Skip to content

AI agents wrong ~70% of time: Carnegie Mellon study

Technology
283 108 245
  • This post did not contain any content.

    Why would they be right beyond word sequence frecuencies?

  • There's a sleep button on my laptop. Doesn't mean I would use it.

    I'm just trying to say you're saying the feature that everyone kind of knows doesn't work. Chatgpt is not trained to do calculations well.

    I just like technology and I think and fully believe the left hatred of it is not logical. I believe it stems from a lot of media be and headlines. Why there's this push From media is a question I would like to know more. But overall, I see a lot of the same makers of bullshit yellow journalism for this stuff on the left as I do for similar bullshit on the right wing spaces towards other things.

    Again with dismissing the evidence of my own eyes!

    I wasn't asking it to do calculations, I was asking it to put the data into a super formulaic sentence. It was good at the first couple of rows then it would get stuck in a rut and start lying. It was crap. A seven year old would have done it far better, and if I'd told a seven year old that they had made a couple of mistakes and to check it carefully, they would have done.

    Again, I didn't read it in a fucking article, I read it on my fucking computer screen, so if you'd stop fucking telling me I'm stupid for using it the way it fucking told me I could use it, or that I'm stupid for believing what the media tell me about LLMs, when all I'm doing is telling you my own experience, you'd sound a lot less like a desperate troll or someone who is completely unable to assimilate new information that differs from your dogma.

  • That looks better. Even with a fair coin, 10 heads in a row is almost impossible.

    And if you are feeding the output back into a new instance of a model then the quality is highly likely to degrade.

    Whereas if you ask a human to do the same thing ten times, the probability that they get all ten right is astronomically higher than 0.0000059049.

  • Again with dismissing the evidence of my own eyes!

    I wasn't asking it to do calculations, I was asking it to put the data into a super formulaic sentence. It was good at the first couple of rows then it would get stuck in a rut and start lying. It was crap. A seven year old would have done it far better, and if I'd told a seven year old that they had made a couple of mistakes and to check it carefully, they would have done.

    Again, I didn't read it in a fucking article, I read it on my fucking computer screen, so if you'd stop fucking telling me I'm stupid for using it the way it fucking told me I could use it, or that I'm stupid for believing what the media tell me about LLMs, when all I'm doing is telling you my own experience, you'd sound a lot less like a desperate troll or someone who is completely unable to assimilate new information that differs from your dogma.

    What does "I give it data to put in a formulaic sentence." mean here

    Why not just share the details. I often find a lot of people saying it's doing crazy things and never like to share the details. It's very similar to discussing things with Trump supporters who do the same shit when pressed on details about stuff they say occurs. Like the same "you're a troll for asking for evidence of my claim" that trumpets do. It's wild how similar it is.

    And yes asking to do things like iterate over rows isn't how it works. It's getting better but that's not what it's primarily used for. It could be but isn't. It only catches so many tokens. It's getting better and has some persistence but it's nowhere near what its strength is.

  • Whereas if you ask a human to do the same thing ten times, the probability that they get all ten right is astronomically higher than 0.0000059049.

    Dunno. Asking 10 humans at random to do a task and probably one will do it better than AI. Just not as fast.

  • What does "I give it data to put in a formulaic sentence." mean here

    Why not just share the details. I often find a lot of people saying it's doing crazy things and never like to share the details. It's very similar to discussing things with Trump supporters who do the same shit when pressed on details about stuff they say occurs. Like the same "you're a troll for asking for evidence of my claim" that trumpets do. It's wild how similar it is.

    And yes asking to do things like iterate over rows isn't how it works. It's getting better but that's not what it's primarily used for. It could be but isn't. It only catches so many tokens. It's getting better and has some persistence but it's nowhere near what its strength is.

    I would be in breach of contract to tell you the details. How about you just stop trying to blame me for the clear and obvious lies that the LLM churned out and start believing that LLMs ARE are strikingly fallible, because, buddy, you have your head so far in the sand on this issue it's weird.

    The solution to the problem was to realise that an LLM cannot be trusted for accuracy even if the first few results are completely accurate, the bullshit well creep in. Don't trust the LLM. Check every fucking thing.

    In the end I wrote a quick script that broke the input up on tab characters and wrote the sentence. That's how formulaic it was. I regretted deeply trying to get an LLM to use data.

    The frustrating thing is that it is clearly capable of doing the task some of the time, but drifting off into FANTASY is its strong suit, and it doesn't matter how firmly or how often you ask it to be accurate or use the input carefully. It's going to lie to you before long. It's an LLM. Bullshitting is what it does. Get it to do ONE THING only, then check the fuck out of its answer. Don't trust it to tell you the truth any more than you would trust Donald J Trump to.

  • Dunno. Asking 10 humans at random to do a task and probably one will do it better than AI. Just not as fast.

    You're better off asking one human to do the same task ten times. Humans get better and faster at things as they go along. Always slower than an LLM, but LLMs get more and more likely to veer off on some flight of fancy, further and further from reality, the more it says to you. The chances of it staying factual in the long term are really low.

    It's a born bullshitter. It knows a little about a lot, but it has no clue what's real and what's made up, or it doesn't care.

    If you want some text quickly, that sounds right, but you genuinely don't care whether it is right at all, go for it, use an LLM. It'll be great at that.

  • This post did not contain any content.

    Reading with CEO mindset. 3 out of 10 employees can be fired.

  • I would be in breach of contract to tell you the details. How about you just stop trying to blame me for the clear and obvious lies that the LLM churned out and start believing that LLMs ARE are strikingly fallible, because, buddy, you have your head so far in the sand on this issue it's weird.

    The solution to the problem was to realise that an LLM cannot be trusted for accuracy even if the first few results are completely accurate, the bullshit well creep in. Don't trust the LLM. Check every fucking thing.

    In the end I wrote a quick script that broke the input up on tab characters and wrote the sentence. That's how formulaic it was. I regretted deeply trying to get an LLM to use data.

    The frustrating thing is that it is clearly capable of doing the task some of the time, but drifting off into FANTASY is its strong suit, and it doesn't matter how firmly or how often you ask it to be accurate or use the input carefully. It's going to lie to you before long. It's an LLM. Bullshitting is what it does. Get it to do ONE THING only, then check the fuck out of its answer. Don't trust it to tell you the truth any more than you would trust Donald J Trump to.

    This is crazy. I've literally been saying they are fallible. You're saying your professional fed and LLM some type of dataset. So I can't really say what it was you're trying to accomplish but I'm just arguing that trying to have it process data is not what they're trained to do. LLM are incredible tools and I'm tired of trying to act like they're not because people keep using them for things they're not built to do. It's not a fire and forget thing. It does need to be supervised and verified. It's not exactly an answer machine. But it's so good at parsing text and documents, summarizing, formatting and acting like a search engine that you can communicate with rather than trying to grok some arcane sentence. Its power is in language applications.

    It is so much fun to just play around with and figure out where it can help. I'm constantly doing things on my computer it's great for instructions. Especially if I get a problem that's kind of unique and needs a big of discussion to solve.

  • This is crazy. I've literally been saying they are fallible. You're saying your professional fed and LLM some type of dataset. So I can't really say what it was you're trying to accomplish but I'm just arguing that trying to have it process data is not what they're trained to do. LLM are incredible tools and I'm tired of trying to act like they're not because people keep using them for things they're not built to do. It's not a fire and forget thing. It does need to be supervised and verified. It's not exactly an answer machine. But it's so good at parsing text and documents, summarizing, formatting and acting like a search engine that you can communicate with rather than trying to grok some arcane sentence. Its power is in language applications.

    It is so much fun to just play around with and figure out where it can help. I'm constantly doing things on my computer it's great for instructions. Especially if I get a problem that's kind of unique and needs a big of discussion to solve.

    it’s so good at parsing text and documents, summarizing

    No. Not when it matters. It makes stuff up. The less you carefully check every single fucking thing it says, the more likely you are to believe some lies it subtly slipped in as it went along. If truth doesn't matter, go ahead and use LLMs.

    If you just want some ideas that you're going to sift through, independently verify and check for yourself with extreme skepticism as if Donald Trump were telling you how to achieve world peace, great, you're using LLMs effectively.

    But if you're trusting it, you're doing it very, very wrong and you're going to get humiliated because other people are going to catch you out in repeating an LLM's bullshit.

  • it’s so good at parsing text and documents, summarizing

    No. Not when it matters. It makes stuff up. The less you carefully check every single fucking thing it says, the more likely you are to believe some lies it subtly slipped in as it went along. If truth doesn't matter, go ahead and use LLMs.

    If you just want some ideas that you're going to sift through, independently verify and check for yourself with extreme skepticism as if Donald Trump were telling you how to achieve world peace, great, you're using LLMs effectively.

    But if you're trusting it, you're doing it very, very wrong and you're going to get humiliated because other people are going to catch you out in repeating an LLM's bullshit.

    If it's so bad as if you say, could you give an example of a prompt where it'll tell you incorrect information.

  • If it's so bad as if you say, could you give an example of a prompt where it'll tell you incorrect information.

    It's like you didn't listen to anything I ever said, or you discounted everything I said as fiction, but everything your dear LLM said is gospel truth in your eyes. It's utterly irrational. You have to be trolling me now.

  • It's like you didn't listen to anything I ever said, or you discounted everything I said as fiction, but everything your dear LLM said is gospel truth in your eyes. It's utterly irrational. You have to be trolling me now.

    Should be easy if it's that bad though

  • Should be easy if it's that bad though

    I already told you my experience of the crapness of LLMs and even explained why I can't share the prompt etc. You clearly weren't listening or are incapable of taking in information.

    There's also all the testing done by the people talked about in the article we're discussing which you're also irrationally dismissing.

    You have extreme confirmation bias.

    Everything you hear that disagrees with your absurd faith in the accuracy of the extreme blagging of LLMs gets dismissed for any excuse you can come up with.

  • 670 Stimmen
    41 Beiträge
    5 Aufrufe
    patatahooligan@lemmy.worldP
    No, there's no way to automatically make something become law. A successful petition just forces the European Commission to discuss it and potentially propose legislation. Even though it's not forcing anything to happen, there is an incentive for the commission to seriously consider it as there is probably a political cost to officially denying a motion that has proven that it concerns a large amount of people.
  • Canada Drops Digital Tax That Infuriated Trump to Restart Trade Talks

    Technology technology
    17
    80 Stimmen
    17 Beiträge
    68 Aufrufe
    R
    Jesus fuck that’s a lot of days
  • 455 Stimmen
    149 Beiträge
    103 Aufrufe
    eyekaytee@aussie.zoneE
    They will say something like solar went from 600gw to 1000 thats a 66% increase this year and coal only increased 40% except coal is 3600gw to 6400. Hrmmmm, maybe these numbers are outdated? Based on this coal and gas are down: In Q1 2025, solar generation rose 48% compared to the same period in 2024. Solar power reached 254 TWh, making up 10% of total electricity. This was the largest increase among all clean energy sources. Coal-fired electricity dropped by 4%, falling to 1,421 TWh. Gas-fired power also went down by 4%, reaching 67 TWh https://carboncredits.com/china-sets-clean-energy-record-in-early-2025-with-951-tw/ are no where close to what is required to meet their climate goals Which ones in particular are you talking about? Trump signs executive order directing US withdrawal from the Paris climate agreement — again https://apnews.com/article/trump-paris-agreement-climate-change-788907bb89fe307a964be757313cdfb0 China vowed on Tuesday to continue participating in two cornerstone multinational arrangements -- the World Health Organization and Paris climate accord -- after newly sworn-in US President Donald Trump ordered withdrawals from them. https://www.france24.com/en/live-news/20250121-china-says-committed-to-who-paris-climate-deal-after-us-pulls-out What's that saying? You hate it when the person you hate is doing good? I can't remember what it is I can't fault them for what they're doing at the moment, even if they are run by an evil dictatorship and do pollute the most I’m not sure how european defense spending is relevant It suggests there is money available in the bank to fund solar/wind/battery, but instead they are preparing for? something? what? who knows. France can make a fighter jet at home but not solar panels apparently. Prehaps they would be made in a country with environmental and labour laws if governments legislated properly to prevent companies outsourcing manufacturing. However this doesnt absolve china. China isnt being forced at Gunpoint to produce these goods with low labour regulation and low environmental regulation. You're right, it doesn't absolve china, and I avoid purchasing things from them wherever possible, my solar panels and EV were made in South Korea, my home battery was made in Germany, there are only a few things in my house made in China, most of them I got second hand but unfortunately there is no escaping the giant of manufacturing. With that said it's one thing for me to sit here and tut tut at China, but I realise I am not most people, the most clearest example is the extreme anti-ai, anti-billionaire bias on this platform, in real life most people don't give a fuck, they love Amazon/Microsoft/Google/Apple etc, they can't go a day without them. So I consider myself a realist, if you want people to buy your stuff then you will need to make the conditions possible for them to WANT to buy your stuff, not out of some moral lecture and Europe isn't doing that, if we look at energy prices: Can someone actually point out to me where this comes from? ... At the end of the day energy is a small % of EU household spending I was looking at corporate/business energy use: Major European companies are already moving to cut costs and retain their competitive edge. For example, Thyssenkrupp, Germany’s largest steelmaker, said on Monday it would slash 11,000 jobs in its steel division by 2030, in a major corporate reshuffle. https://oilprice.com/Latest-Energy-News/World-News/High-Energy-Costs-Continue-to-Plague-European-Industry.html Prices have since fallen but are still high compared to other countries. A poll by Germany's DIHK Chambers of Industry and Commerce of around 3,300 companies showed that 37% were considering cutting production or moving abroad, up from 31% last year and 16% in 2022. For energy-intensive industrial firms some 45% of companies were mulling slashing output or relocation, the survey showed. "The trust of the German economy in energy policy is severely damaged," Achim Dercks, DIHK deputy chief executive said, adding that the government had not succeeded in providing companies with a perspective for reliable and affordable energy supply. https://www.reuters.com/business/energy/more-german-companies-mull-relocation-due-high-energy-prices-survey-2024-08-01/ I've seen nothing to suggest energy prices in the EU are SO cheap that it's worth moving manufacturing TO Europe, and this is what annoys me the most. I've pointed this out before but they have an excellent report on the issues: https://commission.europa.eu/document/download/97e481fd-2dc3-412d-be4c-f152a8232961_en?filename=The+future+of+European+competitiveness+_+A+competitiveness+strategy+for+Europe.pdf Then they put out this Competitive Compass: https://commission.europa.eu/topics/eu-competitiveness/competitiveness-compass_en But tbh every week in the EU it seems like they are chasing after some other goal. This would be great, it would have been greater 10 years ago. Agreed
  • 6 Stimmen
    4 Beiträge
    22 Aufrufe
    T
    Oh I agree. I just think is part of the equation perhaps the thinner and lighter will enable for better processor? Not an AR guy , although I lived my oculus until FB got hold of it. Didn't use it ever again after that day.
  • 108 Stimmen
    22 Beiträge
    81 Aufrufe
    I
    Their previous GPU used an old AMD GPU design if I recall correctly. I wonder if they have in-house stuff now.
  • Stack overflow is almost dead

    Technology technology
    5
    0 Stimmen
    5 Beiträge
    28 Aufrufe
    ineedmana@lemmy.worldI
    students When I was a student I despised the idea of typeless var in C#. Then a few years later at my day job I fully embraced C++ auto. I understand the frustration but unfortunately being wrong is part of learning
  • 7 Stimmen
    9 Beiträge
    41 Aufrufe
    V
    Ah yeah, that doesn't look like my cup of tea.
  • Nextcloud cries foul over Google Play Store app rejection

    Technology technology
    1
    1
    6 Stimmen
    1 Beiträge
    11 Aufrufe
    Niemand hat geantwortet