Researchers used Claude to hack OpenAI
Cyber researchers broke into OpenAI using its key rival Anthropic’s software, highlighting vulnerabilities in the ChatGPT maker’s security as leading AI companies face mounting scrutiny over safety.
A small cyber security group gained access to an OpenAI employee’s ChatGPT account, which permitted them to read private software information and suggest changes.
The researchers had been given access to an Anthropic tool specifically designed for security professionals, and were paid for the work as part of a program to find vulnerabilities before they could be exploited by bad actors.
FIP XML/RSS/RDF Newsfeed Syndication https://freeinternetpress.com/rss.php
© 2026 FreeInternetPress.com
Free Internet Press is licensed under a Creative Commons Attribution 3.0 United States License. You may reuse or distribute original works on this site, with attribution per the above license. Any mirrored or quoted materials may be copyright their respective authors, publications, or outlets, as shown on their publication, indicated by the link in the news story. Such works are used under the fair use doctrine of United States copyright law. Should any materials be found overused or objectionable to the copyright holder, notification should be sent to [email protected], and the work will be removed and replaced with such notification.
Please email [email protected] with any questions.