有人开源了一套 PR Agent 的 Skills 合集,30 多个技能直接复用,还带 newsjack.sh 这种追热点脚本,做公关运营的可以拿来玩玩。
Latest
Higgsfield 的动画团队把自己的 AI 工作流拆开讲了,从分镜到成片每一步怎么用工具都有,做动画的可以直接照着上手。
博主拿 Jev 和 Claude Opus 5 跑同一个新闻监控任务,一个 24.9 秒花 0.19 美元,一个只处理了 4 条花 0.77 美元,做品牌借势的可以看看。
有人把 30 条 Claude Opus 5.5 做浏览器动画的推文整理成库,提示词和方法都给你,想复现的直接抄作业。
斯坦福的 Agent 课程 CS329A,9 讲视频全免费挂在 YouTube 上,讲课老师有 Google Brain 和 DeepMind 背景,想系统学 Agent 的直接看这个。
斯坦福的 AI Agent 课程 CS329A,9 个视频全放出来了,两位老师都在 Google Brain 和 DeepMind 待过,长假正好刷完。
用 opencode 的 10 美元套餐算了笔账:MiMo 能跑 3 万次请求,比 DeepSeek 的 2.6 万还多,就是不太稳。想省钱写代码的可以看看怎么选。
The practical implication is that engineering effort spent on custom scaffolding or fine-tuning pipelines may deliver returns that last only one model cycle. Teams weighing fine-tuning against prompt and context engineering can use this as a counterweight, prioritising flexibility to swap in the newest general model. It reflects Anthropic's own product philosophy behind Claude Code.
Tool output noise is an overlooked cost driver in agent workflows, and filtering it compounds with cheap-model pricing instead of replacing it. Developers running shell-heavy agents on metered APIs can apply the same RTK layer to cut context bloat without changing models. The 70% figure gives a concrete benchmark for judging whether similar filters pay off in your own stack.
Bindu Reddy 演示了用 Astra 6 加 Opus 5.5 自动选模型,直接做出带支付和多人功能的 3D 应用,做 3D 项目的可以试试。
The notable pattern is the agent stack: an AI agent embedded natively over ACP, controlling the browser through an MCP server — a lighter alternative to Electron-based agent shells. Developers building desktop tools with agent integration can study the MCP-over-ACP RFD he links. His claim that native Rust/Swift apps will displace Electron stacks is a bet worth stress-testing against your own toolchain.
The setup turns local-versus-API latency into a visible, playable comparison — a concrete way to feel how response delay shapes agent behaviour in real time. Builders interested in agent frameworks can clone the GitHub repo and adapt the same head-to-head harness to benchmark their own local models against hosted APIs. It also doubles as a showcase of Typesafe's Jev agent in an unusual adversarial role.
有人只对电脑说了 5 分钟需求,Claude Opus 5.5 就自主干了一整晚,帖子里连完整提示词都贴出来了,想学长任务提示词的可以看看他怎么写的。
有人把 Claude Opus 5.5 做视觉设计的完整 Prompt 拆给你看,连生成的 JS 动画源码都开源了,写提示词的可以直接抄结构。
xAI 两位 Grok Bot 核心成员晒真实配置,有 bot 自动卖二手、订跨国航班,还有一套能照抄的放权四步法。
Higgsfield 给 Claude Opus 5.5 做了 11 个技能包,从 Blender 建场景到 PR 调色都能接手,交付后还能接着改,做后期的可以看看。
一场把 AI 设计、3D 打印、拍广告压进一下午的现场挑战,比看 Demo 直观多了,成片快出了。
用 Claude Opus 5.5 做的 282 条爆款视频,每条都附了原提示词,还能在 Skillry 上对照重制效果,抄作业直接抄提示词就行。
阿里云几十位工程师写的企业级 Agent 落地手册,从架构到治理到调优全都有,还带调研数据,做 Agent 工程的直接收藏看。
一位日本开发者用 Claude Opus 5.5 加 Unreal 引擎做出能跑能翻滚能挥剑的 ARPG,还接了手柄实机试玩。
Claude Code 作者是这么用 AI 的:别套死流程,给工具给自由,模型自己会找到路。做智能体的可以听听这期播客。
用 GPT-6 Pro 调研、Opus 5.5 做视频,把 GIS、古籍文本挖掘这些数字史学工具讲了一遍,文科研究可以抄这个流程。
The DropBox analogy for OpenAI's consumer business and the argument that closed labs may stop publishing frontier models altogether are the least-discussed parts of this conversation. Investors and operators weighing AI capex cycles get a framework for judging whether free cash flow can eventually take over from debt and equity financing. His years living in Taiwan also give the TSMC supply-chain discussion a first-hand edge most US commentary lacks.
有博主实测 ChatGPT 语音模式调用 Linear 等工具,反应慢还老报错,说话人设也记不住,想用语音管工作的先看看踩坑。
Recraft V4.1 Flash 的实战案例,一条长提示词画出一堆小细节还都放对位置,完整提示词直接贴出来了,可以抄着改。
Hamel Husain 回答了一个实用问题:用 LLM 当评审做评测时,得先拿人工标注数据验证它靠不靠谱,别直接信。
Matt Shumer 分享的一条提示词,让 AI 从逻辑门一路造出 CPU、操作系统和能玩的 3D 游戏,想折腾提示词的可以抄作业。
Databricks 这篇讲企业 agent 怎么管:91% 公司都在跑两套以上 AI 编码工具,它给了个选型、上下文、管控三件套框架,搞团队落地可以参考。
让 Claude 用 JS 在 canvas 上直接画应用图标,作者拿自己 BaoCut.app 实测,提示词附上,做 App 的可以试试。
宝玉这个方法挺妙,直接让 Claude 在 canvas 上用 JS 画图标,连设计软件都不用开,做独立开发可以试试。
The practical trick is the two-tier confidence output: routing medium-confidence flags back to the agent for verification doubles catch rate without materially inflating false positives. Developers building agent harnesses can offload cheap, deterministic checks like linting to small System One models instead of paying frontier-model prices for every call. DAIR.AI has published related resources at academy.dair.ai for those wanting to replicate the setup.
剪辑师可以看看:4 个开源 skill 分别管粗剪、Premiere 精修、字幕和成片,配 Opus 5.5 就能跑,还附了个 180 个 skill 的合集
The gap between pilot demos and always-on enterprise serving is now being closed inside the PyTorch and vLLM ecosystems, meaning teams no longer need proprietary stacks for reliable agentic workloads. Platform engineers and ML infrastructure leads evaluating serving stacks can benchmark vLLM's enterprise features against alternatives. Developers of independent tools can also learn how Ecosystem Landscape membership raises their project's visibility.
在 VS Code 里装个 Cline 插件,Gemini 3.8 Flash、DeepSeek V4.1 Flash 这些模型都能白嫖,写代码零成本,试试看。
4 个现成 skill 拼出一条完整剪辑流水线,从粗剪到出片全自动,做视频的可以直接抄这套配置。
Muse 和 Grok Bot 老被反爬拦住的话,Garry Tan 推荐用 AsideAI 浏览器加 MCP,拿台旧电脑挂着就能用你自己的账号干活。
Databricks 这份指南教你怎么把 Genie Ontology 越用越准,从数据基础到权限治理一步步搭,建议先挑一个高价值业务域做起。
Most viewers quit after the first lecture, so finishing all 9 gives systematic grounding that ad-hoc prompting cannot replace. Builders designing agent training loops or evaluating self-improvement workflows will get the most value. Since the lectures are free on YouTube, anyone in Singapore or the wider region can follow along without access barriers.
黄叔三个月烧了10万块总结的 Agent-First 踩坑经验,10月16-17日 HIPM 峰会上讲1小时,做产品的可以去现场听。
Only the latest 2000 items are listed; for older ones see the daily archive