Even Google is trying to offload as much of these computations to on-device chips as possible nowadays though.
Their new Pixel has voice control entirely backed by on-device models for example.
I think SaaS is a stopgap for good ML, and that eventually enough of this will be open source, that basic tasks such as vision and speech will be cheap to solve for any company with high tech competency.
Their new Pixel has voice control entirely backed by on-device models for example.
I think SaaS is a stopgap for good ML, and that eventually enough of this will be open source, that basic tasks such as vision and speech will be cheap to solve for any company with high tech competency.