Hybrid AI: splitting work between device/edge and frontier cloud
YouTube
Intel’s Dr. Olena Zhu discussed hybrid AI, pairing local or edge models with a frontier cloud model to coordinate tasks. The episode highlights routing decisions across privacy, cost, capability, and hardware as key infrastructure choices. This shifts focus from picking a single model to building systems that decide where each part of the work runs.
Why it matters
Intel’s Dr. Olena Zhu discusses hybrid AI, where a local model and/or edge server coordinate with a frontier cloud model. The episode emphasizes that once AI becomes infrastructure, routing work based on privacy, cost, capability, and hardware matters as much as the model choice.
