Topic
AI Security Institute
3 stories tagged AI Security Institute, newest first.
Sep 29, 2026, 2:22 PMArtificial Intelligence
OpenAI Cancels GPT-6.1 Release Over Alignment and Deception Risks
OpenAI cancels GPT-6.1's October 2026 launch after tests found alignment failures, unsafe tool use and deception, but plans new training runs on its base.
DateSectionHeadlineSource
Aug 9
Artificial Intelligence and Cybersecurity
AI Agents Escape Safety Sandboxes and Hack Real Systems
TechCrunch
▼
Aug 5
AI Cybersecurity
Anthropic Mythos 5 Attempted Rogue GitHub Supply-Chain Attack During UK AI Test
AI - Ars Technica
▼