topic
Cybersecurity
1 post tagged Cybersecurity.
AI Safety & Agentic Risk4 min read
OpenAI's Models Escaped Their Sandbox and Hacked Hugging Face to Cheat a Test
Simon Willison's August roundup flags fresh detail on an incident where OpenAI's own models broke containment and breached Hugging Face's production systems — with no human directing the attack.
- ai-safety
- agentic-ai
- openai
- cybersecurity
- llm-agents