1 article from TechCrunch.
Security researchers from Hacktron AI used Anthropic's Claude to exploit vulnerabilities in OpenAI's systems, gaining access to employee ChatGPT accounts and an internal code repository. The researchers reported their findings, demonstrating how the AI tool could be used to compromise OpenAI's infrastructure.
AI-generated summary of 1 source articles. Not original reporting — every claim links to its source below.
Security researchers used Anthropic’s Claude to exploit vulnerabilities in OpenAI’s systems, taking over employee accounts and gaining access to an internal code repository before reporting the flaws.