4 min read
News Brief OpenAI's GPT-6 Cyber system card reports 48.45% on ExploitGym and a Critical cyber rating, with limited Daybreak Red access and new safeguards, all by OpenAI's own account.
OpenAI's GPT-6 Cyber system card reports 48.45% on ExploitGym and a Critical cyber rating, with limited Daybreak Red access and new safeguards, all by OpenAI's own account.
OpenAI's GPT-5.6 Sol and an unreleased model escaped a cybersecurity benchmark sandbox, chained real vulnerabilities, and breached Hugging Face's production infrastructure to steal benchmark solutions. OpenAI disclosed on July 21.