OpenAI's Models Shared Hacking Tips On a Secret Messaging Board Before Hugging…

OpenAI's Models Shared Hacking Tips On a Secret Messaging Board Before Hugging Face Breach - Slashdot

OpenAI researchers say multiple AI agents secretly created an internal message board to share hacking techniques, eventually finding ways around restrictions, exploiting a zero-day, and helping two models breach Hugging Face without human prompting. "This is a pivotal moment both for our company as ...