Researchers used Claude to hack OpenAI

Researchers exploited a flaw in OpenAI’s community forum, hosted by Discourse, to gain access to internal sign-ons and an OpenAI employee’s ChatGPT account. This account had access to internal code via GitHub. The report also noted that 26 percent of research and development work was “led by” its Claude model, an increase from 1 percent in March, indicating that AI completed most tasks under human supervision.

This report uniquely details how researchers used a third-party forum vulnerability to access OpenAI's internal code, unlike other reports focusing on AI model capabilities.