A hybrid approach combining client-side models for privacy and latency with cloud fallbacks addresses current hardware limitations.
Using built-in browser AI or fine-tuning with smaller LoRA weights can avoid forcing users to download gigabytes of data.
Community projects are exploring peer-to-peer GPU sharing while the W3C works on standards like WebNL and WebMCP for a stable foundation.
The WebMCP standard allows websites to expose their functionality as tools, enabling agents to perform complex tasks across multiple services.
Technologies like WebGPU and the upcoming WebNN provide the necessary hardware acceleration for running complex models efficiently in the browser.
Developers can choose between built-in browser AI or more flexible "bring your own model" approaches using runtimes like TensorFlow.js and ONNX.
JavaScript developers are encouraged to explore Web AI to build privacy-focused applications and reduce long-term costs by shifting computation to the client.
Jobs that call for the skills explored in this talk.