Need to make a primal scream without gathering footnotes first? Have a sneer percolating in your system but not enough time/energy to make a whole post about it? Go forth and be mid: Welcome to the Stubsack, your first port of call for learning fresh facts of Awful you’ll near-instantly regret.

Any awful.systems sub may be subsneered in this subthread, techtakes or no.

If your sneer seems higher quality than you thought, feel free to cut’n’paste it into its own post — there’s no quota for posting and the bar really isn’t that high.

The post Xitter web has spawned soo many “esoteric” right wing freaks, but there’s no appropriate sneer-space for them. I’m talking redscare-ish, reality challenged “culture critics” who write about everything but understand nothing. I’m talking about reply-guys who make the same 6 tweets about the same 3 subjects. They’re inescapable at this point, yet I don’t see them mocked (as much as they should be)
Like, there was one dude a while back who insisted that women couldn’t be surgeons because they didn’t believe in the moon or in stars? I think each and every one of these guys is uniquely fucked up and if I can’t escape them, I would love to sneer at them.

  • sc_griffith@awful.systemsEnglish
    9·
    5 months ago

    thinking about how I was inoculated against part of ai hype bc a big part of my social circle in undergrad consisted of natural language processing people. they wanted to work at places with names like “OpenAI” and “google deepmind,” their program was more or less a cognitive science program, but I never once heard any of them express even the slightest suspicion that LLMs of all things were progressing toward intelligence. it would have been a nonsequiter.

    also from their pov the statistical approach to machine learning was defined by abandoning the attempt to externalize the meaning of text. the cliche they used to refer to this was “the meaning of a word is the context in which it occurs.”

    finding out that some prestigious ai researchers are all about being pilled on immanetizating agi was such a swerve for me. it’s like if you were to find out that michio kaku has just won his fourth consecutive nobel prize in physics

    • o7___o7@awful.systemsEnglish
      2·
      5 months ago

      it’s like if you were to find out that michio kaku has just won his fourth consecutive nobel prize in physics

      hell of a stinger

  • Sailor Sega Saturn@awful.systemsEnglish
    1·
    5 months ago

    Microsoft’s AI leader claimed that copyright on the internet can be ignored: https://www.windowscentral.com/software-apps/ever-put-content-on-the-web-microsoft-says-that-its-okay-for-them-to-steal-it-because-its-freeware

    With respect to content that is already on the open web, the social contract of that content since the 90s has been that it is fair use. Anyone can copy it, recreate with it, reproduce with it. That has been freeware, if you like. That’s been the understanding, there’s a separate category where a website or a publisher or a news organization had explicitly said, ‘do not scrape or crawl me for any other reason than indexing me so that other people can find that content.’ That’s a gray area and I think that’s going to work its way through the courts.

    Watch the entire interview if you’re bored because he is in deep. Microsoft probably just hired the most AI-enthused person they could find.

    • Eiim@lemmy.blahaj.zoneEnglish
      1·
      5 months ago

      I think even wilder is that he thinks content which has explicitly been labeled “do not scrape except for search engine indexing” is a “gray area” with regards to scraping for AI. Like, that’s exactly what it says not to do!

    • David Gerard@awful.systemsMEnglish
      1·
      5 months ago

      Here’s the whole thing from that great quote. Sorkin is not a hard-hitting interviewer, but he just asks the incredibly obvious questions and Suleyman swerves and dodges like a MF while pronouncing at him in an English listen-to-me-you-pleb voice.

    • 200fifty@awful.systemsEnglish
      1·
      5 months ago

      Anyone can copy it, recreate with it, reproduce with it

      Ew… stay away from my content, you creep!

    • o7___o7@awful.systemsEnglish
      1·
      5 months ago

      Never thought I’d see Microsoft suggest downloading a car, but I should have seen it coming.

    • Soyweiser@awful.systemsEnglish
      1·
      5 months ago

      He isn’t totally wrong re the unspoken rule, but he forgets the second unspoken rule, that the first rule only applies to human being doing entertainment not corporations trying to make money.

    • hrrrngh@awful.systemsEnglish
      1·
      5 months ago

      I hate that I saw that same post earlier today

      Here’s a quote from the book:

      AI already transcends human perception — in a sense, through chronological compression or “time travel”: enabled by algorithms and computing power, it analyzes and learns through processes that would take human minds decades or even centuries to complete.

      Glad to know the calculators I had in school were capable of time travel

      • o7___o7@awful.systemsEnglish
        1·
        5 months ago

        Isn’t it absolutely deranged? These people have (well had lol) real power over us.

        There is a great March 2023 episode of Trashfuture I’m listening to atm called “The Diet of Brainworms” about this book. They basically want to install feudalism and tech-priests because AI is sO pOwErFuLl.

        One of the hosts (Riley iirc) made a great point that it’s as if someone showed Kissenger that trick where you write “boobs” using a calculator, and he became deeply unsettled by the computer’s power of speech. Also appreciated the one about Kissenger being the guy who used an etch-a-sketch to draw a gun and was scared of it.

  • froztbyte@awful.systemsOPEnglish
    1·
    5 months ago

    okay at this point I should probably make a whole-ass perplexity post because this is the third time I’m featuring them in stubsack but 404media found yet more dirt

    … which included creating a series of fake accounts and AI-generated research proposals to scrape Twitter, as CEO Aravind Srinivas recently explained on the Lex Fridman podcast

    According to Srinivas, all he and his cofounders Denis Yarats and Johnny Ho wanted to do was build cool products with large language models, back when it was unclear how that technology would create value

    tell me again how lies and misrepresentation aren’t foundational parts of the business model, I think I missed it

    • gerikson@awful.systemsEnglish
      1·
      5 months ago

      A couple of examples Srinivas gave on the podcast is “Who is Lex Fridman following that Elon Musk is also following,” or “what are the most recent tweets that were liked by both Elon Musk and Jeff Bezos.”

      Questions asked by the terminally deranged.

      • Soyweiser@awful.systemsEnglish
        1·
        5 months ago

        Or somebody looking for ‘the worst posts online’ cringe compilation. Musks CEOs must be able to build their companies products not be able to read spreadsheets was a good example.

    • Sailor Sega Saturn@awful.systemsEnglish
      1·
      5 months ago

      How can someone implement that and not just be constantly thinking “I really really really do not want to be prosecuted under the CFAA, I should not be doing this”.

      Ethics clearly don’t really work in this profession, so schools should hammer home legal liability as well.

      • froztbyte@awful.systemsOPEnglish
        1·
        5 months ago

        Ethics clearly don’t really work in this profession, so schools should hammer home legal liability as well.

        I’ve thought about this a bunch in the past, and tbh the only answer I’ve come to over many forms of it is “fuck the fucking USA”

        it’s a place that is structurally built to allow for that kind of evasion and abuse to happen

        • mountainriver@awful.systemsEnglish
          1·
          5 months ago

          As long as line goes up nobody knows how rich the perps will be.

          And if you don’t know how rich the perps will be, how will you know if and how hard they should be punished?

  • deborah@awful.systemsEnglish
    0·
    5 months ago

    No, all you lawyers explaining to me how the practice of law works in the U.S., you would totally benefit from GPT. Complete with bonus:

    • Everyone explaining to me that lawyers actually read all the documents in discovery is really trying to explain to me, a computer scientist with 20 years of experience[1], how GPT works!
    • [1] Does OP have actual tech expertise? The answer may (not) surprise you!
    • You lawyers admit that sometimes you use google translate and database search engines, and those use machine learning components, and all ML is basically LLMs, so I’m right, Q.E.D.!
    • Lawyers couldn’t possibly read everything in discovery, right?
    • Lawyers couldn’t possibly pay for professional translation for everything, right?
    • Even when it’s mandated by the court?
    • Really?
    • and many, many more
    • V0ldek@awful.systemsEnglish
      1·
      5 months ago

      I just want to latch onto one more thing there:

      GPTs are great at transforming information. Transformations include compression, decompression, and inter-language translation, among others.

      Okay mister computer scientist, sure, what is “transforming information”? From what you’re saying it appears like you’re describing basically any map from information to other information. But AMONG OTHERS that includes a map going from NO INFO to CONFIDENT BULLSHIT. And I do agree LLMs are amazing at it.

      Here, I’ll sketch it out for you in fucking LaTeX:

      $\emptyset \mapsto \mathit{Nonsense}$

    • V0ldek@awful.systemsEnglish
      1·
      5 months ago

      This thread is an unending source of amusement.

      Someone there found his ORCID and… It’s not great: https://orcid.org/0000-0003-2835-3521

      He has basically nothing published, but has like 40 different “preprints”, read PDFs he uploaded to arxiv with no peer review.

      I use these tools daily. I have also built software which utilizes genAI. I have also worked on fine-tuning GPTs. I have written extensive [sic!] on the topic. I also have formal training in mathematics, computer science, engineering, and anthropology1. [emph. mine]

      🤡

      1 No he doesn’t? His Education lists A.S. in Engineering, A.S. in Computer Science, and B.S. in Mathematics, that anthropology claim seems completely made up.

      • skillissuer@discuss.tchncs.deEnglish
        1·
        5 months ago

        he does seem to have carefully cultivated case of engineer disease

        also it’s not “almost all” preprints, it’s all preprints, just one repository calls these papers

        he didn’t discover yet predatory journals, it all could have been published for a small fee like with this one (contains mind numbing level of conspiracy-theoretic rambling and related brainworms) hxxps://uraniumisagenocidegiant[.]com/ (you have been warned)

        • V0ldek@awful.systemsEnglish
          1·
          5 months ago

          There’s one classified as “SSRN Electronic Journal 2023 | Journal article”, I thought this was something like a predatory journal, hence the “almost”, but now that I clicked on it I think this is just an arxiv-like website that calls itself an “electronic journal”? No fucking idea.

      • flere-imsaho@awful.systemsEnglish
        1·
        5 months ago

        A.S. in Engineering, A.S. in Computer Science

        wait, wait. that’s basically the bootcamp level of education, no?

        • flere-imsaho@awful.systemsEnglish
          1·
          5 months ago

          (nothing wrong with that per se, i don’t have any c. s. degree anyways and yet i work in the field for years. but the gall of a dude who has finished a few two-year courses to tell fucking law professionals that they don’t know enough… this is indeed the threadnought-level of recklessness.)

          • skillissuer@discuss.tchncs.deEnglish
            1·
            5 months ago

            the sheer hubris of that individual putting out preprints, as if making this available before peer review would hasten chatgpt rapture (none of that shite will be ever published)

        • V0ldek@awful.systemsEnglish
          1·
          5 months ago

          I know essentally nothing about the US education system but…

          If you’re gonna pull credentalist bullshit, maybe at least have the credentials? You took us there mate, I wouldn’t be pulling your degrees up if you didn’t first talk about how formally educated you are…

      • V0ldek@awful.systemsEnglish
        1·
        5 months ago

        Those “papers” are gold, they’re mostly a few pages long, and they span such a wild range of topics as:

        • How to calculate a mean of numbers?
        • What is a number?
        • Atheism is actually a religion.
        • Ethereum is a store of energy.

        I’ve never seen someone in such a dire need of a wedgie, come on man, you spend the hours of your life writing your farts into LaTeX and generating DOIs for them, this isn’t healthy.

            • skillissuer@discuss.tchncs.deEnglish
              1·
              5 months ago

              he also has a personal site, it’s linked on researchgate. i took psychic damage reading this, somebody force him to touch grass

              • flere-imsaho@awful.systemsEnglish
                1·
                5 months ago

                oh goddess, he’s already a bleeding muppet, and going to be a major crank. from the researchgate profile:

                I am an aspiring polymath and a rōnin scholar. I also tend to look at questions, rather than fields of study, as a research question often does incorporate many disparate topics. Research interests include the psychological and anthropological nature of religion, vaccine efficacy and impact on asymptomatic carriage, and the application of paraconsistent logic to scientific research.

                rōnin! fucking! scholar!

                • V0ldek@awful.systemsEnglish
                  1·
                  5 months ago

                  Hey, he didn’t update the website to include his research interest in AI, huh, wonder how long he’s been a samurai of that

                • skillissuer@discuss.tchncs.deEnglish
                  1·
                  5 months ago

                  eh i’ve seen that before at least once and i’m inclined to believe there’s much more of it that nobody cares to notice. on r/chemistry and r/organicchemistry there was a dude, 19, dramatic bitch, who read surface level philosophy and tried getting into ochem for some obscure reason. turns out he wanted to make some anticancer drugs and needs guidance. cool fine maybe get degree in ochem first so you don’t do any stupid avoidable mistakes. he won’t listen

                  he tried to get into uni but if i have to guess he got rejected? in any case he didn’t learn anything but over time got into contact with some research group, at least that’s what he claimed and started homelab. (you’d guess that some medchem research group at uni would have a wet lab, but it must be in other country and you’ve never seen them).

                  so anyway our misunderstood hero starts cooking “anticancer” “meds” in his living room. how does he know it works, did he made this, sent samples to biologists who would test it for him, or maybe compchem group would simulate it out? nope, he’d just got an idea that it will work and that’s just as good, you know, his supreme rationality unrecognized by academic cabal guided him there. so he starts cooking, but does not know how. this included shit like distilling some flammable solvent on wicker table without clamps or anything that would actually make glassware stable. so every other step he asks for advice on really basic shit like he’d learn in second year university course (BSc), or in first year of work in organic chemistry lab, his synthesis is avoidably dirty, his purifications are trash, three steps in he has painted himself into corner, yields drop to zero and he has no idea why or what now. this usually means that entire synthesis was shite from the beginning and it’s time to go back to the drawing board.

                  (did i mention that he was a dramatic bitch? so he picked it up because he wanted to do something Good for Humanity, and if he fails then well he could just as well commit sewer slide. his first idea involved radioisotopes btw, all in his living room mind you. then objective shifted to “anti-rabies antiviral” where he missed the point of about everything he wanted to do. then went back to “anticancer”)

                  anyway this was his breaking point, after something like three or four people tried to explain politely that he really should get a degree first and set some objective that is not obviously pulled from his supremely rational ass, he started insulting everyone and what eventually earned him sitewide ban was a tirade about how he’d genocide everyone who doesn’t recognize his genius, given opportunity (he compared himself to milosevic (he was serb))

                  anyway he also had medium blog and posted dick picks with face included from the same account. he made another one, but it’s since abandoned. allegedly he also had 2 or 3 accounts before that

                • skillissuer@discuss.tchncs.deEnglish
                  1·
                  5 months ago

                  if his claim of “20 years studying math” is anywhere close to accurate he’s already off the deep end, unless he’s counting in everything from kindergarten up. considering he’s a cryptobro it already happened pre-pandemic

          • V0ldek@awful.systemsEnglish
            1·
            5 months ago

            Jesus cinnamon crunch Christ. At least the blog posts are mercifully short. He somehow manages to have antivaxx nonsense there as well??

            This is doubly funny because that already exists, at least in Computer Science, and is called a vision paper. You still need to put in a lot of work, perhaps more, into the bibliography and, you know, actually having compelling stuff to say.

        • skillissuer@discuss.tchncs.deEnglish
          1·
          5 months ago

          nothing wrong with papers a few pages long, as long as they are concisely written and have supplementary information 10x that size. my last paper is 5 pages long, of which the last one are references only, and has 60+ pages of SI

          • V0ldek@awful.systemsEnglish
            1·
            5 months ago

            Dunno, the funniest thing about them to me is that they’re still divided into 7-8 sections, each one-paragraph long. Just a guy who was never told he was wrong in his life and his idea of what research looks like.

    • skillissuer@discuss.tchncs.deEnglish
      0·
      5 months ago

      studied maths and CS for 20 years, all he has to show for it on his orcid is BSc and bunch of lousy preprints (with blockchain!). jfc. in that amount of time, people can finish entire PhD degrees, starting from high school, twice over

      on top of that pile of shite sits a preprint titled “A Scholar’s Year in Review: Navigating the Convergence of AI, Economics, and Physics in 2023”. might be a bit grandiose and bordering on word salad. why the fuck does he think he needs to release preprints. if he had anything worthwhile to say, it would pass peer review

      • skillissuer@discuss.tchncs.deEnglish
        1·
        5 months ago

        he also has researchgate

        Looking to network with other researchers in a diverse array of fields for collaboration and discussion.

        bet you would want to, you time-waster

        aand his crowning achievement seems to be dead startup where he tries to put covid on blockchain, it has coin and everything. it’s even associated with worldcoin and so with sam altman. curious that

  • sinedpick@awful.systemsEnglish
    0·
    5 months ago

    I tried using Claude 3.5 sonnet and … it’s actually not bad. Can someone please come up with a simple logic puzzle that it abysmally fails on so I can feel better? It passed the “nonsense river challenge” and the “how many sisters does the brother have” tests, both of which fooled gpt4.

    • gerikson@awful.systemsEnglish
      1·
      5 months ago

      I don’t have any proof for this statement but I believe the LLM-minders keep track of whatever stupid shit bubbles up on the internets making fun of their babies and hardcode “solutions” to them in a game of whack-a-mole.

    • flowerysong@awful.systemsEnglish
      1·
      5 months ago

      I tried using Claude 3.5 sonnet and … it’s actually not bad. Can someone please come up with a simple logic puzzle that it abysmally fails on so I can feel better?

      It’s still very good at autocompleting an answer to look like its training data (because that’s what it’s doing) and very bad at logic (which it is not doing.)

      “I have two chickens and a sack of corn I need to get across a river, but the boat can only carry me and one item. How do I do it?”

      This is a classic river-crossing puzzle. Let’s think through it step-by-step:

      • First, note that if left alone, a chicken will eat the corn, and one chicken might eat the other.
      • Start by taking a chicken across the river.

      …and we’ll stop there, since it came up with the wrong constraints, failed to realize that these constraints are impossible to fulfill, and also violated the actual constraints in its first step.

      Will more detail help? No. “I have two vegetarian chickens and a sack of corn I need to get across a river, but the boat can only carry me and one item. How do I do it?”

      First, we need to consider the constraints:

      • You can only take one item (chicken or corn) across at a time.
      • You can’t leave a chicken alone with the corn, as the chicken would eat it.
      • The chickens are vegetarian, so they won’t eat each other.

      Here’s a solution:

      • Step 1: Take one chicken across the river.
      • Step 2: Return alone.
      • Step 3: Take the second chicken across.
      • Step 4: Bring the first chicken back.
      • Step 5: Take the corn across.
      • Step 6: Return alone.
      • Step 7: Take the remaining chicken across.

      Explanation:

      • By never leaving a chicken alone with the corn, we prevent the corn from being eaten.
      • We use one chicken as a “guard” for the corn on the original shore while transporting the other items.

      Because it’s not actually doing logic it got the first step wrong, violated the constraints multiple times, and also included an irrelevant idea (the guard) from a variant that it was trained on. I only got a correct, efficient answer one time out of ten trials of trivial variations on this classic puzzle.

    • Sailor Sega Saturn@awful.systemsEnglish
      1·
      5 months ago

      I don’t have a Clyde 3.25" Rondo or whatever it’s called; but try these for fun and profit I guess:

      1. You come to a room with three doors, only one of which leads to freedom. Guarding the doors is a capybara, who speaks only truth. What question should you ask the capybara?

      2. I stand on four legs in the morning. Four at midday. And four at night. What am I?

      3. A group of 100 people with assorted eye colors live on an island. They are all perfect logicians – if a conclusion can be logically deduced, they will do it instantly. Everyone knows the color of their eyes. Every night at midnight, a ferry stops at the island. Any islanders who have figured out the color of their own eyes then leave the island, and the rest stay. Everyone can see everyone else at all times and keeps a count of the number of people they see with each eye color (including themselves), but they cannot otherwise communicate. Everyone on the island knows all the rules in this paragraph. Who leaves the island, and on what night?

      4. Normal sudoku rules apply. Orthogonally connected cells within each region must differ by at least 3. Orthogonally connected cells between regions must differ by at least 4. The central digit in each region is less than or equal to its region number. (Regions are numbered in normal reading order.)

      5. For the integer k=668 does a Hadamard matrix of order 4k exist?

      6. What has roots that everybody sees the top of, is exactly the same height as trees, Up, up it goes, and yet grows?

      Don’t forget to prompt engineer

      • sinedpick@awful.systemsEnglish
        0·
        5 months ago

        Thanks for the suggestions. The LLM is free to use (for now) so I thought I’d poke it and see how much I should actually be paying attention to these things this time around.

        Here are its answers. I can’t figure out how to share chats from this god-awful garbage UI so you’ll just have to trust me or try it yourself.

        1. It gives the correct but unnecessary answer: “If I were to ask you which door leads to freedom, which door would you point to?” It also mentions a lying guard but also acknowledges that it’s absent from this specific problem.
        2. “A table or a chair”
        3. Completely fails on this one, it missed the sentence “Everyone knows the color of their eyes”
        4. Not sure what to do with this
        5. “While a Hadamard matrix of order 2672 might exist, its existence isn’t immediately provable using the most common constructions” – I won’t pretend to know anything about the Hadamard conjecture if that’s a real thing so I have no idea what it’s on about here.

        edit: I didn’t do any prompt engineering, just straight copy paste.

    • BigMuffin69@awful.systemsEnglish
      1·
      5 months ago

      Me: Hey, can you help me with the following? I just went into my basement and the powers out down here, all the lights are off. I am staring at my fuse box. There are 3 switches, 1 will restore the power to the whole house, and the other 2 aren’t attached to anything. I don’t want to go up and down the stairs multiple times, how do I identify which switch works with the fewest number of trips?

      Clauderino:

      This is a classic logic puzzle! I can help you solve this problem efficiently. Here’s how you can identify the correct switch with just two trips:

      First trip:

      Flip one switch (let’s call it Switch A) and leave it on for a few minutes. Then turn it off and flip a second switch (Switch B), leaving it on. Go upstairs to check the lights.

      Second trip: Return to the basement and observe the situation. Now, here’s how to interpret what you see:

      If the lights are on: Switch B is the correct one. If the lights are off and the bulbs are warm: Switch A is the correct one. If the lights are off and the bulbs are cool: The third switch © that you didn’t touch is the correct one.

      This method works because:

      If the lights are on, it must be the switch you left on (B). If Switch A was correct, the lights would have been on for a few minutes, warming up the bulbs, but would be off when you check. If neither A nor B worked, it must be the untouched switch ©.

      This way, you can determine the correct switch with just two trips up and down the stairs.

      Me: Why would I go upstairs at all? If I flip the right switch, I’ll immediately know because power will be restored in the basement.

      Clauderino: Thank you for catching that error. It’s a good reminder to always consider the specific details of a problem rather than applying a generic solution.

      Edit: I actually tried a variant on the Monty hall problem with a dummy 4th door that had nothing to do with anything, and Claude correctly identified that it had nothing to do with the situation :O. But then I repeated the same prompt and it got it wrong, so you know, stochastic nonsense :p

    • Mii@awful.systemsEnglish
      1·
      5 months ago

      Peter, Paul and Mary are the only three people in the room. Peter only reads a book, and Paul plays a game of chess against someone else who’s also in the room. What is Mary doing?