Ray Fernando describes using the touchscreen and split-screen interface, along with his initial impressions of the keyboard, battery and temperature. He says NVIDIA supplied the device and access to an announcement event.
Ray Fernando discusses 128 GB of unified memory, local model useA local model runs on computing infrastructure controlled directly by the user rather than only through a remote model service. and routing work between machines on a network. He considers possible future on-device workflowsOn-device inference runs a trained model on the user's device rather than relying entirely on a remote model service. such as processing receipts and computer-use agentsComputer use lets an AI agent interact with software through interface controls such as screens, buttons, keyboards and pointers., while noting that he is still experimenting with them.
Watch on YouTube
