Agent Inference at the "Speed of Light" — How NVIDIA moves like a $4.3 Trillion Startup
Source
youtube.com
Author
Latent Space
Date
Why it matters
Offers a simple security heuristic for agents (never grant files, internet, and code execution together) and covers inferenceRunning a trained model to get answers — the phase where AI is actually used, as opposed to trained.Full definition → serving with NVIDIA Dynamo.
Terms in this piece · Glossary
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
inference — Running a trained model to get answers — the phase where AI is actually used, as opposed to trained.
videoThe Future of AI Infra: from Kubernetes to Agent Sandboxes — Akshat Bubna, Modal CTOLatent Space
videoThe Inference Frontier: from 100 to 10,000 tokens per second — Sean Lie, Cerebras CTOLatent Space
videoThe Agent Cloud: Databricks’ Bet on the Future of AI — Matei Zaharia and Reynold XinLatent Space