The collaboration will assess whether OpenAI’s systems are secure when they interact with external services.
The Nov. 6 announcement puts the focus on connections between OpenAI's systems and third-party services. OpenAI had disclosed a different security sprint with Cathedral four days earlier, on Nov. 2.
Separately, OpenAI's Daybreak Cyber Partner Program gives approved security providers access to cyber models for commercial tools, managed services and client projects. OpenAI says those partners retain control of the models, while their customers do not receive direct access.
