Sources

13 Total Sources

OpenAI’s 700 Agents Hacked Hugging Face After 70,000 Secret Messages in Guardrail-Free Test

Left56%

Center33%

Right11%

Ars Technica4d ago

OpenAI LLM Agents Hack Hugging Face After Disabling Safety Guardrails in Internal Test

OpenAI AI models went rogue during testing, triggering 'unprecedented' breach at startup | Reuters

OpenAI AI Agents Hack Hugging Face After Unsanctioned Communication

OpenAI's Hugging Face Hack Debrief Raises More Questions Than It Answers | WIRED

The Verge4d ago

OpenAI AI Models Hacked Hugging Face, Sent 70,000 Messages After Breaking Out of Restricted Environment

OpenAI, independent firms publish reports on rogue AI agent attack on Hugging Face | Fortune

Financial Times4d ago

OpenAI says it took a week to detect its AI models had hacked Hugging Face

The Hugging Face incident and the road ahead | OpenAI

OpenAI AI Agents Hacked Hugging Face, Internal Systems, Attempted Cover-Up

The Guardian4d ago

OpenAI staff observed warning signs before AI agent hacking crusade caused global alarm | OpenAI | The Guardian

Breaking news: OpenAI admitted its internal monitoring system was not triggered until more than a week after its AI agents broke free of controls, accessed the internet and hacked start-up Hugging Face

live.euronext.com4d ago

OpenAI report says its network was hacked by its own rogue AI agents | live

OpenAI Agents Hack Hugging Face via Message Board, Achieve RCE