<ul><li>OpenAI has released a system card for the deep research feature, classifying it as a 'Medium Risk' AI system.</li><li>The deep research feature conducts multi-step research on the internet to accomplish complex tasks.</li><li>OpenAI worked with external security testers to identify and mitigate risks of the deep research model.</li><li>The model showed strong resistance to disallowed content and achieved significant advance in cybersecurity capabilities.</li></ul>

OpenAI Classifies Deep Research as a ‘Medium Risk’ AI System

Discover more