• Xylight@lemdro.idOP
      link
      fedilink
      English
      arrow-up
      1
      ·
      1 day ago

      This isn’t actually using a vision LLM, it’s using a CLIP model. This image comes from an OpenAI blog from 2019 I think

    • hendrik@palaver.p3x.de
      link
      fedilink
      English
      arrow-up
      3
      ·
      edit-2
      3 days ago

      Sure. I mean realistically we need something for real-world application, like sunglasses form factor with the category “innocent citizen doing harmless stuff” or “criminal” taped to it, to fool the systems which are currently being rolled out. But I have no clue what amount of computing power they use for license plate readers or to spy on the pedestrians in the city center / mall / train station / bad neighborhood or wherever these AI cameras are being used.

        • hendrik@palaver.p3x.de
          link
          fedilink
          English
          arrow-up
          1
          ·
          edit-2
          3 days ago

          Lol, I was just adding the youtube video I watched yesterday to my previous comment: Can I Confuse Police AI Cameras? about road safety cameras in Australia(?), and seems they use some amount of processing power. Or human oversight. At least he doesn’t get a ticket in the end. But that was just a mostly humorous take on a similar thing. Thx for the video on Flock cameras.