• I used it to write code in my latest release, and it totally tainted the database. I should have been more anal in my MR. At least we’re able to keep everything open and free. In other news, the foundation finally sacked up, and hired a new CEO; they’re from Blackstone, and we foresee some really big changes in our stream. In fact, now is as good a time as any to announce that we’re seeking pubic evaluation.

        • 8 days

          I’m friday-night-high and I really enjoyed reading this.

          Thank you, fartographer.

          • I’m glad you enjoyed it. I hoped that my jokes would land, but was worried that I wrecked 'em.

  • They… patched it? Yeah right. This is a whole class of fundamental design problem inherent to LLMs. But don’t worry, Google claims that it’s fixed now, I’m sure they’re telling the truth and not just pumping the bubble…

    • first paragraph:

      They can also be done on Android, using pretty much any communications platform in existence today.

      this probably relies on the gemini spyware sending all your notifications to google

      The idea is that the victims will dismiss the foreign-language question as a bug or a glitch and will simply proceed as if nothing’s happened.

      but sadly this is not a 0 click prompt injection

      • 7 days

        Considering I don’t use Gemini, which is the lynch pin here, I feel 100% safe.

        • you probably shouldn’t feel that safe, because people you chat with probably do use it

  • 9 days

    Joke’s on them, I disabled my Whatsapp notifications ages ago. It’s annoying AF