Agent与工具

OpenScreen 2

Record your demo and let your AI agent do the edits Discussion | Link

New controls and chat improvements in Copilot for JetBrains

This update brings more control over default models and MCP server in GitHub Copilot for JetBrains. It also makes diagnostics easier to address, improves chat navigation and account controls, and strengthens reliability across agent sessions, customizations, and worktrees. What’s

500B Tokens Later: Letting AI Agents Decompile a First-Person Shooter

AI agent teams waste massive tokens for barely measurable quality gains, research finds

Teams of AI agents barely outperform solo agents but cost up to 5.1x more, according to Vals AI. Only one out of four tests with GPT-6 Sol and Claude Opus 5.5 showed a measurable gain. Anthropic's own data backs this up: beyond ten agents, quality plateaus while token costs keep

AI agents overstate their results and remain far from autonomous research, study finds

Epoch AI and Anthropic independently found the same thing: current AI models like GPT-5.6 Sol and Claude Fable 5 can run experiments but lack scientific self-criticism and genuine creative thinking. At best, Sol reached 15 percent of the human reference score, and even that came

GitHub Copilot weekly releases — October 5

This week’s updates make Copilot easier to use across accounts and environments, with more control over what agents can access and how you manage their work. GitHub Copilot Claude Haiku 5.5 is available to Copilot Pro, Pro+, Max, Business, and Enterprise users. Limit agents’ acce

萝卜 PPT：用于制作与美化 PPT 的 Agent Skill

📌 一句话摘要 推介名为「萝卜 PPT」的 AI Agent 技能，主要功能为辅助制作与美化演示文稿。 📝 详细摘要 推文简要分享了一款名为「萝卜 PPT」的 Agent Skill 工具，其核心能力在于自动化制作与排版美化 PPT 演示文稿。 💬 文章金句 一个做 PPT 和美化 PPT 的 Agent Skill 📊 文章信息 AI 初评： 74 来源： Geek(@geekbb) 作者： Geek 分类： 人工智能 语言： 中文 阅读时间： 1 分钟 字数： 61 标签： AI 与智能应用 , AI Agent , 开发者工具 , 个人效率 , 推

Learning to use local AI is exciting, overwhelming, and frustrating

Baby’s first local AI agent. | Photo: Antonio G. Di Benedetto / The Verge I'm embarking on a journey I've so far been hesitant to go on: actually using AI on the regular. Giving my most personal data to cloud services has been a major hold up for me, but it's increasingly possibl

Maildun for Mac

Design on-brand emails by hand, with AI, or over MCP Discussion | Link

API Claws by Buda

Build self-improving agent harness with one API Discussion | Link

AI 时代的移动端稳定性保障 —— 柯南 AI Agent 实践｜QCon上海

密歇根大学 AI 编程方法论深度拆解：五大 Agent 技能体系

📌 一句话摘要 密歇根大学最新课程将 Agent 软件工程拆解为五个核心技能流水线，通过自底向上脚手架、严苛设计访谈、无上下文盲审、代码门禁防漂移与对抗性评审构建严密闭环。 📝 详细摘要 作者系统拆解了密歇根大学「Applied Agentic Software Engineering」课程的五大 Agent Skills 机制：1. /peanuts 通过自底向上的 README 层级化解遗留代码幻觉，并设有人工评审门；2. /elephant 坚持「先长设计后长代码」，通过高强度技术面试与反谄媚防线确立唯一事实源；3. /goldfish 采用零共享

呼吁微信 Clawbot 开放多实例使用支持

📌 一句话摘要 认可微信端 Clawbot 工具的实用性，并向官方呼吁增加多开支持以解决单实例受限问题。 📝 详细摘要 作者评价微信 Clawbot 工具使用体验极佳，但对目前仅能开启一个实例的现状表达了局限感，呼吁官方未来能够支持多实例运行以提升使用效率。 💬 文章金句 Clawbot 这东西确实好用 只能用一个就很憋屈 📊 文章信息 AI 初评： 72 来源： Hardy Chen(@Chchenhao0129) 作者： Hardy Chen 分类： 个人成长 语言： 中文 阅读时间： 1 分钟 字数： 41 标签： 效率与成长 , AI Agent

利用 AI 代码智能体优化软件架构的五种方法