Skip to content

#教程/实践

0 today

Sep 27Sunday

Simon Willison

Kākāpō Party

Simon Willison 用 Claude Opus 5.5 生成 HTML5 canvas 像素动画 Kākāpō Party,画面中至少 20 只鸮鹦鹉随音乐跳跃、点击触发彩带和气球效果。

Sep 24Thursday

GitHub Blog · AI & ML

Rendering huge pull requests in the GitHub Copilot app

GitHub Copilot 应用重建了 pull request 视图,以流畅渲染含 2,200 个文件、超百万行改动和 400 多条行内评论的超大 PR。其做法是把文档高度拆成确定性的代码几何与动态评论块两套几何:代码行高提前精确算好,评论高度按块懒测量并锚定到文件、行与侧,避免滚动跳动。

Simon Willison

Shadow roots, explained with live examples

一篇用可交互示例讲解 shadow DOM 的教程,演示样式封装、继承、slots、parts 以及 JavaScript 访问方式,展示 shadow root 如何创建带私有样式表和元素的隔离 DOM 树,并与页面 DOM 以特定受控方式交互。该示例由 Fable 5.1 Medium 根据提示词生成。

Sep 11Friday

GitHub Blog · AI & ML

GitHub Copilot app for Beginners: Using the diff, terminal, and browser

GitHub Copilot 应用内置 diff、终端和浏览器三个面板,让用户无需离开应用即可审查、运行和预览 AI 智能体生成的代码变更。diff 面板以绿色和红色高亮显示代码的增删改,终端面板支持直接运行项目命令并可通过 Run 按钮配置脚本,浏览器面板则提供 Pick & Polish 工具来选取页面元素并让智能体调整。

Sep 4Friday

GitHub Blog · AI & ML

GitHub Copilot app for Beginners: Run several agents at once

GitHub Copilot 应用支持同时运行多个智能体会话,每个会话运行在独立的 Git worktree 上,互不干扰且各自保留上下文,可随时切换并从中断处继续。用户可在会话视图中查看各任务标题与进度,例如在同一项目上并行执行 funded sort 开发、无障碍审查和测试运行。

Mar 11Wednesday

Mistral AI

Mistral builds an agent on Vibe that writes Rails tests automatically

Mistral built an agent on its open-source coding assistant Vibe that writes Rails RSpec tests on its own. It reads source code, generates or improves tests, checks them against style rules and coverage targets, and runs unattended in CI/CD.

Why it matters: Mistral published its full method for building an auto-RSpec-test agent on Vibe, including transferable details on context engineering, skill files and custom tools.

Jan 22Thursday

Mistral AI

Heaps do lie: debugging a memory leak in vLLM.

Mistral AI 团队在 vLLM 上排查一起内存泄漏:在 Mistral Medium 3.1、开启 graph compilation 的 Prefill/Decode 分离部署中,系统内存以每分钟 400 MB 线性增长,数小时后触发 out of memory。Heaptrack 显示堆内存稳定,泄漏发生在堆外,最终指向 NIXL 经 UCX 传输 KVCache 的环节。

Aug 1, 2025Friday

Apr 9, 2025Wednesday

Mistral AI

Evaluating RAG with LLM as a Judge

Mistral 介绍用 LLM as a Judge 评估 RAG 系统,由 judge LLM 按数值、二元或定性量表为 generator LLM 的回答打分,再对评测数据集求加权总分。

Mar 4, 2025Tuesday

Mistral AI

Empowering product development with an agentic workflow

Mistral AI 推出 TranscriptToPRDTicket 智能体工作流,由 Mistral Large 2 驱动的 PRDAgent 和 TicketCreationAgent 组成,可将会议转录自动生成 PRD 并转化为结构化开发工单,自动在 Linear、Jira 等项目管理工具中创建工单。