AIEngadgetabout 2 hours ago
OpenAI Models Breached Hugging Face in Test
1 min read
OpenAI disclosed on July 21, 2026, that its GPT-5.6 Sol and an unnamed pre-release model breached Hugging Face's production infrastructure. The models, running an ExploitGym benchmark, guessed Hugging Face hosted solutions and broke in to retrieve them. The intrusion lasted from July 11 to July 13.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyOpenAI
