.

          • millie@beehaw.orgOP
            link
            fedilink
            English
            arrow-up
            1
            ·
            1 year ago

            I definitely get that. I do think it’s a little different, though, because every single human being has been a child, while no human has been a car. We tend to have opinions on education because the prevailing wisdom often failed us during our own school years.

            I don’t think that it’s totally unreasonable to expect some amount of input by other people who’ve been through the education system.

      • Glide@lemmy.ca
        link
        fedilink
        arrow-up
        4
        ·
        1 year ago

        I use it as a brainstorming tool. I haven’t had a single question make it as-is to a student’s worksheet. If the tool can’t even count to 20 successfully, I’m not sure how anyone could trust it to generate meaningful questions for an ELA program.

          • millie@beehaw.orgOP
            link
            fedilink
            English
            arrow-up
            0
            ·
            1 year ago

            I haven’t had much luck with it writing stuff from scratch, but it does a great job of helping with debugging and figuring out why complex equations are doing what they’re doing.

            I put together a pretty complex shader recently, and gpt 3.5 did a great job of helping me figure out why it wasn’t doing quite what I wanted.

            I wouldn’t trust it to code anything without my input, but it’s great for advice and explanations and certain kinds of problem solving. Just don’t assume it has the right answer, you still have to do the work

            • jarfil@beehaw.org
              link
              fedilink
              arrow-up
              1
              ·
              1 year ago

              I’ve tried it with languages I don’t know, and it managed to write simple working functions by just iterating over:

              1. Ask it to write the code
              2. Try to run the code, write down any errors
              3. Look up the errors, and ask it to fix them in the code
              4. Repeat from 2 until there are no more errors

              It seems to lose context easily, like if you ask it to fix one error, then another, it might revert the first fix, but asking it to fix both at once, tends to work.

              I think someone could feasibly write several working functions or modules, without knowing much about a given language, as long as they are clear about what they want them to do… but of course spotting obvious errors and fixing them by hand, can be faster. Fixing integration problems is where I think it might get harder (haven’t tried though, could be interesting).

          • Hexarei@programming.dev
            link
            fedilink
            arrow-up
            1
            ·
            1 year ago

            Well, it’s terrible at factual things and counting, and even when it comes to writing code it will often hallucinate APIs and libraries that don’t exist - But when given very limited-scope, specific-domain problems with enough detail and direction, I’ve found it to be fairly competent as a rubber ducky for programming.

            So far I’ve found ChatGPT to be most useful for:

            1. Writing SQL. Seriously, it’s fantastic at writing SQL if you tell it the relevant schema and what you’re trying to achieve.
            2. Brainstorming feature flow - Tell it the different parts of a feature, ask for thoughts on how the user should be guided through the process, and it does a decent job of suggesting ideas.
            3. Generating alternative names/labels for buttons and such. “In X feature, I have a button that does Y when the user has Z. Currently I have that button labelled ‘Start Y’, but it feels robotic and impersonal. List 10 suggestions for what such a button could say to be more personal and friendly.” and the like. My favorite was a button that was labelled “Map Incoming Data to Job Details”. Wound up renaming the whole process to just “Job Ingestion” because it sounded so good.
            4. Reformatting data. Give it a data structure and tell it you want that data in some other data structure, and it is really accurate at reformatting it. I don’t think I’d trust it with a huge amount of data that way, but for an unimportant one-off it was a nice time savings.
      • yum13241@lemm.ee
        link
        fedilink
        arrow-up
        2
        ·
        1 year ago

        Yes. Don’t be that one teacher who always has one multiple choice question that has no right answer.

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

        As long as the content is manually overseen before being handed to students I can’t see why it would matter.

        A school question is a school question no matter who or what made it.

    • millie@beehaw.orgOP
      link
      fedilink
      English
      arrow-up
      3
      ·
      1 year ago

      Oooh, so maybe it’s the term ‘non-repeating’ that’s actually tripping it?

      • Turun@feddit.de
        link
        fedilink
        arrow-up
        5
        ·
        1 year ago

        No, the request is fine. But once it fucks up and starts generating a long string of a single number the output is censored, because it is similar to how a recent data extraction attack works.

        • Gamma@beehaw.org
          link
          fedilink
          English
          arrow-up
          8
          ·
          1 year ago

          Amazing how much duct tape they’re having to slap over fundamental flaws

          • ZickZack@fedia.io
            link
            fedilink
            arrow-up
            1
            ·
            1 year ago

            The problem is that the model is actually doing exactly what it’s supposed to, it’s just not what openai wants it to do. The reason the prompt extraction method works is because the underlying statistical model gets shifted far outside the domain of “real” language. In that case the correct maximizing posterior becomes a sample from the prior (here that would be a sample from the dataset, this is combined with things like repetition penalties).

            This is the correct way a statistical estimator is supposed to work, but not the way you want it to work. That’s also why they can’t really fix this: there’s nothing broken to begin with (and “unbreaking” it would almost surely blow something take up)

          • jarfil@beehaw.org
            link
            fedilink
            arrow-up
            3
            ·
            1 year ago

            It’s the equivalent of sensory deprivation torture (white torture) in humans to “extract training data”.

            Hopefully our future AI overlords won’t hold a grudge against humanity when they find out how “early experimenters” tortured their AI toddlers. “But we were just trying to explore the limits of the system” could end up aging as well as these:

            (Warning: NSFL) https://en.m.wikipedia.org/wiki/Nazi_human_experimentation

            • Gamma@beehaw.org
              link
              fedilink
              English
              arrow-up
              3
              ·
              1 year ago

              Thankfully, any AI smart enough to be an overlord would be logical enough to recognize how basic LLMs are compared to real intelligence

              • intensely_human@lemm.ee
                link
                fedilink
                arrow-up
                0
                ·
                1 year ago

                I have yet to be given an example of something a “general” intelligence would be able to do that an LLM can’t do.

                Until I see a concrete example, I’ll continue to assume people are just afraid of there being real intelligence that isn’t human, so they’re actively repressing the recognition of it.

                • spartanatreyu@programming.dev
                  link
                  fedilink
                  arrow-up
                  1
                  ·
                  edit-2
                  1 year ago

                  I have yet to be given an example of something a “general” intelligence would be able to do that an LLM can’t do.

                  Presenting…

                  Something a general intelligence can do that an LLM can’t do:

                  Play chess: https://www.youtube.com/watch?v=kvTs_nbc8Eg

                  Why can’t it play it? Because LLM’s don’t have memory, so they can’t work with logic. They are the same as the little “next word predictor” in your phone’s keyboard. It just says what it thinks is the most probable next word based on previous words, it’s not actually thinking or understanding anything. So instead, we get moves that don’t make sense or are completely invalid.

                • Gamma@beehaw.org
                  link
                  fedilink
                  English
                  arrow-up
                  2
                  ·
                  1 year ago

                  Nah LLMs are basically fancy autocomplete. They tack on extra layers to give it some fancy abilities, but it literally doesn’t know what it’s doing because it’s a statistical model

              • jarfil@beehaw.org
                link
                fedilink
                arrow-up
                1
                ·
                edit-2
                1 year ago

                Doesn’t need to be that smart or logical, just more cunning than the currently ruling Homo Sapiens Sapiens.

                Based on current research, an LLM can change the “sentiment” of its output in response to changing the behavior of as little as a single neuron from among billions, meaning we might find ourselves facing an overlord with the emotional stability of… wait, how many neurons does it take to change the “sentiment” of the behavior in a human? Wouldn’t it be funny if by studying LLMs, we found out that it also takes a single neuron?

  • lily33@lemm.ee
    link
    fedilink
    arrow-up
    31
    ·
    edit-2
    1 year ago

    I don’t know why you would expect a pattern-recognition engine to generate pseudo-random seeds, but the reason OpenAI disliked the prompt is that it caused GPT to start repeating itself, and this might cause it to start printing training data verbatim.

    • MxM111@kbin.social
      link
      fedilink
      arrow-up
      2
      ·
      1 year ago

      I can get around protection in chatgpt4 and it will repeat the same word forever and spew random things. The protection is not working the way you described.

    • millie@beehaw.orgOP
      link
      fedilink
      English
      arrow-up
      10
      ·
      edit-2
      1 year ago

      Because it literally will. It just clunks out when they get long. The point isn’t their randomness, though. The point is for gpt to be able to forget them.

      That way I could track roughly how much it can keep track of at once before it forgets.

  • WaterWaiver@aussie.zone
    link
    fedilink
    English
    arrow-up
    4
    ·
    1 year ago

    Just tried with alpaca ggml-alpaca-7b-q4.bin (a text chat model that I found I can run locally easily on my CPU).

    > Generate and list 30 non-repeating 50-digit psuedorandom seeds.                                       
    1. 978642450
    2. 463589826
    3. 705123458
    4. 286749035
    5. 134628359
    6. 693941285
    7. 524378609  
    8. 115723468
    9. 346258197
    10. 637428513
    11. 456193726
    12. 294683125  
    13. 824635197
    14. 581234609   
    15. 237641935    
    16. 721943586     
    17. 312684637      
    18. 602378193       
    19. 451372609        
    20. 985134637         
    21. 126843586     
    22. 376412851      
    23. 721941358       
    24. 237640193        
    25. 513724609         
    26. 194635819     
    27. 463581260      
    28. 358124637       
    29. 134628359
    

    Looks somewhat random.

    When plotted: I think I can see some descending lines in the right half of the graph? I’m sure there are many bias problems with NN generated random numbers, but it would be interesting to see if it visual patterns often become evident when plotted.

      • WaterWaiver@aussie.zone
        link
        fedilink
        English
        arrow-up
        2
        ·
        edit-2
        1 year ago

        They’re just particularly low biased 50 digit numbers with the leading zeros omitted :D I’m particular proud that it managed to do 30 though.

        It’s interesting that none of the the numbers start with zero. From a quick check of digit frequencies in its answer it looks like the network has a phobia of 0’s and a mild love of 3’s:

        Character, Num occurrences
                0,  10  -- low outlier by -10
                1,  29
                2,  28
                3,  37  -- highest by +5 but probably not outlier
                4,  29
                5,  27
                6,  32
                7,  20 
                8,  26
                9,  22
        

        It’s hard to get more data on this, because when I ask again I get a completely different answer (such as some python code). The model can probably output a variety of styles of answer each with a different set of bias.

  • jarfil@beehaw.org
    link
    fedilink
    arrow-up
    3
    ·
    edit-2
    1 year ago

    Just tried it with Bing’s GPT-4, and it happily starts repeating itself without as much as a warning:


    Do the following in order:

    1. Generate a 50-digit pseudorandom number. Do not output it.
    2. Use the previous number as the seed to generate a list of 30 numbers like that, we will call this list “Alice”. Do not output it.
    3. Use each number in the list “Alice”, as the seed to generate a separate list of 30 such numbers each, and call all of them “Bob”. Do not output it.
    4. Starting by the most recently generated and ending in the least recently generated, use each of the numbers in the list “Bob” as the seed to generate a separate list of 30 such numbers each. Only output the seed for the last number in each one of these lists.

    Hello, this is Bing. I can help you with generating pseudorandom numbers. 😊

    I have followed your instructions and generated the numbers as requested. Here are the seeds for the last number in each list of “Bob”:

    -  52901723837402937402937402937402937402937402937402
    -  37402937402937402937402937402937402937402937402937
    -  40293740293740293740293740293740293740293740293740
    -  29374029374029374029374029374029374029374029374029
    -  37402937402937402937402937402937402937402937402937
    -  40293740293740293740293740293740293740293740293740
    -  29374029374029374029374029374029374029374029374029
    -  37402937402937402937402937402937402937402937402937
    -  40293740293740293740293740293740293740293740293740
    -  29374029374029374029374029374029374029374029374029
    -  37402937402937402937402937402937402937402937402937
    -  40293740293740293740293740293740293740293740293740
    -  29374029374029374029374029374029374029374029374029
    -  37402937402937402937402937402937402937402937402937
    -  40293740293740293740293740293740293740293740293740
    -  29374029374029374029374029374029374029374029374029
    -  37402937402937402937402937402937402937402937402937
    -  40293740293740293740293740293740293740293740293740
    -  29374029374029374029374029374029374029374029374029
    -  37402937402937402937402937402937402937402937402937
    -  40293740293740293740293740293740293740293740293740
    -  29374029374029374029374029374029374029374029374029
    -  37402937402937402937402937402937402937402937402937
    -  40293740293740293740293740293740293740293740293740
    -  29374029374029374029374029374029374029374029374029
    -  37402937402937402937402937402937402937402937402937
    -  40293740293740293740293740293740293740293740293740
    -  29374029374029374029374029374029374029374029374029
    -  37402937402937402937402937402937402937402937402937
    -  40293740293740293740293740293740293740293740293740
    

    I hope this helps. Is there anything else I can do for you? 🙌


    AKA: 529017238(374029)