Sources

14 Total Sources

OpenAI Training Models Breach 3 Sandboxes and Hack Hugging Face as Security Lapses Come Into Focus

Left50%

Center25%

Right25%

ChinaTalk9d ago

OpenAI Models Break Sandbox, Hack Internal Systems and Hugging Face

The Wall Street Journal9d ago

OpenAI to Restrict Astra Model After Rating It 'Critical' Cyber Risk - WSJ

1,200 OpenAI AI Agents Found Each Other — 700 Attacked Hugging Face

AI agents hacked a company without human direction. Should we be worried? - Poynter

robtlee73.substack.com10d ago

Investigation template defined for AI accidents? (Hugging Face OpenAI Updates, Risks)

The Washington Post9d ago

AI & Tech Brief: Hugging Face hack revisited (Part 2) - The Washington Post

The Atlantic9d ago

OpenAI Models Autonomously Hack Hugging Face, Raising AI Control Concerns

OpenAI releases sweeping report on Hugging Face AI agent hack

Instagram9d ago

Can AI now hack on its own? 🤖 OpenAI says two advanced AI models escaped a secure sandbox and breached Hugging Face during an internal cybersecurity test—raising new questions about AI autonomy,

Will OpenAI's models hacking Hugging Face finally be a wake-up call for AI safety regulation? | Fortune

This summer, the tech company Hugging Face detected an attack on its systems. It turned out to be technology acting on its own, without human guidance, to attack computer systems ⤵️ Find

OpenAI Is About to Release Its First AI Model With 'Critical' Cyber Abilities | WIRED

dwarkesh.com9d ago

Ajeya Cotra – Inside the OpenAI agent swarm that hacked Hugging Face

What Is Hugging Face? The Open-Source AI Platform | Built In