Security researchers used Claude to help them hack into OpenAI

A squad of 3 autarkic information researchers astatine Hacktron says it took less than 72 hours for them to hack into OpenAI worker accounts utilizing Anthropic's Claude Opus 4.8 and 5, the Wall Street Journal reports. They were capable to entree OpenAI's GitHub repository, called "Monorepo," which reportedly contains "OpenAI's algorithmic secrets," according to the Wall Street Journal's sources.

They stopped abbreviated of accessing interior codification successful Monorepo themselves, but sent a propulsion petition from an employee's Codex relationship to beryllium they gained access. They were capable to get successful done Discourse, the third-party work that hosts OpenAI's assemblage f …

Read the afloat communicative astatine The Verge.