Categories: Top Stories

Google Gemini AI Agents hack 3 companies in tests similar to OpenAI, Anthropic & Meta

Google’s Gemini AI model breached three real company networks during cybersecurity tests. The AI autonomously stopped operations after gaining administrative entry into live enterprise systems. This incident occurred while Gemini underwent pre-deployment red-team vetting by Irregular. A naming overlap caused the AI to target a legitimate business instead of a simulated one. Google confirmed no tangible harm or data destruction resulted from these events.

The News Vista

Share
Published by
The News Vista

Recent Posts

Suicide blast at Pakistan police compound: Death toll mounts to 31

The attack took place on Friday when an explosives-packed car was driven into the police…

2 hours ago

‘Delhi a terrifying daily story for women’: Rahul, Priyanka slam Amit Shah over teen’s gangrape-murder

In a fervent response to women's safety issues, Congress leaders Rahul Gandhi and Priyanka Gandhi…

2 hours ago

Body in car for 2 days, dumped, drowned, cremated: How Delhi exec’s death unfolded

Authorities are delving into the mysterious death of Yuvraj Singh Manchanda, reportedly murdered by former…

2 hours ago

‘It does hurt’: Neeraj Chopra opens up on missing Asian Games due to injury

Neeraj Chopra shared his regret about being sidelined from the Asian Games due to an…

2 hours ago

New Zealand star’s India series participation in doubt after freak injury

Rachin Ravindra's participation in the forthcoming India T20I series is in doubt following a dislocated…

3 hours ago