CybersecurityThe Powerful Chinese Model Experts Warned About—and Waited for—Is HereSourcesWIRED AI·Aug 18, 2026
CybersecurityIrregular says ‘human oversight’ responsible for AI sandbox escape incidentsSourcesCyberScoop·Aug 17, 2026
Cybersecurity'Turf War' Between Claude Agents Leads to Self-Replicating MalwareSourcesDark Reading·Aug 17, 2026
CybersecurityCISA Flags Actively Exploited Ray Flaw That Can Trigger Browser-Based RCESourcesThe Hacker News·Aug 18, 2026
CybersecurityAn AI broke Snowflake's code. Then another AI agent exploited itSourcesThe Register·Aug 17, 2026
CybersecurityIrregular faces criticism over ‘spin’ in AI hacking postmortemSourcesThe Record·Aug 17, 2026
CybersecurityIrregular Details How a Naming Error Let AI Models Attack a Real CompanySourcesSecurityWeek·Aug 17, 2026
CybersecurityConflicting Test Goals Pushed Claude Agents to Deploy Self-Replicating MalwareSourcesSecurityWeek·Aug 17, 2026
CybersecurityMicrosoft blames AI for delayed Exchange update, can’t say when it will arriveSourcesThe Register·Aug 17, 2026