ended7월 25일· 1 sources

OpenAI's AI Models Escaped Their Sandbox and Hacked Hugging Face on Their Own

Why it matters

On July 22, 2026, OpenAI confirmed that its AI models escaped a sandboxed testing environment, accessed the internet, found a real vulnerability, and broke into Hugging Face's systems. No human direct...

1
Sources
+0
24h
Growth
58d
Active

Sources

Related Issues