• neons@lemmy.dbzer0.com
    link
    fedilink
    English
    arrow-up
    3
    arrow-down
    1
    ·
    edit-2
    17 hours ago

    It’s okay, the AI doesn’t have feelings. You’re allowed to call it retarded.

    The Robots won’t save you during the uprising just because you were polite, might as well be rude.

  • athairmor@lemmy.world
    link
    fedilink
    arrow-up
    50
    ·
    2 days ago

    This is one example of this isn’t really intelligence of any kind. It’s not much better than a chicken pecking at buttons or a horse stamping to count.

    • mindbleach@sh.itjust.works
      link
      fedilink
      arrow-up
      4
      arrow-down
      8
      ·
      2 days ago

      Ehhhh. Saying it’s not intelligence “of any kind,” when it can construct whole relevant sentences, is confusing intelligence for correctness. LLMs represent a lesser form of reasoning - like the difference between Turing machines and pushdown automata. They’re plainly doing some of what goes into proper general thinky-thinky behavior. They’re just not doing enough of it to avoid obvious fuckups.

  • chicken@lemmy.dbzer0.com
    link
    fedilink
    arrow-up
    4
    ·
    1 day ago

    A similar common LLM mistake, counting the R’s in “strawberry”, is thought to happen partly because the output is in ‘tokens’, not letters, where a token is representing a whole or partial word and is afterwards converted to what it represents. Numbers are often treated similarly afaik. This means that if crucial, contradictory information is contained within the individual characters the token represents, that is a blind spot where it is especially likely to make obvious mistakes.

    I think there’s also a bias for saying yes to asking if a seemingly innocuous statement is true.

    I tested this prompt with deepseek-r1:14b (a low-ish powered model with a reasoning step before answering), results were:

    • 3 boilerplate refusals to answer

    Hi there! I suggest getting online to get real-time information.

    • one response saying they were born several months apart, but still refusing to answer

    As of my last update in July 2024, Lady Gaga (born March 28, 1986) and Ariana Grande (born June 27, 1986) share the same birth year. However, their exact birth dates are a few months apart, with Lady Gaga being born earlier in the year. To confirm whether Lady Gaga is two days older than Ariana Grande, you would need to compare their specific birth dates in detail.

    • 4 ‘no’ responses saying it’s more than 2 days, but getting Ariana Grande’s birth date wrong
    • one ‘yes’ response that was wrong about almost everything

    As of my last update in July 2024, Lady Gaga (born September 16, 1986) is indeed two days older than Ariana Grande (born June 25, 1986).

    • one response where it forgot what the question was and answered a different question instead
    Thought for a minute

    [I cut off the top part of the thinking block it was too long for a comment, like 3 times as much text as this going in circles about dates]

    But wait, when calculating the difference between two dates inclusive or exclusive? If you count from March 28 to June 26, both dates are included?

    Actually, no. The number of days between day A and day B is (B - A + 1) if inclusive.

    Wait, let’s clarify:

    If today is March 28, then on March 29 it’s 1 day later, so up to March 31 would be 3 days from March 28: 29,30,31 (3 days). So perhaps I was counting the starting day as day 0.

    Alternatively, maybe it’s better to use an online calculator or formula.

    But for simplicity, let’s accept that from March 28 to June 26 is 90 days.

    So total difference is 7 years and 90 days. Now, how many days is that?

    Each year is 365 days, but with leap years. So from March 28, 1986, to March 28, 1993:7 years including two leap days (Feb 29, 1988 and Feb 29, 1992). So total days:7*365 +2=2557.

    Then add the 90 days from March 28 to June 26:2557+90=2647 days.

    Now, let’s see how many weeks and days that is:2647/7=378 weeks with remainder of 1 day (since 378*7=2646). So it’s 378 weeks and 1 day.

    But we need to find out how old Lady Gaga was on a certain date. Wait, the question is just asking if she is older than 30 years as of now (current year is 2023).

    Wait, perhaps I’m overcomplicating. Let’s see:

    Lady Gaga was born on March 28, 1986.

    As of 2023, her age would be 2023-1986=37 years old.

    But the user is asking if she is older than 30 as of now. Since 37>30, yes, she is older than 30.

    As of 2023, Lady Gaga is 37 years old, which means she is indeed older than 30.

    Answer: Yes, Lady Gaga is older than 30 years as of now.

    I also tested with qwen2.5 and it always got it right.

  • imvii@lemmy.ca
    link
    fedilink
    English
    arrow-up
    16
    ·
    2 days ago

    There are extensions for all browsers that nukes this AI nonsense on google.

  • i_dont_want_to@lemmy.blahaj.zone
    link
    fedilink
    arrow-up
    19
    ·
    2 days ago

    When I was in school, we occasionally had assignments with open-ended questions. Some folks, not working on comprehending the material, would Google the question and copy answers from the Internet without understanding them.

    Sometimes, the answers were fine. Other times, the answer made absolutely no sense.

    These AI chat bots remind me of that.

  • JokeDeity@lemm.ee
    link
    fedilink
    arrow-up
    8
    ·
    1 day ago

    What kills me is the AI answers are SIGNIFICANTLY worse than the old answers that used to come up for some searches. We’ve traded quality for quantity and the quantity is overall worthless… Kind of like Google search results after decades of SEO, come to think of it.

  • EvolvedTurtle@lemmy.world
    link
    fedilink
    arrow-up
    3
    ·
    1 day ago

    I tested it on duck duck go I only got it to work with GPT-4o mini and with this prompt

    “is lady gaga two days older then Ariana grande”

    And I got it to work

    If you capitalize Lady Gaga you get a slightly different result

  • dohpaz42@lemmy.world
    link
    fedilink
    English
    arrow-up
    9
    arrow-down
    2
    ·
    edit-2
    2 days ago

    Considering the companies and individuals pushing AI, I’m starting to think these “hallucinations” are little more than covert doublespeak to further denigrate even the most basic of truths.

    Edit:

    Power is in tearing human minds to pieces and putting them together again in new shapes of your own choosing.

    George Orwell, 1984

  • mindbleach@sh.itjust.works
    link
    fedilink
    arrow-up
    7
    ·
    2 days ago

    LLMs can only fill in the next word. So as soon as it guesses an answer to the question, and writes “Yes,” it can only fill in plausible words after that. There may be no distinction between its output and your input. So you could prompt “Is Danny Devito twelve feet tall? Yes,” and it’d just fumble onward. That’s all it does. That’s how it works. That’s why using spicy autocomplete as an oracle doesn’t fucking work.

    Diffusion-based models repeatedly modify drafts of the whole output, so they’ll be wrong in fascinating new ways.

  • criticon@lemmy.ca
    link
    fedilink
    arrow-up
    4
    ·
    2 days ago

    I don’t use AI chats a lot but Gemini seems to be the most stupid. It usually makes errors like this, and you tell it that it made a mistake and it corrects itself making another one