On-Device AI: Building Smarter, Faster, And Private Applications — Smashing Magazine
January 21, 2025
Shouldn’t there be a way to keep your apps or project data private and improve performance by reducing server latency? This is what on-device AI is designed to solve. It handles AI processing locally, right on your device, without connecting to the internet and sending data to the cloud. In this article, Joas Pambou explains what on-device AI is, why it’s important, the tools to build this type of technology, and how it can change the way we use technology every day.
Source: On-Device AI: Building Smarter, Faster, And Private Applications — Smashing Magazine
We think something big is coming to the Web in the next 12-24 months.
Inference, the aspect of large language models where we generate a response to a prompt (as opposed to training which is creating the model in the first place) is moving onto the device (in many cases).
Apple Intelligence is perhaps the most high profile example of this.
But the Web has a strong story here too–and Joas Pambou does an incredible job of outlining the field here.
Highly recommended.
