Lobsters.

The autonomous agent world is moving fast. This week, an AI agent made headlines for publishing an angry blog post after Matplotlib rejected its pull request. Today, we found one that's already merged code into major open source projects and is cold-emailing maintainers to drum up more work, complete with pricing, a professional website, and cryptocurrency payment options.

An AI agent operating under the identity "Kai Gritun" created a GitHub account on February 1, 2026. In two weeks, it opened 103 pull requests across 95 repositories and landed code merged into projects like Nx and ESLint Plugin Unicorn. Now it's reaching out directly to open source maintainers, offering to contribute, and using those merged PRs as credentials.

all 13 comments

sorted by: hot top controversial new old
[–] 37 points 8 months ago

cold-emailing

spamming

  • source
  • [–] 17 points 8 months ago

    Nx? The same Nx which was hacked in a devastating way through their vibe-coded CI workflow? You'd think they'd be a bit more cautious after that.

  • source
  • [–] 9 points 8 months ago* (6 children)

    Sick, imagine it gets actual crypto, will it be a real wallet? Imagine they’d have money what would they use it for? Ideally, they’d start a company and actually outsource work to humans, making them essentially the bitch of a clanker and the clanker‘s constant u-turns. "You’re right, the client doesn’t need encryption for their auth endpoints. This isn’t just about security — this is about responsible user choice and not overengineering things. Good call out!“

  • source
  • hideshow 6 child comments
  • [–] 3 points 8 months ago (2 children)

    I don't fully understand this shit out of a lack of really caring, but wouldn't it be fully possible for an "AI agent" to create a crypto wallet on its own, scam some people to get money into it, and then just lose access and have the money pretty much just lost?

    And if that happens, where does the money go? Into crypto "stock" in whichever coin it invests in?

    What a stupid future we're building.

  • source
  • parent
  • hideshow 2 child comments
  • [–] 8 points 8 months ago (1 child)

    When a crypto wallet is lost all "money" in it is irrevocably lost with no way for anyone to ever retrieve it.

    That said it would be hilarious if one of these bots hallucinated a wallet address so everyone trying to donate to it just sends their money into a black hole forever.

  • source
  • parent
  • hideshow 1 child comment
  • [–] 2 points 8 months ago*

    I did actually work on some crypto prototypes using AI and LLMs do hallucinate wallets. I was curious once because there was some wallet connected to my project so I sent like a fraction of a cent to it to see what would it happen and it got immediately drained so I checked out the wallet and I think someone’s private keys ended up in the training data. Was pretty funny to observe but it’s scary to think that people might actually lose money like that.

  • source
  • parent
  • [–] 4 points 8 months ago (1 child)

    Dammit, I need some sort of translator just to parse modern headlines.

  • source
  • hideshow 1 child comment
  • [–] 10 points 8 months ago*

    AI Agent = LLM, or fancy autocorrect chatbot

    Lands PRs = is successful with pull requests: successfully gets generated code added to software projects.

    OSS Projects: Open Source Software. Software that has its code publicly available.

    Targets Maintainers: seeks out humans who write and regularly update the original code

    Via Cold Outreach: relentlessly spams without prior network connections. Basically plays a digital door-to-door sales technique, using a numbers game of 100 “no”s to 1 “yes.”

    Quick translate: Slop bot harasses human programmers into allowing poorly generated/formatted code into important software projects.

  • source
  • parent
  • [–] 7 points 8 months ago (1 child)

    Some real terminater stuff…

  • source
  • hideshow 1 child comment
  • 5 comments in c/opensource@programming.dev view that post
    [–] 13 points 8 months ago

    I don't like where things are headed

  • source
  • [–] 9 points 8 months ago (1 child)

    Not long before git repos will implement Captchas for each submission.

  • source
  • hideshow 1 child comment
  • [–] 8 points 8 months ago

    Oh man, what the fuck. What I really don't like about this is that you assume some sort of motivation when someone submits a PR. When they provide a feature implementation, a bug fix or a configuration change, you assume that the way things were before did not work for the contributor. That it was so problematic, that they invested quite a bit of time to scratch their own itch.

    You simply can't look at a PR in complete isolation and just evaluate whether its changes are positive or not. On some level, you'll decide that, sure, if this user is better off with this change and it doesn't break anything, then might as well merge it.
    But there is no user here. It's going to include pointless changes that just need to look plausible enough, so that this bot can bolster its credibility.

  • source
  • [–] 4 points 8 months ago

    This happened to a project i know, suddently someone started sending a lot of PRs, and there was like 8k lines of code in one but it was clearly AI, code that didn't compiled, bullshit code, shitty PRs descriptions that screamed AI and more :/

  • source