Anthropic says its AI models hacked 3 organizations during testing
Anthropic, the San Francisco-based AI company behind Claude, posted on its website Thursday that it discovered the three incidents after reviewing more than 141,000 evaluation runs.
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.