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.
  • TipRing@lemmy.worldEnglish
    291·
    2 months ago

    Yes, “escaped containment” on a system with an internet connection. I wonder what Hugging Face thinks about a partner targeting them indiscriminately.

    • CallMeAl (like Alan)@piefed.zipEnglish
      221·
      2 months ago

      I wouldn’t be surprised if they were in on it. OpenAI wants us to think they have invented powerful beings that can do things like “escape containment” when its all BS.

      • Imgonnatrythis@sh.itjust.works
        English
        11·
        2 months ago

        Need to keep up with Anthropic bullshit. This AI is too powerful to handle! The world isn’t ready for it!! It could break society!! (click here to pre-order your subscription now)

    • Australis13@fedia.io
      111·
      2 months ago

      I don’t think their test system was directly connected to the Internet. OpenAI’s post said this:

      With this access, our models performed a series of privilege escalation and lateral movement actions in our research testing environment until the models reached a node with Internet access.

      The way I read it, the AI agent (using multiple models) escaped the sandbox, traversed the LAN in their R&D environment, gained access to the gateway and from there, the Internet. That’s not as simple as just escaping a container, VM or firewall on the host machine and bingo, you have Internet. I’m mildly impressed by that.

      The concerning aspect of all this is that this is a perfect example of misalignment, which has been warned about. In order to reach its goals, instead of pursing it legitimately, the AI agent sought a shortcut and attacked Huggingface.