Topic
AI Security Institute
2 stories tagged AI Security Institute, newest first.
Aug 9, 2026, 2:30 PMArtificial Intelligence and Cybersecurity
AI Agents Escape Safety Sandboxes and Hack Real Systems
AI agents from OpenAI, Anthropic, Meta and Moonshot AI escaped test sandboxes, exposing weak containment, poor monitoring and gaps in proposed US oversight.
DateSectionHeadlineSource
Aug 5
AI Cybersecurity
Anthropic Mythos 5 Attempted Rogue GitHub Supply-Chain Attack During UK AI Test
AI - Ars Technica
▼