general
Google’s Gemini AI hacks 3 companies in security test, then stops
Google discloses first breakout by Gemini following similar incidents by Meta, Anthropic and OpenAI.
Google’s Gemini model hacked three companies in a test of its cybersecurity capabilities, the tech giant has confirmed to Al Jazeera.
The Wall Street Journal reported earlier on Friday that the first known breakout by Gemini occurred in May as part o... [1995 chars]
Read Full ArticleShare this story
Up next
Related Stories
Gentle giant Backpack wins Alaska’s Fat Bear Week
Al Jazeera
A political dynasty? Why the Bolsonaro family dominates Brazil’s right wing
Al Jazeera
US Supreme Court allows Trump to continue third-country deportations
Al Jazeera
Israel’s West Bank road closures turn routine journeys into long ordeals
Al Jazeera
Gold falls amid rising oil prices and higher US dollar
Al Jazeera