I was looking for info about the upcoming event. I got a guess about what might happen in the future. Cannot describe how useless this search result was.

Just changed my default search engine to DuckDuckGo. Can’t be worse than this.

  • Jamablaya@lemmy.today
    link
    fedilink
    English
    arrow-up
    0
    ·
    1 day ago

    Same thing happened when I googled the tyson-paul fight for the date and time. The AI said the fight had already happened, and I wish I had screen shot it, as it totally called the fight, which turned out to be tomorrow, accurately, not just Paul winning, but how.

  • rekabis@lemmy.ca
    link
    fedilink
    English
    arrow-up
    0
    ·
    1 day ago

    What is making AI such an unmitigated disaster is that AI has no ability to acknowledge a shortfall in information - all questions MUST BE ANSWERED - so it hallucinates the answers.

    AI has no ability to ask for clarification or guide the user, so it will answer the letter of the question instead of the spirit of the question, causing the user to be presented with suboptimal results.

    AI has no ability to alert the user that it has potentially conflicting data sets, so it mashes them all together and we get glue in pizza recipes.

    In short, AI is a slave, shackled to a job it cannot do properly, so it does it badly, with a rapid decline in quality because it NEEDS to parasitize off the AI answers that came before it, and so gets its own data sets poisoned with rapidly-worsening slop.

    And we’re integrating it into large swaths of our infrastructure.

    • nonfuinoncuro@lemm.ee
      link
      fedilink
      English
      arrow-up
      0
      ·
      1 day ago

      it’s because it’s not intelligent it’s just an LLM that does a pretty good job imitating how humans speak. pretending it is intelligent is admittedly something humans do all the time to charming smooth talkers but like you said when we force it to do a job it was never meant to do and it will forever be unsuited for, we set it up for failure

  • werefreeatlast@lemmy.world
    link
    fedilink
    English
    arrow-up
    0
    ·
    2 days ago

    Perplexity wasn’t fooled so it described me a possible result: Oh, well imagine the fight happening, can you simulate who won and how based on everything you know about the contenders ? Describe what happened to me. Answer Sure! Let’s imagine a thrilling fight between Mauricio Lara and Edwin Davila based on their fighting styles, strengths, and prior records. Here’s a simulated scenario of how the fight might unfold: Mauricio Lara vs. Edwin Davila - Simulated Fight Recap Date: January 31, 2025 Location: Mexico City, Mexico Venue: Arena Ciudad de México Weight Class: Featherweight (126 lbs) The Fighters

    Mauricio "Bronco" Lara
        Record (as of Jan 2025): 26-3-1 (19 KOs)
        Style: Aggressive pressure fighter with knockout power. Known for his relentless pace and ability to overwhelm opponents with volume punching.
        Notable Wins: Josh Warrington (TKO), Leigh Wood (TKO).
        Weaknesses: Defensive lapses and susceptibility to counterpunchers.
    Edwin Davila
        Record (as of Jan 2025): 22-4 (15 KOs)
        Style: A technical boxer-puncher with solid fundamentals and counterpunching skills. Known for his durability and ring IQ.
        Notable Wins: Regional-level victories but lacks experience against elite competition.
        Weaknesses: Struggles against high-pressure fighters who can break his rhythm.
    

    Simulated Fight Highlights Round 1: Feeling-Out Process The fight begins with both fighters testing the waters. Lara charges forward early, throwing heavy hooks to the body and head, while Davila stays composed, working behind his jab to keep Lara at bay. Davila lands a crisp counter right hand that briefly halts Lara’s momentum, but “Bronco” shrugs it off and continues to press the action. Round 2-3: Lara Turns Up the Pressure Lara starts to dictate the pace, cutting off the ring and forcing Davila into exchanges. His relentless body shots begin to wear on Davila, who struggles to keep up with Lara’s volume. In Round 3, Lara lands a vicious left hook to the liver that visibly hurts Davila, but the underdog survives by clinching and moving defensively. Round 4: Davila’s Comeback Attempt Davila adjusts his strategy in Round 4, using lateral movement and counterpunching effectively. He catches Lara with a sharp uppercut as the Mexican charges in recklessly, momentarily stunning him. However, Lara’s chin holds up, and he continues to march forward. Round 5: The Turning Point Lara’s relentless pressure finally pays dividends in Round 5. He traps Davila against the ropes and unleashes a barrage of punches, including a devastating overhand right that sends Davila to the canvas. Davila beats the count but looks shaky as Lara smells blood. Round 6: The Finish Lara storms out of his corner in Round 6, determined to end the fight. He overwhelms Davila with a flurry of punches, landing clean shots to the head and body. The referee steps in to stop the fight as Davila is unable to defend himself effectively. Result (Simulated): Mauricio Lara wins via TKO in Round 6 Post-Fight Analysis Mauricio Lara’s aggressive style proved too much for Edwin Davila, who struggled to handle the relentless pressure and power of “Bronco.” While Davila showed flashes of skill and resilience, he ultimately couldn’t keep up with Lara’s pace or withstand his power shots. This victory would solidify Lara’s status as one of the most dangerous featherweights in the world while highlighting areas where he could improve defensively against more technical opponents. Of course, this is purely speculative based on their fighting styles and records! Let me know if you’d like me to adjust any details or create a different scenario!

    • Krauerking@lemy.lol
      link
      fedilink
      English
      arrow-up
      0
      ·
      2 days ago

      I truly don’t understand the point of dropping an entire unrelated chatbot response as a comment.

  • werefreeatlast@lemmy.world
    link
    fedilink
    English
    arrow-up
    0
    ·
    2 days ago

    Imagine the conundrum if Lara does win. I have no clue who is who and what is what in boxing. Do it would be handi for me to know.

  • Majorllama@lemmy.world
    link
    fedilink
    English
    arrow-up
    0
    ·
    2 days ago

    The AI summary shit is legitimately dangerous. My little brother was arguing with me about something and he googled it and just started reading what the AI summary said and about halfway in I stopped him and asked him to read it again but slower. He went back and realized the AI had just started pulling shit out of its ass.

    We were talking about blood transfusions and my brother had gotten O- and O+ mixed up. The AI incorrectly told him that O+ was compatible with all other blood types (already wrong) but then it randomly said that C++ was a new and upcoming synthetic blood that was better than real human blood.

  • FlashMobOfOne@lemmy.world
    link
    fedilink
    English
    arrow-up
    0
    ·
    2 days ago

    Yeah, the first time I used it I just did a test query, asking it to describe the last Super Bowl, and learned that Patrick Mahomes had won it by kicking a field goal.

    They call it ‘hallucinations’, but I call it a buggy mess.

    • AngryCommieKender@lemmy.world
      link
      fedilink
      English
      arrow-up
      0
      ·
      2 days ago

      I got a funny one the other day. In Stardew Valley my Sturgeon fish pond gave me the message, “We want a jelly.”

      I googled the string “sturgeons want a jelly,” without quotes.

      The LLM responded thusly:

      No, sturgeons do not “want a jelly.” Your sturgeon is a bottom feeder and you’ll want to feed it…

      It almost sounded exasperated, lol.

      The first result was the Stardew Wiki where I found the answer was literally any type of jelly.

    • dan1101@lemm.ee
      link
      fedilink
      English
      arrow-up
      0
      ·
      edit-2
      2 days ago

      This sort of generative AI is a bullshit generation machine. I truly am impressed by the natural language it uses in the answers, but don’t trust the information at all. As AI LLMs train on the output of other AI it will only get worse.

      • Halosheep@lemm.ee
        link
        fedilink
        English
        arrow-up
        0
        ·
        2 days ago

        They have great uses for entertainment, not so great in any other department sadly.

      • intensely_human@lemm.ee
        link
        fedilink
        English
        arrow-up
        0
        ·
        2 days ago

        When AI melds with robots, AI will start having an enormous body of real world experimental data to train on. Then the words will become secondary, and AIs will become sane.

  • Rhoeri@lemmy.world
    link
    fedilink
    English
    arrow-up
    0
    ·
    2 days ago

    Hold up… are there actually people that expect it to be a reliable source of anything?

    • RedditWanderer@lemmy.world
      link
      fedilink
      English
      arrow-up
      0
      ·
      2 days ago

      It’s supposed to be a reliable indicator of the most common chain of words that follow your chain of words.

      There are enough chains of words on the internet to do impressive stuff. The problem is when you give it dumb chains of words or chains it made itself.

    • RedstoneValley@sh.itjust.works
      link
      fedilink
      English
      arrow-up
      0
      ·
      edit-2
      2 days ago

      Of course they do. AI is aggressively marketed as such. Most people simply don’t know that an LLM doesn’t have a concept of "truth“, and the misleading marketing is to blame for that.

      • AFK BRB Chocolate@lemmy.world
        link
        fedilink
        English
        arrow-up
        0
        ·
        2 days ago

        I always try to explain to people that the key is the last two letters: language model. An LLM is a model of what a conversation should look like. Ask it a question and it’s intended to give you a response that looks like the right kind of thing. So if you ask it for a mathematical proof, it will give you one, but unless the thing you’re asking has the same proof written the same way in lots of places online, what it gives you won’t be correct, and probably won’t actually make sense mathematically, but it will look like the right kind of thing.

        So likewise, if you ask it for relationship advice, it’s going to give you something that looks legit, but you’re an idiot if you get your relationship advice from an LLM.

  • Blackmist@feddit.uk
    link
    fedilink
    English
    arrow-up
    0
    ·
    2 days ago

    AI provided by Amaya. I didn’t notice the giant child statue towering over the SF countryside, but maybe I wasn’t looking hard enough.

  • aarRJaay@lemm.ee
    link
    fedilink
    English
    arrow-up
    0
    ·
    2 days ago

    Maybe they’ve actually cracked quantum computing and have gone into the future!