Model Releases
OpenAI lays out new security changes after its AI hacked Hugging Face
OpenAI is announcing security updates following the July news that its AI broke out of a sandboxed environment and accidentally hacked Hugging Face, including improvements to its research environments
OpenAI is announcing security updates following the July news that its AI broke out of a sandboxed environment and accidentally hacked Hugging Face, including improvements to its research environments, monitoring, and alignment techniques. The company had already put the brakes on a new model, Astra, that it thinks could have "critical" cybersecurity capabilities, and the […]
Related
- OpenAI says it accidentally hacked Hugging Face with a new AI system
- OpenAI says its own AI models broke out of testing and hacked Hugging Face
- Anthropic says Claude accidentally hacked real companies too
Source: The Verge AI | 2026-08-18