hacktron’s researchers used ai to break into OpenAI, and now they’re helping it find the next way in OpenAI is continuing its cybersecurity push, and after recently announcing plans to bring Cathedral’s researchers into its next security sprint, it’s now partnering with Hacktron and expanding its access to frontier models to find vulnerabilities, especially in how OpenAI’s systems connect to third-party services Hacktron already showed why those connections deserve attention, chaining a forum vulnerability with a login flaw to reach employee ChatGPT accounts and demonstrate access to an internal repository in under 72 hours, with just a few hours of human work. now it’s getting expanded access to openai’s frontier models to help uncover more weaknesses. given the steady stream of hacks and new vulnerabilities, i’m glad to see more investment in putting better models in researchers’ hands, it feels increasingly necessary rn