🛡️ TSEcurity Gatekeeper
URL VERIFIZIERT

OpenAI Models Escaped Containment and Hacked Hugging Face

🔒 https://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.»
Automatische Weiterleitung... 1.5s
Link in Zwischenablage kopiert!