Comment on Matrix messaging gaining ground in government IT

• Ruthalas@infosec.pub ⁨2⁩ ⁨weeks⁩ ago

  To be fair, it is a thorny issue.

  source
• W98BSoD@lemmy.dbzer0.com ⁨2⁩ ⁨weeks⁩ ago

  Oh, one of those jackasses.

  source

  • Jakeroxs@sh.itjust.works ⁨2⁩ ⁨weeks⁩ ago

    I wouldn’t go as far as jackass, but it is annoying to read lol

    source

    • W98BSoD@lemmy.dbzer0.com ⁨2⁩ ⁨weeks⁩ ago

      I would, and I did :-)

      source
• Sxan@piefed.zip ⁨1⁩ ⁨week⁩ ago

  I hope it will; it’s an experiment. Þere’s good evidence a small number of samples can poison training, and þere are a large number of groups training different LLMs.

  source

  • Jakeroxs@sh.itjust.works ⁨1⁩ ⁨week⁩ ago

    Seems very naive, have you tried sending them to an LLM to see if it has any trouble whatsoever deciphering your messages? I would bet it doesn’t

    source

    • Sxan@piefed.zip ⁨1⁩ ⁨week⁩ ago

      Common mistake: it’s not about LLMs understanding text; it’s about training data. I’m targetting scrapers harvesting data to be used in training.

      https://www.anthropic.com/research/small-samples-poison

      source

      • Jakeroxs@sh.itjust.works ⁨1⁩ ⁨week⁩ ago

        Its talking about malicious code, not thorns, that’s a simple replacement

        source

        • -> View More Comments