We’re sharing the GPT-4o System Card, an end-to-end safety assessment that outlines what we’ve done to track and address safety challenges, including frontier model risks in accordance with our Preparedness Framework.
To ensure people could use this technology safely, we tested this model internally and with 100+ external red teamers across 45 languages. Our Preparedness evaluations were reviewed by our Safety Advisory Group before deploying the model.
The System Card focuses on evaluating the novel risks presented by GPT-4o's audio capabilities as well as the guardrails we implemented to prevent the generation of harmful, biased, or copyrighted content, and to ensure the model only generates audio in one of the preset voices.
We care deeply about the impact our technology has on the people who use it, and will continue to assess, calibrate, and share our learnings to ensure everyone can enjoy the benefits of AI.