Skip to content

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

Technology
285 108 690
  • 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.

  • 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.

    You're projecting here. I'm asking you to give an example of any prompt. You're saying it's so bad that it needs to be babysat because it's errors. I'll only asking for your to give an example and you're saying that's confirmation bias and acting like I'm being religiously ignorant

  • You're projecting here. I'm asking you to give an example of any prompt. You're saying it's so bad that it needs to be babysat because it's errors. I'll only asking for your to give an example and you're saying that's confirmation bias and acting like I'm being religiously ignorant

    This is you

  • 142 Stimmen
    5 Beiträge
    0 Aufrufe
    B
    Of all the crap that comes out of the dipshit-in-chief's mouth, the one thing I really wish he would've followed through on was deporting Elmo.
  • 83 Stimmen
    19 Beiträge
    72 Aufrufe
    E
    The cost of consuming media doesn’t match its worth. I never used ad blockers until they became invasive and disruptive.
  • WhatsApp rolls out AI-generated summaries for private messages

    Technology technology
    26
    1
    96 Stimmen
    26 Beiträge
    88 Aufrufe
    W
    So I think, but I'm not sure, this is for group chats. Group chats are only encrypted to/from the server because the server broadcasts the message to each recipient. As the messages are unencrypted on the server, they can feed them to LLMs. This is different to Signal. On Signal it's your phone encrypting each copy of the message before sending to each recipient individually.
  • Palantir hits new highs amid Israel-Iran conflict

    Technology technology
    4
    1
    41 Stimmen
    4 Beiträge
    26 Aufrufe
    W
    I think both peace and war are profitable. But those that profit from war may be more pushy than those that profit from peace, and so may get their way even as an unpopular minority . Unless, the left (usually more pro peace) learns a few lessons from the right and places good outcomes above the holier than thou moral purity. "I've never made anyone uncomfortable" is not the merit badge that some think it is. Of course the left can never be a mirror copy of the right because the left cannot afford to give as few fucks about anything as the right (who represent the already-haves economic incumbents; it's not called the "fuck you money" for nothing). But the left can be way tougher and nuancedly uncompromising and even calculatingly and carefully millitant. Might does not make right but might DOES make POLICY. You need both right and might to live under a good policy. Lotta good it does anyone to be right and insightful on all the issues and have zero impact anywhere.
  • Texting myself the weather every day

    Technology technology
    4
    15 Stimmen
    4 Beiträge
    27 Aufrufe
    G
    Even being too lazy to open the weather app, there are so many better and free ways of receiving a message on your phone. This is profoundly stupid.
  • 61 Stimmen
    11 Beiträge
    51 Aufrufe
    K
    If you use LLMs like they should be, i.e. as autocomplete, they're helpful. Classic autocomplete can't see me type "import" and correctly guess that I want to import a file that I just created, but Copilot can. You shouldn't expect it to understand code, but it can type more quickly than you and plug the right things in more often than not.
  • 25 Stimmen
    9 Beiträge
    48 Aufrufe
    S
    I didn't care much about arc because it was chromium, but damn this is just bland and uninteresting compared to it
  • 0 Stimmen
    4 Beiträge
    6 Aufrufe
    K
    Only way I'll want a different phone brand is if it comes with ZERO bloatware and has an excellent internal memory/storage cleanse that has nothing to do with Google's Files or a random app I'm not sure I can trust without paying or rooting. So far my A series phones do what I need mostly and in my opinion is superior to the Motorola's my fiancé prefers minus the phone-phone charge ability his has, everything else I'm just glad I have enough control to tweak things to my liking, however these days Samsungs seem to be infested with Google bloatware and apps that insist on opening themselves back up regardless of the widespread battery restrictions I've assigned (even was sent a "Stop Closing my Apps" notif that sent me to an article ) short of Disabling many unnecessary apps bc fully rooting my devices is something I rarely do anymore. I have a random Chinese brand tablet where I actually have more control over the apps than either of my A series phones whee Force Stopping STAYS that way when I tell them to! I hate being listened to for ads and the unwanted draining my battery life and data (I live off-grid and pay data rates because "Unlimited" is some throttled BS) so my ability to control what's going on in the background matters a lot to me, enough that I'm anti Meta-apps and avoid all non-essential Google apps. I can't afford topline phones and the largest data plan, so I work with what I can afford and I'm sad refurbished A lines seem to be getting more expensive while giving away my control to companies. Last A line I bought that was supposed to be my first 5G phone was network locked, so I got ripped off, but it still serves me well in off-grid life. Only app that actually regularly malfunctions when I Force Stop it's background presence is Roku, which I find to have very an almost insidious presence in our lives. Google Play, Chrome, and Spotify never acts incompetent in any way no matter how I have to open the setting every single time I turn Airplane Mode off. Don't need Gmail with Chrome and DuckDuckGo has been awesome at intercepting self-loading ads. I hope one day DDG gets better bc Google seems to be terrible lately and I even caught their AI contradicting itself when asking about if Homo Florensis is considered Human (yes) and then asked the oldest age of human remains, and was fed the outdated narrative of 300,000 years versus 700,000+ years bipedal pre-humans have been carbon dated outside of the Cradle of Humanity in South Africa. SO sorry to go off-topic, but I've got a big gripe with Samsung's partnership with Google, especially considering the launch of Quantum Computed AI that is still being fine-tuned with company-approved censorships.