Pai 的 AI 雷达
含近几日仍热话题，按时间衰减排序。今天先看 Claude for Small Business launches new workflows, integrations, and training programs，其次 Mintplex-Labs/anything-llm。并行还有 beenuar/AiSOC、Is z.ai shipping a different ZCode client than the source?。
arXiv:2609.28559v1 Announce Type: cross Abstract: LLMs increasingly operate through coding-agent harnesses that inspect repositories, invoke tools, and modify files. Substituting the model behind such an agent can therefore change security-relevant decisions, including whether it
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%。
📌 一句话摘要 作者分享 OpenClaw 的 `test audit` 技能，该技能要求 Agent 在编写测试前先回答四个必要性问题，以判断是否应添加测试，从而避免生成无用的垃圾代码。 📝 详细摘要 针对 AI 编程中常见的“为了测试而测试”现象，作者指出 OpenClaw 提供了一个名为 `test audit` 的技能。其核心逻辑是强制 Agent 在写测试前进行自我审查，通过回答四个关于必要性的问题来决定是否添加测试。只有判断通过的测试才会被写入，旨在从源头遏制低质量、冗余的单元测试生成。 💡 主要观点 引入前置审查机制以抑制 AI 生成无效测
CodeQL 2.27.1 adds new queries for C/C++ and C#, support for Kotlin 2.4.20, and query-accuracy improvements. CodeQL is the static analysis engine behind GitHub code scanning, which helps you find and remediate security issues in your code. Language and framework support C/C++ We’
arXiv:2609.28530v1 Announce Type: new Abstract: A general-purpose vision-language model can understand a task goal without knowing how a particular robot's motion and functional parts produce the intended effect. We introduce KnowBody, a harness that makes these action-relevant b
arXiv:2609.29394v1 Announce Type: new Abstract: General-purpose robot agents must learn from experience, transfer to new tasks, and act efficiently. Code as Policies (CaP) methods generate and repair programs at runtime, incurring latency and entangling reusable mechanisms with t
arXiv:2609.30249v1 Announce Type: cross Abstract: Coding agents have demonstrated enormous success in solving complex programming problems. To leverage their potential for robot systems, this work introduces Robot Agentic Programming from Demonstrations (RAPID), which automatical
arXiv:2609.29389v1 Announce Type: new Abstract: Foundation vision-language models (VLMs) understand objects, instructions, and spatial relations, yet translating this capability into robotic manipulation remains difficult. Vision-language-action (VLA) models require extensive dem
arXiv:2609.28766v1 Announce Type: new Abstract: Applying adhesive tape to secure wire harnesses or seal packages requires robots to coordinate a flexible strip, a moving roll, and surfaces that attach and detach. Simulation could make these interactions repeatable for robot devel
arXiv:2609.29423v1 Announce Type: new Abstract: No two robots are truly identical: calibration, battery state, sensor drift and wear give every swarm a distribution of behaviour rather than a single point, usually treated as an imperfection to be minimised. In animal collectives
Expired artifacts are no longer displayed in the GitHub Actions run summary or returned by the REST API. Previously, an expired artifact remained visible with an “Expired” pill, even though the underlying files had already been deleted from storage. That leftover pill left some u
📌 一句话摘要 介绍一款名为 ai-copywriter 的 Agent Skill，通过内置 33 种 AI 写作特征自查、强制人工提供数据及多角度生成标题，解决 AI 文案“AI 腔”重和标题空洞的问题。 📝 详细摘要 推文指出当前 AI 生成标题常陷入「终极」「革命性」等空洞词汇，而要求克制又会导致平淡。为此推荐了 ai-copywriter 这一 Agent Skill，其核心机制是将标题/简介生成与「去 AI 腔」结合。它基于维基百科整理的 33 种 AI 写作特征进行自我审查，并在动笔前明确受众、竞品及真实数据背景。该工具强调数字必须由用户提
You can now require an interactive re-authentication or a multi-factor challenge before members take high-impact actions on GitHub Enterprise Cloud accounts. Proof of presence is an expansion of GitHub’s sudo mode for enterprises, enforcing a higher security bar when it’s needed.
We’re 176 years into this AI experiment. Wait…it’s only been three years? Are you sure? Sometimes I remember things that happened last year, but it feels like it was so long ago. Did that really happen to me, or was it something that happened to my dad and he just told me about i
For the past few months I've been a big ChatGPT Codex user and every new Claude release, I was never excited for. Things cost so much. Our startup was spending far too much using fable and the reasoning gap wasn’t justifying it. Personally I was running almost $1,000 a month and
We seem to be entering into an AI agent renaissance. Meta's new consumer-facing AI agent, Muse, topped the App Store charts soon after its release and has 600,000 daily active users in the US, by an Apptopia estimate. And AI agent platform Instinct, whose eponymous creator is fun
Up until five months ago, every PR in our team was reviewed by at least two people - the engineer who wrote the code, and one or more reviewers. Exactly how 99% of software engineering teams have worked for decades. Then in April, we moved to work on a brand new product, without
📌 一句话摘要 F-Droid 2.0 发布，作为十年来最大更新，引入全新界面、改进中文搜索及后台自动安装功能，但移除了部分旧版特性如紧急清除。 📝 详细摘要 开源 Android 应用商店 F-Droid 于 2026 年 9 月正式发布 2.0 版本，官方称之为十年来最大更新。新版全面重构了 UI，简化为「发现」「搜索」「我的应用」三大导航，并细化了 17 个应用分类。核心功能升级包括支持基于描述和翻译的中文/日文/韩文搜索优化，以及实现后台自动下载与安装更新，无需用户手动确认 APK。此外，新版移除了一些旧功能，如伪装成计算器的完整功能（仅保留图标
The findings highlight how AI-generated and vibe-coded apps can spill and expose users' data when not configured or secured properly.
📌 一句话摘要 美股开盘后科技巨头走势分化，微软因发布新版 Copilot AI 功能大涨超 3%，半导体板块受 ARM 等个股带动走高，同时美伊谈判进展导致国际油价下跌。 📝 详细摘要 9 月 25 日晚美股三大股指小幅高开，市场呈现结构性行情。科技七巨头中，微软凭借发布引入 Home、Code 和 Autopilot 三大新功能的新版 Copilot，股价大涨超 3%；谷歌、英伟达、苹果小幅上涨，而 Meta 跌逾 2.7%。半导体板块整体走强，费城半导体指数涨超 1%，ARM 领涨超 5%，安森美、SK 海力士等跟涨，英特尔逆势下跌。此外，受伊朗向
GitHub Copilot code review now offers additional personal configurations to an expanded set of Copilot plans and an enterprise-level default setting. These improvements are now generally available: A dedicated personal settings page for automatic review and your default review ef
Broad refactors and migrations often have to land as one change. Stacked pull requests are a great way to split work into smaller changes, which makes reviews easier and helps teams ship with less risk. But some changes, like this one, can’t be split cleanly. That leaves you with