From Cloud Dependency to Local Intelligence: The Future of Accessible AI | Intel

Описание: As AI models grow more powerful, the question of where they run is becoming just as important as what they do. In this episode, Brandon Weng, Co-Founder and CEO of Fluid Inference, unpacks what it takes to move AI from massive data centers to everyday devices—and why that shift matters. Brandon shares the story behind Fluid Inference, a company focused on making it easier for developers to deploy large AI models like transformers on consumer hardware. From pivoting away from his previous project, Slipbox, to the technical and philosophical choices that shaped Fluid’s direction, he walks us through the thinking behind local-first AI. We explore the tradeoffs between cloud-based and on-device inference—touching on privacy, cost, control, and performance—and the hardware breakthroughs that are making edge AI more viable, including integrated NPUs in devices like Intel’s AI PCs.

00:00 Intro
01:00 Brandon’s Journey to Fluid Inference
03:20 AI Costs & Meeting Bots
05:00 Why Run AI Locally
09:00 What is Fluid Inference
15:00 Pivot to Open Source
17:30 Cloud vs. Local AI
20:00 Deploying Models on Devices
23:00 Use Cases: Voice, IoT & Security

Subscribe now to Intel on YouTube: https://intel.ly/3IX1bN2

About Intel:
Intel, the world leader in silicon innovation, develops technologies, products and initiatives to continually advance how people work and live. Founded in 1968 to build semiconductor memory products, Intel introduced the world's first microprocessor in 1971. This decade, our mission is to create and extend computing technology to connect and enrich the lives of every person on Earth.

Connect with Intel:
Visit Intel WEBSITE: https://intel.ly/Intel
Follow Intel on X: https://intel.ly/Twitter
Follow Intel on INSTAGRAM: https://intel.ly/Instagram
Follow Intel on LINKEDIN: https://intel.ly/LinkedIn
Follow Intel on TIKTOK: https://intel.ly/TikTok

From Cloud Dependency to Local Intelligence: The Future of Accessible AI | Intel
   / intel