Skip to content

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

Technology
285 108 721
  • 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

  • 64 Stimmen
    2 Beiträge
    2 Aufrufe
    W
    In April, Nigeria asked Google, Microsoft, and Amazon to set concrete deadlines for opening data centers in the country. Nigeria has been making this demand for about four years, but the companies have so far failed to fulfill their promises. Now, Nigeria has set up a working group with the companies to ensure that data is stored within its shores. Just onshoring the data center does not solve the problems. You can't be sure no data travels to the US servers, some data does need to travel to the US servers, and the entire DC is still subject to US software and certificate keychains. It's better, but not good or safe. I need to channel my inner Mike Ehrmantrout to the US tech companies and government: you had a good thing going you stupid son of a bitch. You had everything you needed and it all ran like clockwork. You could have shut your mouth, cooked, and made as much money as you needed, but you just had to blow it up, you and your pride and your ego. Seriously, this is a massive own goal by the US government. This is a massive loss to US hegemony and influence around the world that's never coming back. It has never been easier to build sovereign clouds with off the shelf and open source tooling. The best practices are largely documented, software is commoditized, and there are plenty of qualified people out there these days and governments staring down the barrel of existential risk have finally got the incentive to fund these efforts.
  • Uber, Lyft oppose some bills that aim to prevent assaults during rides

    Technology technology
    12
    94 Stimmen
    12 Beiträge
    56 Aufrufe
    F
    California is not Colorado nor is it federal No shit, did you even read my comment? Regulations already exist in every state that ride share companies operate in, including any state where taxis operate. People are already not supposed to sexually assault their passengers. Will adding another regulation saying they shouldn’t do that, even when one already exists, suddenly stop it from happening? No. Have you even looked at the regulations in Colorado for ride share drivers and companies? I’m guessing not. Here are the ones that were made in 2014: https://law.justia.com/codes/colorado/2021/title-40/article-10-1/part-6/section-40-10-1-605/#%3A~%3Atext=§+40-10.1-605.+Operational+Requirements+A+driver+shall+not%2Ca+ride%2C+otherwise+known+as+a+“street+hail”. Here’s just one little but relevant section: Before a person is permitted to act as a driver through use of a transportation network company's digital network, the person shall: Obtain a criminal history record check pursuant to the procedures set forth in section 40-10.1-110 as supplemented by the commission's rules promulgated under section 40-10.1-110 or through a privately administered national criminal history record check, including the national sex offender database; and If a privately administered national criminal history record check is used, provide a copy of the criminal history record check to the transportation network company. A driver shall obtain a criminal history record check in accordance with subparagraph (I) of paragraph (a) of this subsection (3) every five years while serving as a driver. A person who has been convicted of or pled guilty or nolo contendere to driving under the influence of drugs or alcohol in the previous seven years before applying to become a driver shall not serve as a driver. If the criminal history record check reveals that the person has ever been convicted of or pled guilty or nolo contendere to any of the following felony offenses, the person shall not serve as a driver: (c) (I) A person who has been convicted of or pled guilty or nolo contendere to driving under the influence of drugs or alcohol in the previous seven years before applying to become a driver shall not serve as a driver. If the criminal history record check reveals that the person has ever been convicted of or pled guilty or nolo contendere to any of the following felony offenses, the person shall not serve as a driver: An offense involving fraud, as described in article 5 of title 18, C.R.S.; An offense involving unlawful sexual behavior, as defined in section 16-22-102 (9), C.R.S.; An offense against property, as described in article 4 of title 18, C.R.S.; or A crime of violence, as described in section 18-1.3-406, C.R.S. A person who has been convicted of a comparable offense to the offenses listed in subparagraph (I) of this paragraph (c) in another state or in the United States shall not serve as a driver. A transportation network company or a third party shall retain true and accurate results of the criminal history record check for each driver that provides services for the transportation network company for at least five years after the criminal history record check was conducted. A person who has, within the immediately preceding five years, been convicted of or pled guilty or nolo contendere to a felony shall not serve as a driver. Before permitting an individual to act as a driver on its digital network, a transportation network company shall obtain and review a driving history research report for the individual. An individual with the following moving violations shall not serve as a driver: More than three moving violations in the three-year period preceding the individual's application to serve as a driver; or A major moving violation in the three-year period preceding the individual's application to serve as a driver, whether committed in this state, another state, or the United States, including vehicular eluding, as described in section 18-9-116.5, C.R.S., reckless driving, as described in section 42-4-1401, C.R.S., and driving under restraint, as described in section 42-2-138, C.R.S. A transportation network company or a third party shall retain true and accurate results of the driving history research report for each driver that provides services for the transportation network company for at least three years. So all sorts of criminal history, driving record, etc checks have been required since 2014. Colorado were actually the first state in the USA to implement rules like this for ride share companies lol.
  • 92 Stimmen
    5 Beiträge
    22 Aufrufe
    H
    This is interesting to me as I like to say the llms are basically another abstraction of search. Initially it was links with no real weight that had to be gone through and then various algorithms weighted the return, then the results started giving a small blurb so one did not have to follow every link, and now your basically getting a report which should have references to the sources. I would like to see this looking at how folks engage with an llm. Basically my guess is if one treats the llm as a helper and collaborates to create the product that they will remember more than if they treat it as a servant and just instructs them to do it and takes the output as is.
  • 1k Stimmen
    78 Beiträge
    275 Aufrufe
    K
    I just hear that they move to LibreOffice but not to Linux, ateast not right now.
  • 80 Stimmen
    14 Beiträge
    55 Aufrufe
    B
    Didn’t he pay a hitman to murder a couple of people?
  • A World Without iPhones?

    Technology technology
    7
    34 Stimmen
    7 Beiträge
    39 Aufrufe
    S
    I believe the world was a better place before smartphones started dominating everyone's attention. It has had a profound impact on how people are socializing, and not in a positive way if you ask me.
  • A.I. Companies Believe They're Making God with Karen Hao [1:14:07]

    Technology technology
    8
    45 Stimmen
    8 Beiträge
    38 Aufrufe
    P
    … it was
  • 374 Stimmen
    69 Beiträge
    241 Aufrufe
    T
    In those situations I usually enable 1.5x.