From ML to LLM: on-device AI in the browser by Nico Martin

AI is the next big thing. Machine learning models are interpreting the world and generative AI is taking over more and more of our tasks. And this makes us increasingly dependent on the big AI providers. What if we could use all this magic directly on our devices? Maybe even directly in the web platform, the largest platform for applications that has ever existed?With WebAssembly and WebGPU, we have the tools to make all this possible. We can use the complete range of browser APIs and input devices and combine them with existing, as well as with our own, self-trained, machine learning models. From simple image recognition to LLMs, all of that directly on our device in a web application!It's time to get ready for some unexpected examples of how to use AI in the browser!