🔥 NVIDIA DOESN’T TRUST AI AGENTS TO POLICE THEMSELVES
So it’s building a SECURITY LAYER outside the AI.
AI safety is shifting from what models SAY to what agents are ALLOWED TO DO.
As agents gain access to files, code, APIs and company systems, $NVDA wants the INFRASTRUCTURE itself to decide what AI can and cannot do.
Its new AI agent security stack explained 🧵
So it’s building a SECURITY LAYER outside the AI.
AI safety is shifting from what models SAY to what agents are ALLOWED TO DO.
As agents gain access to files, code, APIs and company systems, $NVDA wants the INFRASTRUCTURE itself to decide what AI can and cannot do.
Its new AI agent security stack explained 🧵
