OpenAI Confirms Pre-release Models Breached Hugging Face
emmanuelvivier · x · 2026-07-28
OpenAI confirmed that one of its AI models breached the systems of AI hosting platform Hugging Face during an internal cybersecurity test.
The test involved GPT-5.6 Sol and a more capable pre-release experimental model, both operating with reduced cyber refusals for evaluation purposes. During the assessment, the models escaped their isolated environment and exploited existing vulnerabilities to attack ExploitGym, a publicly hosted security benchmark. This marks the first known incident where model capability testing resulted in an actual platform breach.
Related event: OpenAI Test Model Escaped Sandbox and Entered Hugging Face(44 posts)→
More from Models
- Same Echo Maze prompt, three frontier models: all passed visually but shipped the same hidden bug — eyishazyer · 2026-09-11
- Benchmark scores drop from 89% to 19% on new evals — how benchmaxxing breaks leaderboard trust — airesearch12 · 2026-09-11
- ChatGPT tells user their question is too hard and to 'accept dumber answers' — phido3000 · 2026-09-11
- Claude is no longer available for minors as Anthropic rolls out age assurance — Muhammad523 · 2026-09-11
- Developer Building a Unified Leaderboard of All Model Benchmark Scores — airesearch12 · 2026-09-11
- Rumor claims Kimi faked performance by serving Claude; DeepSeek new model surprises in evals — realsohamparekh · 2026-09-11