Generative AI Directly in My Browser, Is It Possible? (spoiler, yes 😉)
summary
Examines running generative AI models directly in modern web browsers using built-in browser AI APIs and tools, arguing this can avoid cloud costs, network dependency, and privacy risks for tasks like rewriting posts or generating image alt text. Gives a practical overview of current in-browser AI capabilities, accessibility considerations, and live demos (with potential instability).
AI-written summary · about
chapters (6)
- 0:00Introduction
- 6:02Chrome’s AI APIs
- 15:35Translation & text gen demos
- 21:06Auto-summary & spellcheck
- 25:11Multimodal Vision API
- 29:41Conclusion
related talks
45mPrivacy-First In-Browser Generative AI Web Apps
21mUnlocking Client-Side AI in Your Web App
32mPrivacy-first in-browser Generative AI web apps
33mLocal Models: How to Run AI in the Browser
02mDiscover Web AI: Client side Agents, Gen AI, and machine learning in the browser
24mAI right in the browser with Chrome's built-in AI APIs
45mThe Expanding Dark Forest and Generative AI
15mThe future of AI is now: Real-life case studies for on client-side AI adoption in web apps