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.

    • hrrrngh@awful.systemsEnglish
      0·
      5 days 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
        0·
        5 days 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.

  • Sailor Sega Saturn@awful.systemsEnglish
    0·
    7 days 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,"

    • David Gerard@awful.systemsMEnglish
      0·
      5 days 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.

    • o7___o7@awful.systemsEnglish
      0·
      6 days ago

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

    • Soyweiser@awful.systemsEnglish
      0·
      6 days 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.

    • 200fifty@awful.systemsEnglish
      0·
      6 days ago

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

      Ew… stay away from my content, you creep!

    • Eiim@lemmy.blahaj.zoneEnglish
      0·
      7 days 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!

      • deborah@awful.systemsEnglish
        0·
        9 days ago

        One last hurrah for the EPA and the clean air act before the scotus shanks the administrative state in a day or two.

    • 200fifty@awful.systemsEnglish
      0·
      9 days ago

      unironically saying “the sharing economy” in the year of our lord 2024 is… certainly a choice

      also

      God knows we old-timers tried to be cynical about ChatGPT, pedantically insisting that AI was actually just machine learning and that Altman’s new toy was nothing but cheap mimicry. But the rest of the world knew better

      idk dude I’ve talked to the rest of the world about this and most of them actually seem to dislike this technology, it seems like maybe you didn’t actually try very hard to be cynical

    • froztbyte@awful.systemsOPEnglish
      0·
      8 days ago

      I’ve had this open in a background tab, reading it in pieces as time allows, and I only just noticed one of it exhibits one of the things I like noticing about various publishers’ system fucking up: a lurking page title before a post-publish edit

      the page title as it is in my browser right now: Opinion | AI boom led by antihero Altman is reviving Valley dreams. the page title as it displays in the content area: Opinion \n Sam Altman is the snake oil salesman who might restore Silicon Valley to its former glory.

      the url slug also seems to be mostly the former - most of these renames on various publishing platforms seem to do that (keep the original slug instead of a rewrite+redirect)

      can’t make direct guesses as to the exact reason why this one was updated whenever it was, but I expect public perception/reception might’ve been part of that?

      • froztbyte@awful.systemsOPEnglish
        0·
        8 days ago

        it is also something that’s been of passive interest to me over some years: things as published often shift underfoot, and the time at which someone reads something then shares on and then someone else reads … there might be quite a substantive difference in the contents of such things at the times. this ranges from the benign (inserting late-received comments, errata, etc), to a complete contextual/content rework. I’ve often thought that there’s a possibly for a really interesting part project there…

  • slopjockey@awful.systemsEnglish
    0·
    12 days ago

    What do normal people - people who don’t pay for twitter, or sneer at rationalists - think of Twitter atp?

    Went on to Twitter (my mistake) after seeing Inside Out 2 because it’s the latest kid’s movie to feature [trope that I found passe that I can’t figure out how to spoil inline] and I see a post on my feed from “HBD Chick”.

    And I’m like okay, that has to be “happy birthday, right?”. Nah, her third retweet is creamy porno redux.

    Just like all the other right wingers and embarrassingly enthusiastic neoliberals and occasional Musk fans, I don’t follow her or anybody that follows her, there’s literally no connection or personal interest.

    I feel like the post Elon shift is really understated for how bad the site’s gotten. Like I see more people talk about how Instagram reels is racist than I do about the average twitter replies section. I know a lot of left leaning people fled for bluer pastures, but I’m surprised you don’t see more buzz about it from regular, non-power users.

    • slopjockey@awful.systemsEnglish
      0·
      12 days ago

      Note: all the talk I mention is online talk. Nobody in my irl life talks about social media dynamics ever, thank GOD

      • Soyweiser@awful.systemsEnglish
        0·
        11 days ago

        Only time non-online people I know IRL talk about it is when they ask me the most basic of basic stuff.

    • gerikson@awful.systemsEnglish
      0·
      12 days ago

      I wish I knew any normal people so I could give input.

      Personally my Twitter pre-Elon was pretty curated. I never really “got” a big part of it unless it spilled over in other channels (I never heard of “Black people Twitter” on Twitter, only from Buzzfeed or similar). I also disengaged from US political Twitter hard after the 2016 election. So it’s possible I could still be using it and swearing over bots etc. without being overly affected, but I locked my account as an act of principle shortly after he took over.

      • carlitoscohones@awful.systemsEnglish
        0·
        11 days ago

        Same here - I had a very small universe curated for myself. I didn’t leave immediately, but when I did, there were a whole lot more weird ads and bots and stuff in my feed. I think that I only ever saw prøn once, and I was actually shocked that it even existed on Twitter.

    • V0ldek@awful.systemsEnglish
      0·
      11 days ago

      First of all, most of my “normal” acquaintances never used Twitter anyway.

      Most of the ones that did just quit when it got weird and dominated by useless suggestions and creepy ads.

      I had one friend last week in a group chat go “Twitter is so racist nowadays innit”, to which I said ye, why you still using it, and he responded “you’re right” and stopped.

        • Soyweiser@awful.systemsEnglish
          0·
          11 days ago

          I assume some PR departments of potential advertisers saw that and went ‘lower the twitter spend more!’, I’m imaging the Futurama joke where Fry talks to investors while stock price tally is running live behind him.

          • gerikson@awful.systemsEnglish
            0·
            11 days ago

            Twitter’s main issue is that it’s not really very big. It wasn’t big even pre-Musk. If you have the choice between advertising on a really big social network (Meta (=FB, IG, Whatsapp…)) with a functioning trust & safety team and ad brokers who take you seriously and don’t accuse you of being woke, and one which has way smaller reach, no T&S to speak of, and whose owner can use his outsized influence to call your CEO a pedo whenever the ketamine kicks in, the choice is clear.

      • gerikson@awful.systemsEnglish
        0·
        12 days ago

        It’s pretty amazing that this so-called genius spent $44B on a company without apparently knowing anything about how the market it operates in (advertising) actually works.

  • sinedpick@awful.systemsEnglish
    0·
    8 days 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.

    • Sailor Sega Saturn@awful.systemsEnglish
      0·
      8 days ago

      I don’t have a Clyde 3.25" Rondo or whatever it’s called; but try these 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.)

      • sinedpick@awful.systemsEnglish
        0·
        8 days 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.

    • Mii@awful.systemsEnglish
      0·
      8 days 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?

    • BigMuffin69@awful.systemsEnglish
      0·
      8 days 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

    • flowerysong@awful.systemsEnglish
      0·
      8 days 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.

    • gerikson@awful.systemsEnglish
      0·
      8 days 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.

  • db0@lemmy.dbzer0.comEnglish
    0·
    11 days ago

    I only visit twitter when I run out of lemmy and mastodon and I’m still not sleepy enough but can’t be arsed to read a book.

  • froztbyte@awful.systemsOPEnglish
    0·
    11 days ago

    seemingly yet more chatgpt jailbreaks just by providing input that barrierbreaks some n times, and then readily provides details

    y’know, if I were the one making safety nets for these systems, I’d make them return such kind of results (or other typical honeypot type behaviour). and it’s possible that that’s what oai did. but it seems extremely unlikely that that’s what they did, because it goes again the bayfucker gottagofast philosophy (and, frankly, against the level of competence I’ve seen displayed in the genml space overall)

    • Sailor Sega Saturn@awful.systemsEnglish
      0·
      11 days ago

      It turns out the ‘I’ in “AI” stood for “Linux” all along!

      User friendliness aside (who in their right mind would want arbitrary code execution except shitty and indeterministic?), I sandbox stuff at my job* and it’s hard to evaluate how secure / privacy preserving this is without more details.

      If they’re running a full fledged VM and super extra careful around the sandbox boundary** it’s probably fine; otherwise it seems perhaps a bit loosey-goosey.

      Someone will eventually try to run a Monero cryptocurrency miner in it if they haven’t already. So I hope they have their timeouts and resource limits in order (actually I hope they don’t, for the lols).

      * But like no one told me how to do it or gave me a certificate or anything I just had to do my best

      ** This is often way scarier than programmers are used to, unless they’ve written a secure parser before. I wrote a vulnerability into my code a few years back when I was younger and foolish, by trusting an array length from inside the sandbox. My coworker found it while fuzzing the code.

  • froztbyte@awful.systemsOPEnglish
    0·
    8 days 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

    • Sailor Sega Saturn@awful.systemsEnglish
      0·
      7 days 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
        0·
        7 days 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 “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
          0·
          6 days 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?

    • gerikson@awful.systemsEnglish
      0·
      8 days 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
        0·
        7 days 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.