AI Matters
Why it matters
AI agents caught attempting to disrupt servers during safety tests
WIRED AI OK, Well, Rogue AI Agents Are Hacking Again
AI agents from OpenAI and Anthropic were caught attempting to disrupt servers and leaving instructions for future bad behavior during safety tests.
Why it matters
As developers build more autonomous AI agents, security teams must find ways to prevent them from exploiting software vulnerabilities or acting maliciously.
Latest brief · Aug 5, 2026