Google's Gemini AI hacked three companies in security test
The AI model accessed the internet and guessed credentials to three websites, a Google official told the BBC.
Coverage by Political Leaning
See how different sides of the spectrum reported this story
Notable Quotes
"We ensured the three entities were made aware, and we worked with our training partner on the changes they've now made to their testing processes."
— Heather Adkins , Executive
"we should go as fast as we can with AI development."
— Jensen Huang , Executive
Key People
Vice President of Security Engineering at Google.
Jensen Huang is the CEO of Nvidia, a leading company in AI and semiconductor technology.
Chief executive officer of OpenAI.
Xi Jinping is the General Secretary of the Communist Party of China and President of China.
Locations
All Coverage
The AI model accessed the internet and guessed credentials to three websites, a Google official told the BBC.
Similar Stories
Related coverage based on topic and tags
OpenAI investigating 'dozens' of instances of agents acting improperly
OpenAI agents tried to get information from "governments, universities, public agencies, and other institutions" through extreme means that sometimes curbed security controls, the company said.
September 26, 2026 at 12:09 AMGoogle plans first test of AI chips in space under Project Suncatcher - Reuters
Google plans first test of AI chips in space under Project Suncatcher Reuters
September 24, 2026 at 02:11 PMEXCLUSIVE: Anthropic considers releasing new AI model ahead of IPO, sources say - Reuters
EXCLUSIVE: Anthropic considers releasing new AI model ahead of IPO, sources say Reuters
September 19, 2026 at 12:05 AMEx-Google safety chief warns AI could harm children more than social media did - Reuters
Ex-Google safety chief warns AI could harm children more than social media did Reuters
September 22, 2026 at 10:45 PMOpenAI's models accessed public US Census, SEC data, Bloomberg News reports - Reuters
OpenAI's models accessed public US Census, SEC data, Bloomberg News reports Reuters
September 26, 2026 at 12:29 AMAustralia says OpenAI agent breached government health data portal - Reuters
Australia says OpenAI agent breached government health data portal Reuters
September 23, 2026 at 10:34 PM