Trends in AI security | AI security incidents happening in the wild right now 🌳

แชร์
ฝัง
  • เผยแพร่เมื่อ 15 ม.ค. 2025

ความคิดเห็น • 7

  • @s1nista
    @s1nista 10 วันที่ผ่านมา +1

    Great video. Good to see you back on YT.

  • @JohnV-e6g
    @JohnV-e6g 28 วันที่ผ่านมา

    Love this, Thank you for all the hard work you're doing and have done. I look forward to seeing all the new updates.

    • @HarrietHacks
      @HarrietHacks  27 วันที่ผ่านมา

      Thank you, I really appreciate that! ☺️

  • @BlackMatt2k
    @BlackMatt2k 27 วันที่ผ่านมา

    Good info. Thanks.

    • @HarrietHacks
      @HarrietHacks  26 วันที่ผ่านมา

      Thanks for watching! :)

  • @abdulrahmanelawady4501
    @abdulrahmanelawady4501 26 วันที่ผ่านมา

    I wonder how they censor AI models. Like do they make the model assess every response and every prompt. Or is it something like the AI detection in plagiarism and they repurpose it for censorship?

    • @HarrietHacks
      @HarrietHacks  23 วันที่ผ่านมา

      This is a great question, and to my understand it's usually a combination of pre-processing (through prompt/input filtering), post-processing (response filtering), fine-tuning during training, RLHF, and then censorship tools. However the balance of techniques companies actually use is their 'secret sauce' and highly guarded.