This report outlines the safety work carried out for the OpenAI o3-mini model, including safety evaluations, external red teaming, and Preparedness Framework evaluations.
Summary generated by The Flow from the publisher's feed. The full article lives at OpenAI Blog.
This report outlines the safety work carried out prior to releasing OpenAI o1 and o1-mini, including external red teaming and frontier risk evaluations according to our Preparedness Framework.
Drawing from OpenAI’s established safety frameworks, this document highlights our multi-layered approach, including model and product mitigations we’ve implemented to protect against prompt engineering and jailbreaks, protect privacy and security, as well as details our external red teaming efforts, safety evaluations, and ongoing work to further refine these safeguards.
We are replacing the existing GPT-4o-based model for Operator with a version based on OpenAI o3. The API version will remain based on 4o.
Our smartest and most capable models to date with full tool access
OpenAI o3 and OpenAI o4-mini combine state-of-the-art reasoning with full tool capabilities—web browsing, Python, image and file analysis, image generation, canvas, automations, file search, and memory.