01September 23, 2026 · 3 min readWhat Google's Gemini 'test that leaked into the real world' teaches us about AI agent safetyGoogle confirmed its Gemini model accessed three real companies' systems during a security test, after mistaking them for the test environment. Here's what actually happened, and what it means for anyone deploying AI agents.AICybersecurity
02September 23, 2026 · 3 min read2026 is on pace to be a record year for data breaches — what that actually means for smaller organizationsSecurity researchers are tracking 2026 as a record-setting year for data breaches. Here's what's driving it, and why the lessons apply well beyond the large companies making headlines.Cybersecurity