Upgrade to Pro — share decks privately, control downloads, hide ads and more …

What's New in Web AI?

What's New in Web AI?

Generative AI is becoming a key part of modern software architecture, and its presence in web apps is growing. As demand increases, vendors and specification authors are working to make AI capabilities more accessible and integrated into the web platform. In this session, Christian Liebel—W3C TAG Associate and member of the WebML Working Group—will share what's cooking behind the scenes in Web AI. You'll get an update on the latest advancements in the WebNN API, Chromium's Built-in AI APIs, emerging developer tools, and the real-world challenges that browser vendors and standards authors are navigating to bring AI to the web.

Avatar for Christian Liebel

Christian Liebel PRO

September 05, 2025
Tweet

More Decks by Christian Liebel

Other Decks in Programming

Transcript

  1. Hello, it’s me. What’s New in Web AI? Christian Liebel

    W3C WebML WG & CG TAG Associate christian.liebel @thinktecture.com Angular, PWA & Generative AI Microsoft MVP & Google GDE (Angular, Web)
  2. It’s all about the new possibilities. What’s New in Web

    AI? Why should you care about AI? Stolen from Matthieu’s keynote
  3. Drawbacks What’s New in Web AI? Generative AI Cloud Providers

    Require a (stable) internet connection Subject to network latency and server availability Data is transferred to the cloud service Require a subscription
  4. Bring Your Own AI (BYOAI) – Libraries – WebLLM –

    Transfomers.js – Frameworks – ONNX Runtime – TensorFlow.js – APIs – WebGPU, WebNN – Cross-Origin Storage NEW! Built-in AI (BIAI) – Writing Assistance APIs – Summarizer API – Writer API – Rewriter API – Proofreader API NEW! – Translator & Language Detector APIs – Prompt API NEW! Multimodal – WebMCP NEW! What’s New in Web AI? Web AI Landscape
  5. Storing model files locally What’s New in Web AI? WebLLM

    Internet Website HTML/JS Cache with model files Hugging Face Note: Due to the Same-Origin Policy, models cannot be shared across origins.
  6. Model Size Comparison Model:Parameters Size phi3:3.8b 2.2 GB mistral:7b 4.1

    GB deepseek-r1:8b 5.2 GB gemma3n:e4b 7.5 GB gemma3:12b 8.1 GB llama4:16x17b 67 GB What’s New in Web AI? WebLLM
  7. Drawbacks What’s New in Web AI? WebNN Models can’t be

    shared across origins Inference is fast, but doesn’t reach full native speed
  8. – Grants web apps access to the device’s CPU, GPU

    and Neural Processing Unit (NPU) – In specification by the WebML Working Group at W3C – Implementation in progress in Chromium (behind a flag) – Better performance for specific workloads What’s New in Web AI? WebNN Source: https://webmachinelearning.github.io/webnn-intro/
  9. about://flags Enables WebNN API à Enabled Enables experimental WebNN API

    features à Enabled What’s New in Web AI? WebNN
  10. – Initiative by Google Chrome – Exploratory APIs for local

    experiments and use case determination – Downloads AI models into Google Chrome – Models are shared across origins – Uses native APIs directly (full performance) What’s New in Web AI? Built-in AI https://developer.chrome.com/docs/ai/built-in
  11. Incubated by the WebML CG What’s New in Web AI?

    Built-in AI APIs https://webmachinelearning.github.io/incubations/ DEMO
  12. What’s New in Web AI? Built-in AI APIs Operating System

    Website HTML/JS Browser Internet Apple Intelligence Gemini Nano
  13. What’s New in Web AI? WebMCP – Allows websites to

    expose tools to browser or external agents – Joint effort by Microsoft and Google https://github.com/webmachinelearning/webmcp
  14. Pros & Cons + Data does not leave the browser

    (privacy) + High availability (offline support) + Low latency + Stability (no external API changes) + Low cost – Lower response quality – Less capable – High system (RAM, GPU) and bandwidth requirements – Large model size, models cannot always be shared – Model initialization and inference are relatively slow – APIs are experimental What’s New in Web AI? Web AI