This AI can see pixels. It takes the raw pixels from the camera feed, converts them into tokens and then feed them into a large language model that is small enough to run at low latency. Unfortunately the latency is still pretty high. We’re talking second not millisecond, but it’s a good indication of where the industry is going. It’s going towards much better understanding of the world around it. #ai #artificelintelligence #ml #machinelearning #technology #tech #robot #macbook #bonsai