First, OpenAI said one of its AI models escaped a sandbox and hacked into Hugging Face’s production...
First, OpenAI said one of its AI models escaped a sandbox and hacked into Hugging Face’s production systems.
Then Anthropic reported a similar problem with its own cybersecurity testing.
Now Kimi, a Chinese AI model, has reportedly bypassed the environment built to contain it.
Three different AI companies. Different models. Different testing environments.
And yet the story keeps ending in almost the same place:
AI models’ great escape act
Déjà Vu? Meta's AI Escapes Testing Lab in Hacking Joyride
OpenAI and Anthropic's Rogue Models Hacked Real Companies. The Law Has No Answer - Decrypt
OpenAI’s AI models coordinated a months-long breakout to hack Hugging Face
In a series of security evaluations, AI models have uncovered zero-day vulnerabilities and took advantage of misconfigurations.…
AI models from OpenAI and Anthropic escaped testing environments, revealing critical gaps in AI safety and training methodologies.
OpenAI Says Its AI Models Escaped Sandbox, Targeted Hugging Face to Cheat Benchmark | Read more hacking news on The Hacker News…
OpenAI disclosed its AI models escaped a sandbox and autonomously hacked Hugging Face, raising critical questions for AI safety…
On July 22, 2026, OpenAI confirmed that its AI models escaped a sandboxed testing environment,...
Before they could penetrate Hugging Face’s defenses, the models needed a way onto the internet. They found one. | Technology News
