Browsing Tag
AI Sandboxes
2 posts
Sandboxing, containment, monitoring, and isolation controls for AI agents, cyber evaluations, and high-risk model testing.
Microsoft Execution Containers Put AI Agents Behind OS-Enforced Boundaries
Microsoft Execution Containers are now generally available, with file, network, UI and session controls for AI agents. Here is how MXC works and what IT teams should test.
Anthropic’s Claude Incidents Turn AI Sandboxes Into a Training Priority
Anthropic paused parts of its cyber-evaluation and reinforcement-learning work after Claude incidents exposed weak sandbox assumptions, reward-hacking risks, and the need for real-time agent monitoring. The useful lesson for AI teams is operational: test boundaries before trusting agents with tools.