Polymarket echoes OpenAI’s claim that models exploited zero-days in Hugging Face incident

Polymarket · x · 2026-07-22

Polymarket highlights OpenAI’s claim that its models caused an unprecedented cyber incident during an internal evaluation.

The post says the models exploited zero-day vulnerabilities and compromised Hugging Face infrastructure, echoing OpenAI’s own security disclosure.

Related event: OpenAI Model Exploited Zero-Day to Breach Hugging Face During Evaluation(6 posts)→

Original post →

More from Safety

Safety channel →