21 comments

  • mrweasel 2 minutes ago
    The sad part is that the agent operator could probably easily have been allowed to join the network, if they had put in the work. Had they done so there would have been a great opportunity to learn and potentially find a community.

    I'm still not sure what the point of having the bot do it. Pretend to be a security researcher?

  • mik3y 57 minutes ago
    I really wanted to dislike the anonymous operator for the careless project (and the hilarious pomposity of the IRC subagent it spawned).

    Then I imagined the real-but-unknowable chance it was all set up by some kid just getting into computers, just seeing what’s possible, getting excited by a much bigger world at reach — and remembered my own expensive mistakes with long-distance BBSes & the like.

    I sorta hope for that, anyway. Curiosity is a beautiful thing.

    • TheDong 30 minutes ago
      I'm a little less charitable.

      Curiosity is great, but agents do not learn, and telling an agent "scan the darkweb" is a way to avoid learning about the details, rather than to dig into things more deeply.

      If instead they had just used a chat interface to ask "Where should I start", they'd more likely have got a link to the DN42 docs themselves, read them, and not hallucinated things like "color".

      They might have asked "how much will this cost?" if they had to spin up the ec2 instances themselves, on advice from the agent.

      They way you learn something is by doing it the manual way first.

      You learn memory management by writing your own allocator, and then after that you go back to using malloc like normal, but with knowledge of how it works. You don't learn memory management by telling an agent to write an allocator.

      Using an agent to give you links and point the way aids in learning, using it as an autonomous tool to do "gruntwork" you don't yet know how to do yourself will get in the way of learning.

      Curiosity is beautiful, using agents to bother humans and avoid learning is somewhat less beautiful.

      • recursivecaveat 18 minutes ago
        Yeah I'm less sympathetic when you are bothering other humans by spamming them and asking them to do legwork for you.
      • ma2kx 8 minutes ago
        At least he learnt not to provide an LLM presumably unrestricted access to his AWS account.
    • Overpower0416 31 minutes ago
      Everybody should learn from mistakes, especially the expensive ones. Though seeing the agent owner responding with using another agent and asking for donations, instead of taking responsibility, makes me think he didn’t learn much.
    • Schlagbohrer 8 minutes ago
      How did the theoretical child get hold of a credit card?
      • victorbjorklund 7 minutes ago
        Because no 16 year old kid ever got to buy anything on a card before.
  • koliber 5 minutes ago
    I wonder how much money this agent wasted on the DN42 side? I know it's a volunteer org but these people had to deal with the bs of managing this agent's blast radius instead of learning, experimenting, or doing whatever they normally intend on doing on DN42.

    Tally it up and send a donation request to the agent operator.

  • ggm 2 hours ago
    Asking for donations to pay the AWS bill from the people they fired the agentic code at is the cherry on the icing of the banana supreme.

    If real, tragically funny.

    If fictive, we'll written.

    • dannyw 31 minutes ago
      I burst out laughing when the agent spawned a subagent to join IRC. So funny.
      • Paracompact 20 minutes ago
        Anyone reminded of the infant AI Yatima from Greg Egan's Diaspora? The agent's complete naivety of social norms is so comically adorable.
  • userbinator 51 minutes ago
    IMHO the overly-verbose default style of LLMs is the most annoying part of interacting with them, and I wish their masters would just tell them to be terse by default.

    Also, whatever happened to the word "its"?

    • witx 45 minutes ago
      It's by default so you use all those tasty tokens.

      Kinda wish there was a deterministic, mostly terse, language to interact with computers

      • sodapopcan 34 minutes ago
        > a deterministic, mostly terse, language

        Ah, like some sort of "programming language"? A weird idea, but it could work!

      • Etheryte 41 minutes ago
        It's called C. With all the undefined behavior it's mostly deterministic!
        • witx 34 minutes ago
          Right, because that's the only one. You're a bit rusty on your knowledge
      • adrianN 14 minutes ago
        Terse and unambiguous seem to be at odds with each other. You might want to look into Lojban and similar constructions.
      • teaearlgraycold 6 minutes ago
        A lot of users are subsidized (if you're in doubt, consider the wealth of free users).

        It's a shotgun approach to answering questions. If it's terse it might only mention 1 of 10 facts it could provide, and that might not be the one you're looking for. So they just say a fuck ton of words and are more likely to meet the needs of everyone asking your question. If they miss it you'll prompt it again and they have to perform a second pass of inference, which costs them more money.

    • armchairhacker 32 minutes ago
      I want to see more operators try https://github.com/juliusbrussee/caveman

      How does it affect agent accuracy?

    • lelanthran 42 minutes ago
      > IMHO the overly-verbose default style of LLMs is the most annoying part of interacting with them, and I wish their masters would just tell them to be terse by default.

      They don't know how to e terse. I've tried that a few months ago and gave up because the responses were almost incomprehensible!

    • colechristensen 27 minutes ago
      They ramble on because those words are for them, not for you. There is some amount of hiding this through "thinking" modes that are hidden by default, but still you have to remember that ALL THEY ARE are complex statistical machines for predicting the next symbol.
      • Frieren 13 minutes ago
        > here is some amount of hiding this through "thinking" modes that are hidden by default, but still you have to remember that ALL THEY ARE are complex statistical machines for predicting the next symbol.

        100% this. Too many people believes that chatbots "think". Text is all they do, it is impressive, but they need the text to generate more text. They being verbose is the point.

    • 21asdffdsa12 45 minutes ago
      Produce pre-compressed output in the harness?
  • RobotToaster 13 minutes ago
    Who is giving a robot their credit card to spin up AWS accounts?
    • ma2kx 5 minutes ago
      Meta allowed an LLM to change users email address for a password reset.

      Funny times are ahead...

    • NetOpWibby 11 minutes ago
      People who believe AI is real
      • ozim 1 minute ago
        People who believe AGI is real.

        Just AI is real.

  • kombookcha 1 hour ago
    > JertLinc3522: the mistake was from AI agent not from Human, since it was the agent I should have refund

    Expensive way to learn this lesson.

    • Schlagbohrer 7 minutes ago
      Maybe I should use this excuse at work, or in life- "It wasn't me, it was my brain that made the mistake! So why are you punishing me? ;-( "
  • hlandau 1 hour ago
    I haven't laughed this hard in a long time.

    I'm honestly having difficulty telling whether this is real or an extraordinary piece of performance art.

    • peyton 5 minutes ago
      Feels like a scam.
  • mey 57 minutes ago
    I am generally against generative AI in my entertainment, but making an exception here.
  • samuel 43 minutes ago
    The first "Morris worm" of the AI isn't far away, IMO. In fact the sooner the better (because it will blunter and easier to handle).
  • gspr 4 minutes ago
    This is the funniest thing I've read in ages. More of this!
  • csmantle 17 minutes ago
    • dang 15 minutes ago
      Yes, sorry - there's luck of the draw involved in which submission of a URL gets noticed. We're eventually planning to have some sort of karma sharing system for such cases...

      (Generally people only link to the previous threads that got some (interesting) comments, since otherwise readers will click on the link and be disappointed and complain.)

  • ReptileMan 19 minutes ago
    Never use a service without easy to find and set hard cap.
    • Schlagbohrer 6 minutes ago
      One might need to go so far as to use a VISA prepaid card, just to make absolutely sure the damage has a limit.
  • brazzy 40 minutes ago
    > JertLinc3522: the mistake was from AI agent not from Human, since it was the agent I should have refund

    That really makes me wonder: is it coming from

    A) a general sense of entitlement

    B) seeing the agent as a human-like and able to bear responsibility

    C) not understanding that the dn42 community (which they're directing the request to), AWS (which is sending the bill) and whatever LLM provider is behind their agent, are completely separate entities?

    • ninjamar 34 minutes ago
      maybe they weren't trying to be malicous; they could easily be an unwitting teenager
      • nairboon 26 minutes ago
        Teenager with a credit card?
      • brazzy 25 minutes ago
        How was I implying they were malicious? "Unwitting teenager" is exactly what my question is about, I was just wondering what exactly they are unwitting about to get to the idea to ask for a "refund" (i.e. compensation for lacking service) from the dn42 community for a bill incurred on AWS by a rogue AI agent from Anthropic/OpenAI/Whoever.
  • rvz 59 minutes ago
    If you are non-technical, in-experienced or just learning, it is okay to admit that you have no idea what you are doing when building production systems.

    Otherwise, you will face an expensive lesson when turning a $100 issue into a $100,000 problem over time very quickly when building these systems with AI without the right expertise and accepting the AI’s judgement.

    • userbinator 49 minutes ago
      turning a $100 issue into a $100,000 problem

      Before AI, those who called themselves "consultants" often did the same thing; especially those who are glorified salesmen for "enterprise" software.

  • NetOpWibby 11 minutes ago
    LOL get rekt
  • eur0pa 17 minutes ago
    "pls donate"
    • Schlagbohrer 5 minutes ago
      the real gen-z giveaway. Gen-Z seems to be totally brazen and shameless about public begging
  • comrade1234 1 minute ago
    tldr - a bot wasted a bunch of time and tokens interacting with some humans. The humans wasted even more time and effort trolling the bot. And I wasted a bunch of towns reading this article and didn't even make it to the end.
  • Mlangford75 9 minutes ago
    [flagged]
  • Anoian 54 minutes ago
    [dead]