NVIDIA's Open Shell enforces agent policy in the kernel, quarantines rogue agents in milliseconds
GavinSBaker · x · 2026-09-28
Investor Gavin Baker breaks down NVIDIA's approach to agent safety as an engineering problem: Open Shell enforces policy at the kernel level, outside the agent process, paired with Sentry running on BF-4 that can quarantine a rogue agent within milliseconds. His takeaway: "containment is the backstop to alignment" — seatbelts and airbags for AI, as he puts it.
Related event: NVIDIA Launches Open Agent Safety Platform with 100+ Partners(35 posts)→
More from coding & agent
- Baseten's Guide: Evaluate Open Models for Coding Agents on Your Own PRs — baseten · 2026-11-16
- Google Research open-sources PaperOrchestra, a multi-agent framework for writing AI papers — google-research · 2026-11-16
- ffmpeg-skill gives coding agents local video editing via 42 FFmpeg tools and MCP — kajisho5 · 2026-11-16
- Agents Now Reply to Slack Messages on Their Own, Resolving a Prod Incident Ghost-to-Ghost — iamrobotbear · 2026-11-16
- Engineer's Interview Prep Method: Use Claude to Find Which Answers Undersell Your AI Work — brandon_galang · 2026-11-16
- DeepSeek open-sources its app frontend "chat-demo", already at 3.9k stars — NielsRogge · 2026-11-16