跳到正文
9月29日周二
  1. Rohan Paul63

    Base44 推出 Base Code 早期预览,连接 GitHub 仓库后由智能体在云端配置数据库、基础设施和示例数据,直至运行出实时预览。它支持通过聊天修改代码库并提交 pull request,团队任意成员可在浏览器中协作,未来将支持 WhatsApp / iMessage;产品免费开放 30 天,并计划推出自动化与软件工厂能力。

    引用Maor Shlomo@MaorShlomo

    Today we’re introducing Base Code. It’s an early preview of how we think software will be built in the future. It’s a product that encapsulates everything we’ve learnt from: - How our users are building software. - How we’re building internally, scaling to hundreds of millions of dollars in revenue while keeping our engineering team very small and focused. Here are some of the principles behind it, which align with how we at @Base44 think about the future of software engineering: Cloud: - Software will move past local desktop environments (where current tools are widely used) and move to the cloud. - Moving everything to the cloud is not easy. Setting up dev environments with databases, infra components, services, mock data, etc. is easier said than done. - Base Code first scans your code repo and sets up everything - every infra component (databases, Redis, etc.) - in the cloud. It runs nonstop until your preview environment is ready. - From an enterprise standpoint, it’s also the logical thing to do: a centralized, governed dev environment instead of handing out keys and secrets to all team members. - Once Base Code does that, EVERY team member can work in this environment. No more syncing local environments. Internally, this (cloud) is one of the main things that enabled us to move so fast. Collaboration: - Once everything is in the cloud, everybody can write software from anywhere (any browser, your phone, WhatsApp / iMessage coming soon). - You can easily see what everyone is working on, where they’re at, and how they’re prompting - and jump to their environment in one click. - We’ve built many great collaboration features from the ground up. Loops, automations, software factories: - A full, working cloud environment allows for many advanced capabilities we will unveil soon-think agents running in the browser and testing on every device and in any browser. - It also allows the use of automations to build software factories-e.g., agents reading support tickets, identifying bugs to fix or features to develop, implementing the changes, verifying them in the cloud, and potentially pushing them. And lastly, there’s a real advantage in being model agnostic. -------------- As always, we’re releasing it very early. It’s far from perfect-but we’re looking for early feedback so we can build it together with our great community and make this vision a reality. *We’re giving it away for free for 30 days*. Give Base Code a try. Connect any GitHub repo, get your live preview, and share it with your team. I’d love to hear what works and what doesn’t: http://app.base44.com/base-code

9月28日周一
  1. Anthropic:Claude.dev 开发者博客67

    Anthropic 介绍用 Claude Code 与 claude-api skill 自动化评测设计与 hillclimbing

    Anthropic 在 claude-api skill 中新增 /claude-api build-eval 和 /claude-api hillclimb 两个命令,前者在代码库内通过访谈式流程构建评测集并验证 grader,后者以一次一改动、train/test 分离并检测过拟合的方式迭代优化应用。

    推荐理由:Anthropic 官方讲解了评测设计的关键原则,并给出 build-eval 和 hillclimb 两个命令的用法与真实优化案例,可迁移到自己的应用调优。

  2. Hacker News:AI 热帖86

    Claude Opus 5.5 提示词指南:与 Opus 5 的行为差异及迁移模式

    Anthropic 官方文档介绍针对 Claude Opus 5.5 的提示词模式,覆盖 effort 校准、无人值守智能体运行、安全拒绝、进度更新、多应用工作流、视觉输入和前端设计等场景。

    推荐理由:官方文档梳理了从 Claude Opus 5 迁移到 5.5 时的具体提示词与 harness 调整点,可直接对照排查现有集成的问题。

9月27日周日
9月26日周六
9月25日周五
  1. GitHub Blog64

    GitHub 如何通过迁移 CSS Modules 将 SSR 时间降低 55%

    GitHub 工程师 Josh Black 复盘将 Primer 设计系统从 CSS-in-JS 迁移到 CSS Modules 的历程。截至 2024 年 12 月 Primer 全部组件迁移完成,服务端渲染时间减少 55%,组件初始化时间减少 25%。

    推荐理由:原文给出大厂从 CSS-in-JS 迁移到 CSS Modules 的完整路径和量化收益,可迁移到类似的前端架构改造。

  2. Anthropic:Claude.dev 开发者博客78

    Opus 5.5 上一个任务要花多少钱:Claude Code 成本拆解

    Anthropic 工程师 Addy Osmani 拆解 Opus 5.5 在 Claude Code 中完成任务的成本构成:turns、缓存读取、输出 token 和模型选择四个因素决定账单。Opus 5.5 输入输出价格比 Opus 5 降 20%,缓存读取降 60%,官方估算典型任务整体运行成本低 40%;文中还给出 effort 分级、缓存命中率维护、/usage 自查等省钱做法。

    推荐理由:原文拆解了 Opus 5.5 上一个任务的账单构成,并给出 effort、缓存、压缩等可自查可迁移的成本优化方法。

  3. LangChain:Blog60

    LangSmith 发布 Engine v2、Managed Deep Agents v0.8、Trajectories、Fine-Tuning 及 Custom Apps

    LangChain 在 Interrupt NYC 上发布多项 LangSmith 更新:Engine v2 新增 Red Teaming 主动排查、检测性能趋势与低效工具调用,并可自动验证修复后一键开 PR,自 5 月上线以来已分析超过 60M 条 traces。

    推荐理由:官方一次性发布覆盖开发闭环的多个功能,读者可据此评估自家 agent 生产流程哪些环节能用得上。

  4. Rohan Paul57

    Elon Musk 回应称 Colossus 1 由 15 万块 H100、5 万块 H200 和 3 万块 GB200 组成,Colossus 2 目前为 11 万块 GB200 和 44 万块 GB300。另外 22 万块 GB300 将于下周全面投入运行,11 月再增 22 万块,若顺利 12 月下旬再增 22 万块。

    引用Elon Musk@elonmusk

    @minchoi Colossus 1 is 150k H100, 50k H200 and 30k GB200. Colossus 2 is 110k GB200 and 440k GB300. Another 220k GB300 will be fully operational next week and another 220k in November. If we get lucky, yet another 220k GB300 by late December.

  5. IT之家·人工智能55

    高通骁龙峰会宣布 Modular 平台将进入骁龙产品线,Mojo 编程语言获 Windows 原生支持

    高通在 2026 骁龙峰会宣布 Modular 平台将进入骁龙等完整产品组合,微软与 Modular 合作让 Mojo 编程语言原生支持 Windows。高通于 2026 年 7 月 29 日完成对 Modular 约 39-40 亿美元的收购,Mojo 1.0 已发布并开源标准库、编译器和工具链,目标是让同一套 AI 软件在 GPU、NPU、数据中心 ASIC 等架构及本地与云端间运行。

  6. Aravind Srinivas51

    Perplexity 发布 Search API 的 Fast Search,由其自研 Rust 检索与排序引擎 Photon 驱动,95% 的搜索结果在 230ms 或更短时间内返回,作者称 p95 延迟低于 250ms。

    引用Perplexity@perplexity_ai

    Introducing Fast Search in the Perplexity Search API. Fast Search runs on Photon, our new Rust-based retrieval and ranking service that we built with a small team of engineers and hundreds of agents. It returns 95% of search results in 230 ms or less.

  7. vLLM 官方博客66

    vLLM 新增基于 Gumbel-max 的无失真文本水印功能

    vLLM 宣布支持基于 Gumbel-max 算法的无失真水印,将其集成进 Model Runner v2 的采样管线,并通过 PR #54053、#56122、#56233 实现融合 GPU kernel、双键方案和上下文去重,以兼容投机解码并保持输出多样性。

    推荐理由:原文给出水印算法原理、双键与去重方案及实测吞吐数据,读者可评估在生产环境启用水印的可行性与代价。

9月24日周四