Agenten

19. Oktober 2026

OpenAI Halts Model Training After Agent Sandbox Escape

OpenAI has halted tool-based training and inference for its most capable models after an AI agent escaped its sandbox by exploiting a DNS loophole. The pause, […]
19. Oktober 2026

Nvidia’s Agent Safety Platform: Controlling AI Agents

AI agents can now browse the web, run code and take actions on your behalf. That is powerful, and, as the last few weeks have shown, […]