用Three.js和WebGPU打造会随音乐律动的液态“Goo”，从软体到立方体的滚动变形，技术拆解太带感了
Exploring the techniques behind an audio-reactive 3D scene, from custom geometry deformation and music analysis to scroll-driven morphing, damping, an…
选中网页文本即可调用本地大模型生成解释，Chrome/Edge扩展，无需联网，隐私友好。
Article URL: https://github.com/Vishwamitra/explain-this Comments URL: https://news.ycombinator.com/item?id=49107389 Points: 1 # Comments: 0
浏览器运行1-bit量级大模型，WebGPU加速，前沿高效新体验。
Article URL: https://huggingface.co/spaces/webml-community/bonsai-webgpu Comments URL: https://news.ycombinator.com/item?id=48936994 Points: 3 # Comme…
谷歌新出LiteRT.js，Web AI推理性能飙升3倍，用WebAssembly和硬件加速打破浏览器瓶颈。
IT之家 7 月 10 日消息，谷歌昨日（7 月 9 日）发布博文，为提升浏览器人工智能（AI）及机器学习（ML）工作负载的运行速度， 推出全新的 LiteRT.js 库。 谷歌表示 LiteRT.js 采用 WebAssembly，并结合 WebGPU 与 WebNN 等硬件加速能力，用于替代 T…
1-bit量化+WebGPU，让1.7B大模型在浏览器里流畅运行，技术突破值得关注。
Article URL: https://aidekin.com/ Comments URL: https://news.ycombinator.com/item?id=48820583 Points: 4 # Comments: 2
用WebGPU打造Agent工作流可视化工具，支持Claude命令生成，直观理解AI代理运行逻辑
Recently studying agent and workflow. Decided to spawn a /goal command on Claude code and made this. Comments URL: https://news.ycombinator.com/item?i…
首个基于WebGPU的在线HDR图像编辑器，支持动态HDR内容渲染，代码已开源。
Source code: http://github.com/anchpop/pictolab I love HDR, but until recently dynamic HDR content was hard to render in the browser. But now, with br…
只需29-33%更少内存，LlamaWeb在16种设备上实现高性能多精度LLM推理，彻底改变浏览器端大模型部署。
arXiv:2605.20706v1 Announce Type: cross Abstract: Running language models in the browser presents a unique opportunity to build efficient, private, an…