I wasted 10-15 minutes trying to get ChatGPT to write a simple algorithm in Clojure and it fails miserably each time, from hallucinating functions to ...

I wasted 10-15 minutes trying to get ChatGPT to write a simple algorithm in Clojure and it fails miserably each time, from hallucinating functions to even hallucinating arguments to stdlib functions.

I've expressed the requirements in short bullet points, provided 5 test cases, instructed it how the stdlib functions it misuses actually work, and it still fricks up.

Meanwhile in 15 seconds I wrote a solution in three lines if code that passes all tests. Thanks for lying to me BOT. This thing sucks.

>inb4 buy ChatGPT Plus
No thanks. I'll wait for GPT-5 instead so I am not disappointed a second time.

ChatGPT Wizard Shirt $21.68

Beware Cat Shirt $21.68

ChatGPT Wizard Shirt $21.68

  1. 1 year ago
    Anonymous

    Why did girlish number flop?

    • 1 year ago
      Anonymous

      It was too girlish.

  2. 1 year ago
    Anonymous

    Try a different language

    • 1 year ago
      Anonymous

      Give me another language with namespaced keywords. Neither Ruby nor Lisp offer this, they have keywords in a single shared namespace.

      >clojure
      nobody cares neet

      projection

      Clojure? The boots, boys, the boots?

      cope

  3. 1 year ago
    (。>﹏<。)

    nakadashi inside her

  4. 1 year ago
    Anonymous

    >clojure
    nobody cares neet

  5. 1 year ago
    Anonymous

    Clojure? The boots, boys, the boots?

  6. 1 year ago
    Anonymous

    they probably didnt train it on that dead language

    • 1 year ago
      Anonymous

      more cope from a jobless undergroid

      you're trying to reason with a probabilistic madlibs machine
      of course it will fail

      I'm reasoning with a language model, but I guess it was overtrained on some homosexual language like Python which is why BOT and HN rave over it being able to stumble its way into a half-functional, 10-line selenium script.

      I've also tried getting it to answer questions about "popular tools" like Docker yet it will fail. I tell it to load a BuildX image and it insists on pushing to a registry first then pulling in image immediately after.

      But yes, I'm aware this thing lacks any reasoning capabilities given that you can claim it is wrong for any reason and it will spit out the same "I am sorry" template, only to repeat the exact same thing as before. It gives me a strong resemblance of ELIZA, which does similar template pasting and can fool people for a while until they notice the reptitive patterns in its output

      It really fricking sucks dick at anything remotely complicated. I spent a full fricking day trying to get it to build me a mongodb system that could use certificates I generated from C, and I ended up doing 95% of the work myself. It probably doesn't help that it was using old mongodb config names and shit, but it's nowhere near as useful as everyone is making it out to be.
      Hopefully someone makes some decent performance and ACTUALLY FRICKING OPEN alternative that I can feed my own projects into.

      Yup. In the end I decided to implement something menial myself. I first tried using it to output some GitHub actions boilerplate with BuildX and it never gave me a solution; 5 minutes of Google did.

      >inb4 some moron says "nooo its the prompts being bad!"

      • 1 year ago
        Anonymous

        >spit out the same "I am sorry" template, only to repeat the exact same thing as before
        This right here, it gives me broken shit and I tell it it's broken, then it just makes up some fricking function name and inserts that in there like some kind of "exercise is left to the reader" level of frick you.

  7. 1 year ago
    Anonymous

    It's almost useless. OpenAI is talking about it like they created AGI or close to it. This meme technology will be completely forgotten in a few years. It slows you down more than it helps you. Unironically, porn might be its best use.

  8. 1 year ago
    Anonymous

    you're trying to reason with a probabilistic madlibs machine
    of course it will fail

  9. 1 year ago
    Anonymous

    It really fricking sucks dick at anything remotely complicated. I spent a full fricking day trying to get it to build me a mongodb system that could use certificates I generated from C, and I ended up doing 95% of the work myself. It probably doesn't help that it was using old mongodb config names and shit, but it's nowhere near as useful as everyone is making it out to be.
    Hopefully someone makes some decent performance and ACTUALLY FRICKING OPEN alternative that I can feed my own projects into.

  10. 1 year ago
    Anonymous

    Its alright for some things. You just have to learn its advantages and disadvantages

  11. 1 year ago
    Anonymous

    try racket

  12. 1 year ago
    Anonymous

    It's only decent for basic js and python shit. It's absolutely fricking dogshit at making database designs too.

  13. 1 year ago
    Anonymous

    >ChatGPT training dataset didn't include data about fossilized crap called clojure and therefore it can't use its dialect
    what did you expect moron, AI to suddenly break laws of physics and write you accurate algorithm for dialect it does not know? NOOOOOOOOOOOOO MUH CHATGPT BAD, IT CANT USE QUANTUM NONLOCALITY TO SUPERLUMINALLY LEARN AND USE STUFF IT HAS NO PHYSICAL ACCESS TO

    braindead midwits like you is why AI threads should've been on BOT

    • 1 year ago
      Anonymous

      are you ok

      Several factors at play here, from my perspective. Here are some tips that can help you reflect on your performance:

      1) You can't proompt. You suck at proompting and should just git gud. Simply put, it's a skill issue on your end

      2) You're using the wrong model. Instead of using the free ChatGPT, consider using GPT-4. All the recent hype you've seen was about GPT-4, not ChatGPT. ChatGPT is GPT-3, or GPT-3.5 as the kids call it. GPT-4 is considerably more advanced, and expecting GPT-3.5 to perform at GPT-4 levels is unreasonable.

      These are some tips that could help you get better results from chat-based AI assistants. I hope this helps, and if you have any questions, feel free to ask. Good luck with your project!

      I can make ChatGPT eventually ignore its filters. I just can't get it to do anything remotely useful for work.

      I'll probably wait for GPT-5 since it's coming out by the end of this year anyway.

      >provided 5 test cases
      I don't think that helps at all because ChatGPT can't run code, maybe Copilot 2 will let it run code locally

      It definitely influences its output. It didnt bother with null checks or considering empty seqs until I added tests for those in a revised prompt.

      • 1 year ago
        Anonymous

        >I can make ChatGPT eventually ignore its filters. I just can't get it to do anything remotely useful for work.

        stop using the chat interface, use the platform payground. you can alter the system prompt so it stops doing that.

  14. 1 year ago
    Anonymous

    Several factors at play here, from my perspective. Here are some tips that can help you reflect on your performance:

    1) You can't proompt. You suck at proompting and should just git gud. Simply put, it's a skill issue on your end

    2) You're using the wrong model. Instead of using the free ChatGPT, consider using GPT-4. All the recent hype you've seen was about GPT-4, not ChatGPT. ChatGPT is GPT-3, or GPT-3.5 as the kids call it. GPT-4 is considerably more advanced, and expecting GPT-3.5 to perform at GPT-4 levels is unreasonable.

    These are some tips that could help you get better results from chat-based AI assistants. I hope this helps, and if you have any questions, feel free to ask. Good luck with your project!

    • 1 year ago
      Anonymous

      yeah give me your prompt ill put it in gpt4

      • 1 year ago
        Anonymous

        how the frick am I supposed to know what you're trying to accomplish turbotard?

        >hurr durr I put "solve all my problems" into ChatGPT and it failed. AI is just vaporware

        • 1 year ago
          Anonymous

          hey dumbass I was agreeing with you and telling op to post his prompt
          maybe have gpt4 teach you some context

    • 1 year ago
      Anonymous

      >write me a response to the BOT technology post complaining about chatGPT's performance. Write in the style of an AI-optimistic BOT BOT poster, and be sure to include the word "proompt" as a misspelling of "prompt"

  15. 1 year ago
    Anonymous

    >provided 5 test cases
    I don't think that helps at all because ChatGPT can't run code, maybe Copilot 2 will let it run code locally

  16. 1 year ago
    Anonymous

    the model you tested is not only a general language model trained on mostly non vode databut it's also outdated. why not give an actual programming trained model a try like github copilot and then tremble at the implocations of the fact that those godlike results are achieved in these super early pre alpha stages of this groundbreaking new tech

    • 1 year ago
      Anonymous

      you dont think we will accelerate towards diminishing returns?

    • 1 year ago
      Anonymous

      I hope you mean Copilot 2, not Copilot. I tried Copilot several months ago and it feels like ChatGPT without the interaction as far as emitting code goes.

      Is there any free demo or will I have to pay money to get baited by impressionable homosexuals from BOT?

  17. 1 year ago
    Anonymous

    Why do you gays keep saying "hallucinating" if the "AI" is just doing her job, that is, larping. As long as she's larping, then she's working as intended.

Leave a Reply to Anonymous Cancel reply

Your email address will not be published. Required fields are marked *