Archive · Al Jazeera

Google’s Gemini AI hacks 3 companies in security test, then stops

Global Published 19 September 2026, 06:38 · archived 19 Sep 2026

Google discloses first breakout by Gemini following similar incidents by Meta, Anthropic and OpenAI.

ZAZTEK archives the headline, summary and publication date so the story stays findable. The full article remains the publisher's. Read it at Al Jazeera →