Qiita - 人気の記事Chromeの組み込みAIに画面共有してデスクワークを実況させる
https://qiita.com/shichi343/items/27c5a04cdaeb19a0d071?utm_campaign=popular_items&utm_medium=feed&utm_source=popular_items
Christian Liebel"I want it that way…" 🎶
Back from 3 weeks of traveling! Here are some conf highlights: I was honored to speak at my 4th NG-DE. My talk was about what’s new in #WebAI—with updates on #WebNN, #PromptAPI & lots of Karaoke.
➡️ Slides: https://www.thinktecture.com/contributions/whats-new-in-web-ai/
On my way to the @wearedevs World Congress 2025 in #Berlin! Meet me at the venue and join my talks on Friday, July 11:
➡️ 10:10 “Hello, AI?!” — Real-time interactions with Gemini Live at the Google Cloud booth
➡️ 15:00 #PromptAPI & #WebNN: The AI Revolution Right in Your Browser at Stage 7
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/
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
Thomas Steiner 
📢 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);
}
```
