NVIDIA engineer on agentic safety: containment and monitoring beat model-level guardrails
LuizaJarovsky · x · 2026-10-22
AI safety researcher Luiza Jarovsky interviewed Ali Golshan, one of the lead engineers behind OpenShell — the core software of NVIDIA's Open Agent Safety Platform — at NVIDIA GTC.
- Core thesis: agentic safety is a technology problem; companies should focus on agentic containment and monitoring rather than relying solely on model-level guardrails
- They discussed why openness matters and what companies get wrong about AI safety and security today
- Jarovsky left more optimistic, arguing AI governance and regulation should address safety at multiple layers including the technology layer
- Full interview video to be published in her newsletter
Related event: NVIDIA unveils OpenShell reference architecture for secure AI agents(3 posts)→
More from coding & agent
- CreateOS x Stripe Hackathon Draws 59+ Projects Where Agents Write and Verify Their Own Code — jeff_weinstein · 2026-10-22
- v0 on Mobile: One Prompt Repaints a Car Simulator and Pushes to a Branch — fernandorojo · 2026-10-22
- Dev Warns: No CVE Scanning on Every PR in 2026 Means You Won't Make It — letandrewcook · 2026-10-22
- "You asked for better, it added a border": AI design skill meme goes viral — kieranklaassen · 2026-10-22
- Anthropic reportedly previews Claude Duet, a proactive agent built on Opus 5.5 — BLCNYY · 2026-10-22
- Replacing LLM routing calls with 15ms CPU encoders: workshop on deterministic routing — camerongreen95 · 2026-10-22