Check out my three-part article series about the benefits of on-device large language models and learn how to add AI capabilities to your web apps: https://web.dev/articles/ai-llms-benefits #GenAI #WebLLM #PromptAPI

I’m hosting a free webinar tomorrow (in German) about the experimental Built-in AI APIs that the Web Machine Learning Community Group is working on. These APIs are all secure and privacy-preserving, as they perform all the computations on your device. Come and join me! #webml #builtinai #promptapi https://lnk.thinktecture.cloud/webinar-20241218

Just wrapped up an incredible @wearedevs World Congress! 🚀 Excited to share my presentation on cutting-edge web technologies:

🌐 WebGPU
🧠 WebNN
🆕 Chrome’s Prompt API

Slides available here: https://www.thinktecture.com/contributions/generative-ai-power-on-the-web-making-web-apps-smarter-with-webgpu-and-webnn/

#wearedevs #wwc24 #genai #webgpu #webnn #promptapi

As always, I had a great time at DWX! Here are my slides from my talk about local, offline-capable #GenerativeAI models via #WebLLM, #PromptAPI, #WebGPU, and #WebNN: https://www.thinktecture.com/contributions/generative-ai-power-im-web-progressive-web-apps-smarter-machen/ #pwa #dwx2024

📢 On the Chrome team, we've published an Explainer for the planned Prompt API that gives developers access to a (small) language model (shipping with the browser or the operating system) from JavaScript: https://github.com/explainers-by-googlers/prompt-api/.

```js
const session = await ai.createTextSession();

// Prompt the model and stream the result:
const stream = await session.promptStreaming("Write me an extra-long poem.");

for await (const chunk of stream) {
console.log(chunk);
}
```

🔮 #AI #PromptAPI