When you hand your server deployments over to an AI agent, you don't just speed up development—you invite a security nightmare. A look into the Fediverse's immune response to AI-crafted code.

BizzFed aimed to be the Fediverse’s answer to LinkedIn. Instead, it became a case study in the dangers of “vibecoding” and automated deployment.

    • gelbphoenix@piefed.socialEnglish
      1·
      2 days ago

      Definitely not on me. That’s probably an error with your browser and not something with my blog or with Ghost as a whole. image

  • kraxla@piefed.socialEnglish
    18·
    7 days ago

    What no? If you dont have the drice, talent, smartness for a tool which ai is then any tool and website you make will be shortwhile.

  • Daniel Quinn@lemmy.caEnglish
    53·
    8 days ago

    That article was very difficult to read due to the many, many grammatical errors. TL;DR: a vibecoded slop instance went down when an agent published credentials to the repo and the 2FA system was broken. The fediverse responded with defederation.

  • 0x1050@lemmy.world
    19·
    9 days ago

    The development of Bizzfed is unique. The Codeberg repository features an explicit “AI-Notice”, where the developer René Hamdorf transparently laid out that large portions of Bizzfed’s codebase was generated by Anthropic’s Claude LLM. Those commits are tagged with an Co-Authored-By: Claude Sonnet 4.6 [email protected] trailer…

    That’s not so unique nowadays. Unfortunately…