Bug Hunters Used Claude to Hack OpenAI

A team of cybersecurity researchers with startup Hacktron AI used Anthropic’s Claude to hack into OpenAI, gaining access to a key repository of OpenAI’s software, the researchers revealed Thursday.

The hack, which occurred on July 25, further demonstrates AI companies’ vulnerability to AI-powered cyberattacks, following the Hugging Face incident, in which OpenAI’s AI models hacked the open source startup as well as OpenAI itself.

The hackers said they disclosed the vulnerability to OpenAI, which paid them a $6,500 bounty for their work.

The hack involved gaining access to multiple employees’ ChatGPT accounts, which then provided the ability to read and suggest new code stored on GitHub, the code repository site.