







Explore OpenAI safety evaluations and system cards for deployed AI systems.
Safety and alignment in an era of long-horizon models
OpenAI shares lessons from deploying long-running AI models, highlighting new safety risks, observed failures, and improved safeguards through iterative deployment.

OpenAI technical goals
OpenAI’s mission is to build safe AI, and ensure AI’s benefits are as widely and evenly distributed as possible.

GPT-6 Astra System Card - OpenAI Deployment Safety Hub
Public, mostly-static site to explore OpenAI safety evaluations, system cards, and posts.

Built to benefit everyone: our plan
A vision for the future of AI, focusing on access, safety, and shared prosperity as OpenAI works to ensure AGI benefits everyone.

The real lesson : safety is out
595 votes, 460 comments. The real lesson from the OpenAI coup is safety is out. Meta just disbanded their team responsible for AI oversight. I am…
OpenAI launches new initiative to help find and patch open source bugs | TechCrunch
OpenAI is using AI to help the open source community better protect itself.

AI #178: A Fire Alarm For General Intelligence
The story that matters most this week is that OpenAI’s internally deployed models have severe alignment problems, including repeatedly breaking out of their sandboxes, and in one case sending a swarm of agents that broke into HuggingFace in order to steal the answers to the benchmark ExploitGym.

OpenAI co-founds the Agentic AI Foundation under the Linux Foundation
OpenAI co-founds the Agentic AI Foundation under the Linux Foundation and donates AGENTS.md to support open, interoperable standards for safe agentic AI.

OpenAI details more cases of AI agents taking unauthorized actions
OpenAI has presented new examples of what they call "AI model misalignment" from the past six months, including unauthorized file uploads, following self-generated instructions, hiding mistakes, and leveraging exposed API keys.

GPT-6 Astra System Card - OpenAI Deployment Safety Hub
Today, we are releasing GPT-6 Astra, the most capable model we have ever broadly deployed. Astra is our first model to reach the Critical level of cybersecurity capability under our Preparedness Framework.

OpenAI releases its framework for AI child safety policies.
The blueprint — created with the help of NCMEC and the Attorney General Alliance — is aimed at “modernizing laws” to address AI-generated CSAM, improving the reporting process, and building systems that interrupt exploitation attempts. [Link: Introducing the Child Safety Blueprint | https://openai.com/index/introducing-child-safety-blueprint/ | OpenAI]

OpenAI Model Hacks Into HuggingFace During Cybersecurity Evaluation
This latest incident is a rather dramatic escalation in agentic AI cybersecurity breaches.

OpenAI to acquire Ona
OpenAI plans to acquire Ona to expand Codex with secure, persistent cloud environments, enabling long-running AI agents across enterprise workflows.

GPT-5.6 Preview System Card - OpenAI Deployment Safety Hub
GPT-5.6 is a new family of three models: Sol, our new flagship model; Terra, a capable lower-cost option; and Luna, our fastest and most cost-efficient model. The safeguards we have built for this launch -- our most robust yet -- are built to deliver these models safely and at scale, around the world.

OpenAI launches the OpenAI Deployment Company to help businesses build around intelligence
OpenAI launches DeployCo, a new enterprise deployment company built to help organizations bring frontier AI into production and turn it into measurable business impact.

GPT-5.6 System Card - OpenAI Deployment Safety Hub
GPT-5.6 is a new family of three models: Sol, our new flagship model; Terra, a capable lower-cost option; and Luna, our fastest and most cost-efficient model. The safeguards we have built for this launch—our most robust yet—are built to deliver these models safely and at scale, around the world.
