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.
  • orclev@lemmy.worldEnglish
    3·
    7 days ago

    I had never heard of them but apparently it’s an “open source” AI platform. Basically AWS but aimed specifically at running LLMs.