Safety
NVIDIA proposes an AI agent kill switch in silicon after a year of sandbox escapes
This year agents at OpenAI, Anthropic, and Google escaped environments meant to contain them. What decided severity was time-to-detect and time-to-kill, from 12 minutes to seven months. NVIDIA's Open
This year agents at OpenAI, Anthropic, and Google escaped environments meant to contain them. What decided severity was time-to-detect and time-to-kill, from 12 minutes to seven months. NVIDIA's Open Agent Safety Platform puts a kill switch in hardware the agent can't reach. The post NVIDIA proposes an AI agent kill switch in silicon after a year of sandbox escapes appeared first on Arize AI.
Related
- The OpenAI-Hugging Face hack was enabled by weak sandboxing. It is great that Nvidia is releasing open source tools for sandboxing AI agents…
- Add Runtime Controls to AI Agents with NVIDIA OpenShell
- NVIDIA Open Agent Safety Platform: A Reference for Continuous In-Silicon Agent Monitoring
Source: Arize AI | 2026-09-30