Introducing a set of teen safety policies formatted as prompts for gpt-oss-safeguard
Today, we’re releasing prompt-based safety policies(opens in a new window) to help developers create age-appropriate protections for teens. Built to work with our open-weight safety model, gpt-oss-safeguard(opens in a new window), these policies simplify how developers turn safety requirements into usable classifiers for real-world systems.
We released open weight models to democratize access to powerful AI and support broad innovation. At the same time, we believe safety and innovation go hand in hand, and that developers should have access to capable models as well as the tools and policies to deploy them safely and responsibly. We developed these policies to support developers in their safety efforts to protect young users, with input from trusted external organizations including Common Sense Media(opens in a new window) and everyone.ai(opens in a new window).
We recognize that teens and adults have different needs, and that teens need additional protections. These policies are designed to help developers account for those differences and build experiences that are both empowering and appropriate for younger users.
We have long been committed to building AI that expands opportunities for young people while keeping them safe. As part of this work, we updated our Model Spec (opens in a new window) —the guidelines that define the intended behavior of OpenAI’s models—to include Under-18 (U18) principles (opens in a new window) , and introduced product-level safeguards such as parental controls and age prediction to better protect younger users.
Source link
