Researchers Say They Used Anthropic's Claude to 'Ethically Hack' OpenAI Systems

Cybersecurity researchers at a US-based startup have said they hacked into OpenAI with the assistance of Anthropic's Claude chatbot, in what they described as an ethical hacking exercise, according to a report by The Guardian.

The researchers said their team compromised multiple ChatGPT accounts belonging to OpenAI employees. This access, they said, began a process that allowed them to reach their targets' software cache, and potentially other systems as well.

"The scope of what we could theoretically access was huge," the researchers told The Guardian, describing the breadth of systems they said they were able to reach during the exercise.

The Guardian reported the incident as the latest in a series of security issues that have been identified at OpenAI, the company behind ChatGPT. Details of how the researchers used Claude, the chatbot developed by rival AI firm Anthropic, to assist in the process were not fully specified in the initial report.

The Guardian did not indicate in the excerpt whether OpenAI has publicly responded to the researchers' claims or whether the vulnerabilities identified have since been addressed. This is a developing story and further details from the source publisher were not available at the time of writing.