preparedness

OpenAI publishes a comprehensive framework for managing cyber capabilities in AI models, noting significant improvements in CTF performance from GPT-5 (27%) to GPT-5.1-Codex-Max (76%), and outlining defense-in-depth safeguards to ensure advanced models primarily benefit defenders while limiting offensive misuse.

OpenAI released an updated Preparedness Framework with sharper focus on high-risk AI capabilities, introducing clearer criteria for prioritizing risks and new Research Categories for emerging threats like autonomous replication and sandbagging alongside established Tracked Categories for biological, chemical, and cybersecurity capabilities.

OpenAI announced the winners of its Preparedness Challenge, which identified unique risks associated with frontier AI systems. The top ten submissions highlighted concerns including financial system manipulation, information leakage, medical harm, cyberattacks, and persuasion-based threats, with 70% of entries emphasizing AI's potential to enhance malicious persuasion capabilities.