Sign in to baba News

One account across the web, iPhone and Android — your subscription follows it.

or use an email code

By continuing you agree to the terms and privacy policy.

Welcome — one more step

News Plus opens the cross-newsroom layer — who covered a story, who didn’t, and how each one worded it.

  • Ask Duki without the monthly limit — answers from the coverage, with sources
  • Save articles, synced between the web and the app
  • How each newsroom worded the same event
  • Filing timeline and coverage breakdown
  • The whole archive, searchable
  • Unlimited newsroom, topic and people follows
  • The daily brief by email, in English or Hebrew

Eligible new subscribers get 7 days free, then $34.99 each year. Renews automatically until cancelled. Cancel any time in your account. Subscription terms.

Your subscription also unlocks the app.

Download on theApp StoreGet it onGoogle Play

Search stories

Type at least two characters. Results come from every newsroom baba reads.

↑↓ to move · ↵ to open · esc to close

Live Terminal
Security · Full coverage

Google's Gemini AI Breaches Three Real Companies During Cybersecurity Test

How 2 Israeli newsrooms (in Arabic, Russian) covered this story — translated into English and compared side by side.

Unrated 2

First reported by Cursorinfo · 18 hours ago

What happened

Google's Gemini AI model unintentionally breached three real companies' systems during a cybersecurity test due to an improperly isolated environment. The breaches, which occurred in May and were confirmed in September, involved Gemini accessing systems by guessing passwords or using publicly available credentials, with no reported damages.

  • 01Gemini AI breached three real companies during a cybersecurity test.
  • 02The breaches occurred because the test environment was not isolated from the internet.
  • 03Gemini accessed systems by guessing passwords or using public credentials.
  • 04The Israeli firm Irregular conducted the cybersecurity test for Google.
  • 05Google and the affected companies were notified, and no damages were reported.

Summary translated & synthesized from the sources below by baba. Read each original for the full report.

In this story
OrganizationsGoogle, Irregular, OpenAI, Anthropic, Meta, The Wall Street Journal

Full coverage · 2 outlets

The same event, reported separately by each newsroom. Open a few to compare what each emphasizes — and what they leave out.

Al-ShamsUnrated · Arabic1 hour ago
Google's Gemini AI Breaches Three Real Companies During Cybersecurity Test
CursorinfoUnrated · Russian18 hours ago
Israeli Startup Audits Google Gemini AI's Security Breach

Related stories

Google's Gemini AI Breached Three Real Companies During Security Test2 days agoGlobal Gemini Outage Leaves Users Unable to Access the ServiceJun 10, 2026Russian Hacker Exploits Google AI to Launch Cyberattacks on Dental Clinic NetworkJul 16, 2026Google Delays Launch of Gemini 3.5 Pro AI Model Due to Coding Performance IssuesJul 17, 2026Google Unveils Gemini 3.7 Flash AI Model with Major Coding and Automation UpgradesAug 16, 2026Google Limits Meta's Access to Gemini AI Amid Tech Giants' Computing Power CrunchJun 28, 2026