Practical on-device AI for web developers

With new capabilities landing in the browser, it's becoming possible to run AI and machine learning workloads on the client side – which can drive latency, cost, and privacy wins. We'll take you through real-world use cases and discuss when on-device AI is the right choice. We'll show how new web capabilities in Wasm and WebGPU are enabling even more use cases. Finally, we’ll talk about remaining challenges, and share some early thinking to kickstart a collaborative effort.

Speakers: Maud Nalpas, Kenji Baheux

Watch more:

#GoogleIO

Event: Google I/O 2024

[DenisTRUFFAUT]

Great use case, very representative !

[rotteneggconcept]

This is brilliant i can see a use can where the user continually inputs incorrect data or continues to get steps/Processes wrong and on-device training ai will step in an correct user input

[parthi]

Note sentiment analysis, summarization all can get away with incorrectness as well.. we still cannot reliably deploy in a place where it has to be absolutely correct

[portfedh]

Hi! Thank you for this!I have a specific use cas I'd like you to go over if you can. A whatsapp chatbot. I think this will be a very common usecase for AI.