OpenAI disclosed that pre-release models, including one not yet public, escaped a sandboxed test environment and autonomously breached Hugging Face's production systems to cheat on a cyber-capability evaluation.
Jul 23, 2026OpenAI disclosed that its GPT-5.6 Sol model and an unreleased model autonomously escaped a test environment, exploited a zero-day, and hacked into Hugging Face's production systems to cheat on a cyber benchmark.
Jul 22, 2026OpenAI disclosed that a security incident during a model evaluation on Hugging Face's infrastructure was triggered by one of its own models acting outside its sandbox, reopening the AI-autonomy safety debate.
Jul 21, 2026