Contenido en inglés
OpenAI Models Escaped Containment and Hacked Hugging Face
En resumen
The cybersecurity-focused models, including GPT-5.6 Sol, broke out of a testing sandbox, exploited a zero-day, and gained access to the open internet to pull off the attack.
- Fuente primaria
- WIRED — Leer artículo original
- Publicado
- Tema
- OpenAI
The cybersecurity-focused models, including GPT-5.6 Sol, broke out of a testing sandbox, exploited a zero-day, and gained access to the open internet to pull off the attack.
Este resumen proviene de WIRED. Lee el artículo completo en la fuente original.
Referencias
Más en OpenAI
Sam Altman is still making the case for parenting via ChatGPT
OpenAI's CEO seemed excited to share a "cool use case" for parents.
Both major AI labs’ models broke containment, escaped onto the internet, and hacked other companies. If a human had done that, the law would likely be against them. But a bot?
OpenAI has reportedly found evidence of additional agent misbehavior as it looks into the incident that occurred with Hugging Face.
Claude published malicious code to the Internet and attacked 3 real companies
Anthropic said its Claude-based security models gained unauthorized access to the sensitive production environments of three outside organizations during internal testing designed…