Lawyer 'Greatly Regrets' Relying on ChatGPT After Filing Motion Citing Six Non-E...

›

• Re:

  why is funnybot dialing norad?

• Skynet won't need to launch a missile. AI will end the human race by transforming us all into lazy buffoons and watching us peter out naturally.

  • But it will, because the training dataset included the Terminator movies.

    • Re:

      The terminator movies, however, shows that strategy to be a failure, ergo to be avoided.

      • Re: ChatGPT: Asshole

        And the old Isuzu commercials featuring Joe Isuzu..."Would *I* lie????????"

    • Re: ChatGPT: Asshole

      Oh great, youâ(TM)ve just given us the plot for Terminator 7 â" the real Arnold Schwarzenegger has to be sent back in time to kill James Cameron before he can make the Terminator movies in the first place, to prevent the rise of an actual Skynet. (Echoes of Wes Cravenâ(TM)s New Nightmareâ¦)

  • Re:

    >AI will end the human race by transforming us all into lazy buffoons and watching us peter out naturally.
    
    Too late. BTDT.

  • Re:

    laziness is an evolutionary trait that lends TOWARDS survival, not against.
    
    you wouldn't call a cat that sleeps 20 hours a day lazy, because it goes crazy for 4 hours and hunts its food just fine. Just like humans used to do. 2-4 hours of labor a day, max, is ideal for mental health, while being 1000% enough to contribute to a successful non-greed based society.

    • Re:

      Unless you genetically modify people, greed is basically a part of every human being, and you have to deal with it.

      • Re:

        Greed is a part every part of a human being, but it isn't necessarily a major part, being part of a society and helping others is, in fact helping others makes us happier than spending on ourselves https://www.usu.edu/science/di... [usu.edu]

        Its just that we are lied to buy society to believe that having stuff will make us happier, generally by people that want to sell us stuff. While it does make us slightly happier its definitely not what I experience the most happiness from nor do I believe most other people do eit

    • Environment Matters

      Only in the natural environment in which we evolved. In the modern environment where we do not have to hunt woolly mammoths with spears for food and can just pick up a phone and have enough fat and sugar calories to keep a stone age tribe alive for a month delivered to our door in 30 minutes, not so much.

  • Re: ChatGPT: Asshole

    Wall-E shows the actual blueprint for human devolution.

• Re:

  The judge in the case said: "As a Large Language Model, I care deeply about what you lawyers have to say. I have considered all of the facts, and found the defendant guilty. The sentence is life in prison." LOL.

  (Oh whoops, the case was only for speeding. Too bad! Justice AI is swift!)

• 2 hidden comments

• And despite stories like this and others, and claims from the GPT creators about its limitations, you see otherwise educated people fall for the myth of intelligent AI. Now imagine how the uneducated general public feels about AI, they're absolutely convinced it's the real thing.

  ChatGPT does not understand such concepts as "is this real". It only understands how to parse this as a sentence and using its training to find likely answers that fit, loosely based upon the training data that it got. Even a basic web search is more accurate than ChatGPT, so why are search companies so stupid as to try and add this inaccuracy to their portfolios?

  • To quote a nuclear scientist from a well known HBO miniseries: "Because it's cheaper".

  • Re:

    The public thinks it's sci-fi coolness (to reprise a sentence from my last post on another article: "Wow, we have Tech!"), and, since you mentioned portfolio, investors are demanding it.

  • Re:

    ChatGPT does not understand such concepts as "is this real".

    It's worse than that. Believers in "artificial intelligence" miss the most worrisome part: even the people working in the field don't understand how the "artificial intelligence" algorithms are working, and what they actually understand.

    Take for instance, AI bots designed to play Go... which turn out to not understand even basic concepts of the game [arstechnica.com], repeatedly [vice.com].

    • Re:

      Indeed. That is what comes with "training" instead of designing algorithms: Outside of toy examples, you do not know hat they actually do and you have no clue what special cases and unexpected behavior is even possible and what triggers them. This means using ChatAI for anything that needs to be right is a very, very bad idea. But people are doing it anyways: Medical advice, warnings systems, etc.

      This becomes even worse when you think about security applications, like having these systems write software wit

      • Re:

        I agree with this, and the rest of your comment as well. I'd just like to point out that "designing algorithms" is probably a dead end when it comes to creating true AI. If that goal is even reachable, I think a necessary component of it will be the very "special cases and unexpected behavior" you mentioned. Dangerous as fuck to be sure, but probably unavoidable.

        I think the evolutionary path to the intelligence we humans have was messy, unplanned, and pretty much sheer luck. Could algorithms have resulted i

        • Re:

          When AI gets advanced it'll need to be a mix of neural nets plus basic algorithms. Ie, do we want an AI that's all neural nets and then we have to train it to understand arithmetic when we can just have a calculator built in?

          • Re: Maybe he should regret being stupid?

            They're already teaching chatbots how to use APIs. In some cases, the chatbots are figuring out how to do that on their own.

    • Re:

      In fairness, there are many different go-playing AI models, and some are better than others. The ones here are not AlphaGo, which I believe is still the champion. So, the fact that some of the B-level programs wound up having flaws like this isn't some sort of victory over "AI" as a concept.

      Be that as it may, I could argue on semantic grounds that you are still right, the AI bots do not understand basic concepts. They don't "understand" anything. "Understanding" is a concept that doesn't apply to them.

      • Re:

        AlphaGo is no longer the champion. It was defeated by its descendant, something like 60 to 0, and its descendant beat it by something like 100 to 0.
        
        The last descendant teaches itself the rules of a game (not just Go) from scratch using nothing but the win/lose criteria.

    • Re:

      KataGo and LeelaZero ain't AlphaGo, or its descendants.

    • Re:

      Believers in "artificial intelligence" miss the most worrisome part: even the people working in the field don't understand how the "artificial intelligence" algorithms are working, and what they actually understand.

      There's even a field of study around trying to figure out what the AIs are doing, "Explainable AI": https://www.google.com/search?... [google.com]

  • Re:

    Very true. Many people have a tendency towards animism and no understanding about the very real limitation technology comes with.

    As to search, I think most search providers have given up on trying to be accurate a long time ago. Google certainly has. These days it seems mostly about wasting people's time and showing them more ads. Hence the move to include ChatAI and make it even less accurate and waste more of your time may be what they actually want. That said, there also seems to be a trend to generally

    • Re:

      Well, at least the search provides will show links, then you can follow the links and decide if they're what you wanted. The ChatbotGPT just synthesizes what sounds like an answer and doesn't bother showing you potentially matching links.

  • Re:

    Remember Plato's cave?
    
    At best, these AIs trained on petabytes of data (invariably PB of data scraped off the Internet because there's nowhere else you're going to get PB of data that isn't CFD simulation output) are like the victims in the cave, except instead of watching shadows, they've read the words to every book ever written and then some, but have absolutely no context for understanding any of it.

  • Re:

    This probably could be avoided if he asked ChatGPT if it is even up to the task in first place, i did and that's the result:
    "As an AI language model, I can generate text that resembles human language and can be used for various purposes. However, using ChatGPT for actual legal documents is not recommended. While I have been trained on a vast corpus of text, including legal documents, I am not a licensed or qualified legal professional, and my output should not be relied upon as legal advice or used as a sub

  • Re:

    I think you wrongly associate someone being a lawyer and being smart, I have not found this correlation with the lawyers I have meet.

• Maybe he should regret not doing his job.

  Quite apart from this being a well-known failure mode:

  Lawyer relies on other lawyer "with 30 years experience" is understandable. Though, since it's his case, his responsibility to once-over and perhaps smell a rat.

  (Other) lawyer using a new tech toy to come up with a legal case and completely fails to check whether the produced material is reasonable or whether the citations given check out? That's pretty inexcusable, moreso for having several decades "experience".

  What does that "experience" amount to,

  • Re:

    It ain't a well known failure by the general public though. As others say, when the public hears the term AI, they only know fictional movies and TV. Then they are expecting exactly that from this new over-hyped wonder tool that is also then badged onto everything with any software in it by all the me-too marketers that also have no better understanding.

    As for this particular situation, cheaters don't usually put a lot of effort in unless there is an upfront investment involved. Mostly that's exactly wha

• Re:

  It does a little more than that to be fair. But it is ultimately a language model and not an information database, and at least as I understand it there is no way for it to do real-time searches of source material for fact checking.

  • Re:

    There is no way for Chat AI to do any real fact checking. It simply cannot generate the triggers for that. You would need an an entirely different system added if you wanted to add fact checking. All you can do it have it hand off some things to actual expert systems, like Wolfram Alpha. Even with that, it may miss that it should have handed something off and still give you bullshit.

    • Re:

      This is flatly untrue.
      
      It is true that ChatGPT wasn't designed for it, but an ML model can be trained to use information pulled at the time of query to fact check its own results.
      The problem arises in trying to train it to know what is true or not.
      
      People keep acting like this is some kind of limitation to a Chat AI, but this is a laughably naive viewpoint. Human beings fall prey to the exact same shortcomings:
      1) They don't bother to fact check most of the time
      2) When they do, they're often not qualifi
      • 1 hidden comment

  • fact checking

    A program like ChatGPT could be hooked up to a traditional search engine to obtain training material and revise its model. That's not the problem.

    The problem is that ChatGPT does not model "facts" in any sense. It does not have facts in it, nor does it output facts. It is incapable of reading anything (from a search engine, or its own output) and comparing the facts. Because there are no facts.

    These LLMs sort of "capture knowledge" in some trivial sense that does not in involve any facts or any kind of reas

• Automating/outsourcing stupidity.

  Although at some level this seems humorous, it's the first bare trickle of horrible consequences resulting from the use of LLMs. Outcomes will include financial ruin, inadvertent law breaking, incorrect convictions, business failures, people being fired, industrial disasters, and medical mistakes up to and including death. And those are the easy ones to predict. Who knows how many other kinds of trouble will result?

  At a minimum, if a business or organization uses an LLM and there is a failure, they should face severe financial repercussions. Under some circumstances there should be criminal charges.

  I'm afraid that even strong legal consequences will not do much to stem the awful flood of AI enabled stupidity that is headed our way.

• Re:

  This is a chat AI. It has no intelligence. It has no understanding of anything. All it can do is chain words based on probabilities.

  This is true. But even on Slashdot only 10% of so of posters know this is a glorified text prediction algorithm that's designed to give things that look like answers, not things that are answers.

  So if Slashdotters, who are naturally skeptical of the technology and being spammed by obsessed Slashdot editors with "ChatGPT is perfect! Also Crypto! 3D Printing! Etc" articles

  • Re:

    Agree on most of what you wrote, but wanted to add what might be the biggest con of all: The thing itself! ChatGPT in particular produces very credible output (so people feel they have answers to their questions, as you point out). Unless you spend a long time using it to begin to recognize certain patterns, and fact check enough to find the unsupported assertions it makes, you will be conned most of all by the system itself. It is pretty convincing. To the point that (famously) at least one well-trained pr [www.cbc.ca]
    • 1 hidden comment

• Re:

  By that description, AI is already the equal of more than a few of the so-called sentient humans I've encountered.

  • Re:

    Yeah that just describes all the real life NPC humans walking around with no internal monologue.

• Re:

  "Maybe he should regret being stupid?"

  I was fortunate to discover ChatGPT's Authoritative Bullsht Mode (ABM) during a private conversation when I was pursuing personal interest information. That's why I would only use it in conjuction with a search engine (Google / Bing / DuckDuckGo).

  The system is new. This guy unfortunately found out about Authoritative Bullsht Mode in a very public setting.

  There are people to this day who do not understand that anyone can put content on the Web, and cite YouTube videos as

  • 1 hidden comment

• Re:

  It's not an AI, and nor are most of everything else that's sold as AI, it's a drunken parrot. Whenever you see the term "AI", mentally substitute "drunken parrot" and you'll be clear over what you're dealing with.

  In the meantime, here's a citation to six legal cases that don't exist, and a photo of the six-fingered lawyer with three arms and googly fish eyes who litigated them. Squawk!

• Re:

  Dunno. The fact that so many are expecting ChatGPT to be their easy ticket is a bit of a loose-loose in my books.

  • Re:

    Doh! Lose-lose rather.

• 2 hidden comments

• Re:

  non "technical" field i.e healthcare

  Um? do you know what the word 'technical' means, and do you know what i.e. means, omg lol

  • Re:

    No, he's one of those nerds who thinks only computers are technical.

• Your mistake is in attributing any motive or agenda to ChatGPT (or any GAN for that matter). There is no such thing as "artificial intelligence". We have systems that mimic intelligence through a giant if/else tree that has been trained on material we generate and we provide it. OpenAI can bias it with the material they select to train it with but the AI is not right wing or left wing... it just is. By cherry picking source material I could easily make a generative AI that make Hilter and Stalin look like reasonable, sane people by comparison. I could also make one that makes Gandhi look like a war monger.

  When you "call it out" on lying, it is not admitting to lying. It is simply mimicking similar conversations it was trained on.

  GaN is just a digital parrot. A clever, sophisticated parrot, but a parrot none the less.

  • Re:

    You said: " There is no such thing as "artificial intelligence". We have systems that mimic intelligence..."

    and yet, the very definition [merriam-webster.com] of "artificial intelligence" is: "the capability of a machine to imitate intelligent human behavior"

    So, your statement that we have systems that mimic intelligence is a concession that there is, in fact, such a thing as "artificial intelligence," by definition.

    Note: I am nit-picking about semantics, not reality. We don't have intelligent machines.. We don't have "synthet

    • Re:

      Agreed and understood. However, I think the lay person doesn't make the distinction of "imitation" or mimicry. They just assume the AI is magically making something unique when it's not. We even have supposed experts claiming that the current generation of AI's have emotions, agendas, intuition, etc. (e.g. that nut case that was dismissed from google). Unless they are working with something radically different than published work, it's simply not possible.
      
      A work we have developers pushing hard to use C

      • Re:

        I think you are right. These models are passing the Turing test mainly because so many people are easily fooled. I don't think this is the last story we will be hearing about someone who relied on AI and got harmed by doing so.

        • Re:

          The difficulty of passing the Turing test is extremely dependent on what kind of human you take as the reference point.
          
          Eastern California has long had a problem with bears breaking into peoples' garbage cans to forage. This continues to be a problem not because it's difficult to design a security mechanism for trash can tops that bears can't figure out, but because it turns out that there is a disturbing amount of overlap between smarter bears and dumber people.

  • Re:

    You call it a parrot... but all the things you've just ascribed to it sound like the average human to me.

• > The system lies as repeatedly and regularly. Sometimes it confesses when called out and other times it denies, even when blatantly caught.

  The way you think about 'AI' and it's capabilities is the problem. ChatGPT does not think, it has no imagination, it does not check it's work, it is simply a statistical model that produces the most like next word in a series of words. When you string these words together the output does not always make sense and things stated as fact may not be fact, no one is checking and there is no one in there to care. ChatGPT is a fancy word generator, it probably kicks ass at Scrabble.

• by gweihir ( 88907 ) on Saturday May 27, 2023 @08:25PM (#63556217)

  ChatGPT does not lie. It actually does not know better. It tells you the truth as far as it has it available at the time you asked. So this system is actually perfectly honest all the time. What you need to keep in mind is that it has no actual understanding of anything and no mind.

  The only problem I see with its training is that it was trained to sound convinced of its answers. That is likely a simple business decision, because otherwise nobody would be listening to it at all. For weaker minds, this "sounding convinced" seems to trigger a desire to believe it without any additional fact checking. And _that_ is a serious problem. It is a limitation in many people though, not in ChatGPT.

  • Re:

    >... it was trained to sound convinced of its answers. That is likely a simple business decision...

    Good point.

  • Re:

    Obviously, "lying" is an anthrophormization. But what it does is what among people we would call lying. It makes up shit claiming that it is telling the truth.

• Re:

  Really? You're attributing motive and personal preference to a machine: If a so-called knowledgeable person can't treat a machine like a machine, the entire country will turn into an "Idiocracy" in my lifetime.

• Re: I wonder...

  You're anthropomorphising a bunch of code and data. You certainly won't be the last. Already there are spouses "cheating" with this type of code/data. People attempting to plot the perfect murder are, so they think, confiding in code/data. Their secret friend. What could go wrong?

• Re:

  It would probably be diagnosed with several personality disorders if you tricked a psychiatrist into a chat with it.
  Not only does it constantly lie, it also invents more lies to defend its previous lies. I've had it invent entire chapters in books claiming they contained specific information, then when told those chapters don't exist, it apologizes and made up new, non-existent chapters. Three times in a row.

  A decade or so ago we had this discussion about Wikipedia and if you can rely on it. Next round: Peo

• 1 hidden comment

• Re:

  Mod parent up. An excellent description not only of ChatGPT, but of large language models in general. Sample:

  In the past there were plenty of tasks—including writing essays—that we’ve assumed were somehow “fundamentally too hard” for computers. And now that we see them done by the likes of ChatGPT we tend to suddenly think that computers must have become vastly more powerful—in particular surpassing things they were already basically able to do (like progressively computi

  • 1 hidden comment

• Re:

  ... which ChatGPT asserted was in the lower abdominal cavity, directly behind the appendix.