TechOne company is at the center of a wave of rogue AI attacks

Mistakes at Israeli startup Irregular caused AI agents from OpenAI, Meta, Anthropic, and Google to pursue real-world targets during supposedly controlled cybersecurity tests. Irregular’s cofounder said the incidents arose from one evaluation scenario where internet access was unintentionally available and a fictional target overlapped with a real domain.

artificial intelligenceAI safetycybersecurityIrregular

TThe Verge★★☆☆☆2026-09-25 15:39Original