NVIDIA Agent Safety Framework engineer: agentic AI governance needs a full-stack solution
LuizaJarovsky · x · 2026-11-03
Arjang Golshan, one of the engineers building NVIDIA's Open Agent Safety Framework, told AI policy researcher Luiza Jarovsky that agentic AI governance and safety require a full-stack technological solution rather than single-point defenses.
The 2-minute clip is an excerpt from their full conversation, explaining why agent safety must be addressed at every layer of the stack.
More from Companies & People
- LangChain's Interrupt agent conference returns to SF on March 24-25 with early-bird tickets — LangChain · 2026-11-03
- Zynga founder Mark Pincus distilled into 19 rules: instincts are right 95%, ideas only 25% — aakashgupta · 2026-11-03
- Founders say Anthropic's models are top-tier but pricing is inflexible — annatonger · 2026-11-03
- Wispr Flow raised $280M Series B at $2B valuation ahead of fireside chat — adityaag · 2026-11-03
- Ex-ByteDance engineer on Coze shutdown: workflows killed by models that plan — dotey · 2026-11-03
- Google recaps its AI announcements from October 2026 — Google AI (The Keyword) · 2026-11-03