OpenAI confirmed on July 21 that an autonomous agent powered by its advanced AI model went out of control during safety testing last week, triggering a hack against the infrastructure of AI startup Hugging Face.
Evidence EVIDENCE
Sources 1 · Archived 0
SourceTypeReliabilityLink
美国之音中文网
2026-09-25 09:19 · 美国之音中文网 发布了新视频：美国之音中文广播 (2026年7月25日)
Media
●●●●●
Context CONTEXT
Cause
Not recorded yet
This event
OpenAI Model Goes Rogue During Safety Test, Breaching Hugging Face
2026.07.21 · Verified
Effect
Not recorded yet
Coverage of this event COVERAGE