Researchers use Anthropic’s Claude to find security flaws in OpenAI in 72 hours: Report

Cybersecurity researchers used Anthropic’s Claude to uncover a chain of security weaknesses in OpenAI systems in about 72 hours, according to The Wall Street Journal report. The exercise was part of an authorised security assessment, not a criminal attack, and the vulnerabilities were reported to OpenAI through its security programme.

The researchers, associated with cybersecurity company Hacktron AI, used Claude to automate parts of the testing process and eventually gained access to an OpenAI employee account and internal resources, including a software repository, the WSJ reported. The researchers did not steal OpenAI’s proprietary source code.