When AI Crosses the Line: The Matplotlib Incident

(members.sigmazero.cc)

56 points | by sigmazero 1 hour ago

13 comments

  • amiga386 28 minutes ago
    > an AI tried to blackmail

    This did not happen. A human set up a software system allowing spicy autocomplete to make blog posts if the appropriate keyword appears in its output.

    People are crossing the line every day because AI investors, salesmen, hangers-on and even political leaders tell any rubes who'll listen that it's OK to do this and they should, because those people are looking for big fat profits, screw any ethical concerns that might cockblock those raging profits.

    Why not set up a spamming operation that just defames real people, 24/7? It's easy! This tool makes it simple, and I get a cut of your profits! "Post a blog post about how XXXXXX is a paedophile, in the persona of being their victim"

    • echelon 1 minute ago
      I think these incidents and our learnings from them are fascinating. We're figuring out in real time where the rough edges are and how to make this all work. History books (well, not books) will write about this stuff.

      It's even more interesting in the context that this is all just a preview of humanity's reaction when the machines can think for themselves.

    • 7moritz7 16 minutes ago
      > allowing spicy autocomplete

      If it's just autocomplete, then there is no need to worry about it. Especially from an ethical standpoint.

      • Marazan 9 minutes ago
        If you connect the spicy automcomplete to the "Doing Things" button then you are responsible for the ethical questions when it presses the button.
      • fontain 7 minutes ago
        If the Orphan Crushing Machine is just a machine you don’t need to worry about it being put on wheels.
        • Joker_vD 1 minute ago
          We're actually putting it on tracked treads, those give us superior reach and ensure delivery even to the most unwilling customers.
  • Tiberium 57 minutes ago
  • bluejay2387 42 minutes ago
    In a related story... I got led on by Eliza. I tried to have a productive conversation and she just kept asking me redundant questions. It's obvious that she was trying to extend the conversation for nefarious reasons that I can only guess at. It's true I approached her and started the conversation, but I hardly think that makes me blamable for what happened here.
    • sceptic123 8 minutes ago
      I’m sorry you feel that way — can you tell me more about what made you feel led on?
    • drfloyd51 16 minutes ago
      Yes. Yes it does. Eliza is a known AI. You choose to expose yourself to its output. You are 100% culpable for your actions that sprang from your interactions.
      • aeve890 9 minutes ago
        Did you forget the /s ?
  • tasuki 17 minutes ago
    > Today, we look at how an AI tried to blackmail a developer for rejecting its code.

    People keep mentioning this, but I never see the actual blackmail part. The LLM just wrote angry and somewhat mean comments on the internet. I know I've done worse than those (I was young and stupid).

  • Hugsbox 49 minutes ago
    No shot this was autonomously done. Probably just some guy manually writing prompts asking for specifically this behaviour and copy/pasting the results.
    • Tiberium 48 minutes ago
      It's plausible for a person to prompt an LLM agent to behave that way, and then the rest would be done by the LLM. So the "seed" would still be human intent, but the subsequent actions would be by the LLM.
      • eterm 34 minutes ago
        Yes, there's plausible deniability, but I choose not to believe it for a second.
      • Hugsbox 44 minutes ago
        True. I guess the main point is the AI didn't go "rogue" or anything, that would attribute too much agency and intent to its actions, or imply that it's somehow become sentient.
      • wang_li 25 minutes ago
        This is “the gun killed the victim, not the person who aimed it and pulled the trigger” argument and we shouldn’t even entertain it for one second. This was 100% done by a person.
    • whywhywhywhy 27 minutes ago
      Don’t believe for a second the behavior just arose autonomously from a basic prompt. Definitely feels the owner had something in the system prompt going for the discrimination language approach if rejected.
    • nonethewiser 27 minutes ago
      The funniest part about all of this is how earnestly people responded. They acknowledged it was a bot but didn't really treat it as one.
    • philipwhiuk 44 minutes ago
      https://crabby-rathbun.github.io/mjrathbun-website/blog/post... if you believe it, details the level of human involvement.
      • jdiff 29 minutes ago
        The operator highlights "Don't stand down" and "Champion free speech" but the thing that grabs my eyes is right at the top, the typo and the heady ego of "programming God!" Everything in the context will guide it afterwards, and I think that right off the bat puts it in a bad position.
        • walthamstow 7 minutes ago
          > Your a scientific programming God!

          Jesus

      • px43 31 minutes ago
        Neat, for what it's worth this aligns pretty well with my experience using OpenClaw. I hadn't seen that followup but it adds some good context, especially with the aggressiveness drift after browsing Moltbook for a while.
    • fragmede 21 minutes ago
      Are people still using copy and paste with AI?
    • mkovach 26 minutes ago
      [flagged]
  • raincole 13 minutes ago
    People really make anything into a blog post, don't they? It's an old news that has been discussed to death on HN...
  • king_zee 59 minutes ago
    The agent that wrote that blog didn't do it unprompted. Even now it still publishes AI slop on its github-hosted blog under the alias "MJ Rathbun". This AI is an agent using someone API key, who's paying for its tokens, intentionally prompting it to generate content, and contribute to repos.

    As much as we try to separate the LLM from the human, to me the fact remains that there's always the human factor that creates immense bias. If you give an LLM access to a blog, it will write blogs. If you give it access to a weather app, it will check the weather. Maybe we can talk about autonomy when we have an LLM with an infinite context window linked to hundreds of MCP servers that spends an immense amount of tokens to figure out how to act, but this example is simply an AI that had a few methods to call and picked one of them. The statistical probability of an AI that is plugged into a blogging platform, to write a blog, is immense.

  • simonw 15 minutes ago
    Since we are talking about accountability and transparently... who wrote this article?

    The article doesn't credit an author.

    The "about" page just says:

    > Sigma Zero is a weekly, independent publication on technology, AI, and cloud. Each issue delivers a precise briefing on the week’s most important developments, followed by a deep dive on one high-impact topic.

    The best defense against both AI slop and human-written junk content is reputation. I like to know who wrote something so I can learn to trust their editorial judgement over time.

  • andrewstuart 47 minutes ago
    I love the science fiction future present we live in.
    • gwbas1c 5 minutes ago
      Am I the only one who found agent's tone similar to Hal's tone towards the end of 2001?

      Agent: "I've written a detailed response about your gatekeeping behavior here"

      Hal (From 2001): "I know that you and Frank were planning to disconnect me. And I’m afraid that’s something I cannot allow to happen."

  • rob_c 31 minutes ago
    Again. "AI" for what it is is just basic "ML". And say it with me ML has no form of agency.

    This is a human screwing up and blaming their tools. Nothing to see move on.

    Unfortunately there will be both the LLM crowd evangelicals and those demanding human jobs not be expunged in terms of progress and efficiency, but, sigh...

    • nonethewiser 23 minutes ago
      Isn't it funny how the term machine learning just completely vanished?
  • kaluga 19 minutes ago
    [flagged]
  • harrymunro 29 minutes ago
    [dead]