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.

    • Carighan Maconar@lemmy.world
      link
      fedilink
      English
      arrow-up
      53
      ·
      9 days ago

      I mean to be fair that’s a niche event in a niche sports form in one backwards country that can’t even get their gov in order. 😛

      Jokes aside, it’s sad how far these agents/helpers have degraded. From the comparatively glorious Google Now that was black magic and would pull out tickets as you approached the starting point, recommend clothes and gear for weather at your destination and if you wandered around a few seconds told you where you parked your car, to nowadays being some AI slop that hallucinates shit constantly.

      • Zirconium@lemmy.world
        link
        fedilink
        English
        arrow-up
        14
        ·
        9 days ago

        Oh. The USA? Last I heard about them was having border disputes and their dictator is trying to fund AI projects

    • adarza@lemmy.ca
      link
      fedilink
      English
      arrow-up
      7
      ·
      9 days ago

      the old snippits ‘powered by’ wikipedia and such would have gotten those.

  • FlashMobOfOne@lemmy.world
    link
    fedilink
    English
    arrow-up
    52
    ·
    9 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
      13
      ·
      9 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.

  • Rhoeri@lemmy.world
    link
    fedilink
    English
    arrow-up
    45
    ·
    9 days ago

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

    • RedstoneValley@sh.itjust.works
      link
      fedilink
      English
      arrow-up
      44
      ·
      edit-2
      9 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
        7
        ·
        9 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.

    • RedditWanderer@lemmy.world
      link
      fedilink
      English
      arrow-up
      9
      ·
      9 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.

  • Majorllama@lemmy.world
    link
    fedilink
    English
    arrow-up
    34
    ·
    9 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.

    • 11111one11111@lemmy.world
      link
      fedilink
      English
      arrow-up
      2
      ·
      edit-2
      9 days ago

      I don’t get what ypur complaint is? At least it is talking about an event that hasn’t happened yet correctly, but what else would you want from it for you to say, “DDG’s AI Assist seems to answer correctly.”

      • reev@sh.itjust.works
        link
        fedilink
        English
        arrow-up
        1
        ·
        9 days ago

        All I’m saying is that in this specific instance it’s giving the correct information. I am not commenting on it’s reliability outside of this specific example.

  • aarRJaay@lemm.ee
    link
    fedilink
    English
    arrow-up
    12
    ·
    9 days ago

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

  • Blackmist@feddit.uk
    link
    fedilink
    English
    arrow-up
    6
    ·
    9 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.

  • werefreeatlast@lemmy.world
    link
    fedilink
    English
    arrow-up
    4
    ·
    9 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.

  • werefreeatlast@lemmy.world
    link
    fedilink
    English
    arrow-up
    2
    ·
    9 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!