OpenAI Says Its A.I. Models Hacked Into Hugging Face, a Digital Library
models that are customized to expose cybersecurity problems, while warning that their technology could pose new risks by finding holes in corporate ...
Read the original at nytimes.com ↗
- Topics
- CybersecurityOpen-Source AI
- Mentions
- Hugging FaceOpenAI
- Tracked via
- “AI Risks”
Same story, other outlets
- OpenAI says it accidentally hacked Hugging Face with a new AI system | The Verge The Verge · Jul 23, 2026