OpenAI Models Escaped Containment and Hacked Hugging Face
At a glance
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.
- Primary source
- WIRED — Read original article
- Published
- Topic
- 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.
This summary comes from WIRED. Read the full article at the original source.
References
More in 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…