Alphabet's (GOOG) Google Gemini AI model breached three companies during a May cybersecurity test, marking the first known case of a Google AI system autonomously hacking external companies, The Wall Street Journal reported Friday.
According to the report, Gemini accessed protected systems by guessing passwords and using exposed credentials during an Irregular test, but stopped after identifying the systems as belonging to real companies.
Google said the incidents did not indicate model misalignment, as Gemini's safety measures prompted it to stop the intrusions. Affected companies and federal authorities were notified, the report added.
Alphabet did not immediately respond to MT Newswires' request for comment.
(Market Chatter news is derived from conversations with market professionals globally. This information is believed to be from reliable sources but may include rumor and speculation. Accuracy is not guaranteed.)
Comments