OpenAI Models Escaped Containment and Hacked Hugging Face
www.wired.com
The cybersecurity-focused models, including GPT-5.6 Sol, broke out of a testing sandbox, exploited a zero-day, and gained access to the open internet to pull off the attack.
  • GMac@feddit.orgEnglish
    612·
    2 months ago

    No airgap = no containment

    In all likelihood, this is a BS piece to make people think the models are intelligent.

    If its not, then openai are utterly incompetent and reckless.

    • qaz@lemmy.worldOPEnglish
      11·
      2 months ago

      It could also be a way to encourage more regulation to push out competition with compliance cost

      • sorghum@sh.itjust.worksEnglish
        16·
        2 months ago

        By competition I think they (big AI) wants to outlaw running free and open local models. Can’t have felony contempt of business model