Generative AI power on the web: making web apps smarter with WebGPU and WebNN

The surge of AI is evident, with tools like Generative Fill in Adobe Photoshop and Microsoft Copilot seamlessly integrated into Office and Windows. Developers are now exploring on-device AI execution, challenging the prevailing cloud-based approach. This paradigm shift offers advantages such as offline accessibility, data privacy, and cost-free execution, while considering device capabilities and initial download times. Large Language Models and Stable Diffusion models already run in web browsers thanks to the WebGPU API. The upcoming Web Neural Network API (WebNN) by W3C will boost the performance of AI model execution even more, providing web apps access to OS machine learning APIs. In this session with Christian Liebel, Thinktecture’s W3C representative, explore diverse approaches, use cases, and the future of AI integration in web development.