精选归档 · 第 4 页
第 61–80 条 · 共 356 条
02:27
用Claude和Python构建技能驱动的金融分析智能体本教程基于Anthropic的financial-services仓库,用纯Python复现其技能驱动架构。通过解析SKILL.md文件构建可搜索技能注册表,并创建可复用SkillAgent,将金融分析剧本注入Anthropic Messages API,支持迭代工具调用循环。
推荐理由:这个教程把手教你将 Anthropic 的金融技能库打包成可运行的 Python 代理,不是概念演示而是完整工作流,做金融 AI 落地的可以直接抄。
00:50
GitHub Copilot app 入门指南:多 Agent 会话工作区与 Canvas 预览GitHub Copilot app 将 AI 编码工具升级为多 Agent 会话工作区,支持同时管理多个任务线程而不丢失进度。用户可为每个会话绑定项目上下文,通过 /create-canvas 命令在浏览器 Canvas 中预览 UI 并直接点选修改,还能启用 Agent Merge 自动处理 PR 审查反馈和合并冲突。
推荐理由:GitHub Copilot 应用把 AI 编程拆成多会话、画布和 Agent Merge,让 '一键修 bug' 变成真·项目管理流,Copilot 用户该上手试试。
12:00
浪费20亿Token后,我开源了帮Agent定义目标的Leader.skill作者开源了Leader.skill,用于将模糊的人类需求转化为Agent可独立执行数小时的目标任务书。该Skill基于“目标七问”方法论,涵盖目的、完成态、反作弊、边界等维度,并推荐用Claude Fable 5或Kimi K3规划目标,再交由GPT-5.6 Sol或GLM-5.2等模型长程执行。项目已开源。
推荐理由:卡兹克这次把“目标定义”拆成了可操作的七问框架,尤其反作弊和边界思考部分,用 Agent 干长活儿的人看一遍就能省掉 20 亿 token 的冤枉路。
08:12
浪费20亿Token后,我开源了帮Agent定义目标的Leader.skill作者开源了Leader.skill,用于将模糊需求转化为Agent可独立执行数小时以上的清晰目标任务书。该Skill基于“目标七问”方法论,强调指挥官意图与Harness(排除项)比Goal本身更重要。作者推荐用Claude Fable 5或Kimi K3规划目标,再交由GPT-5.6 Sol或GLM-5.2等模型长程执行。
推荐理由:目标七问把指挥官意图与禁止路径前置为约束,让模糊需求转成带边界的任务书,能减少 Agent 长程执行时的方向偏离,适合需要自主跑数小时的团队复用。
06:31
Claude Opus 5深夜发布,以一半价格逼近Fable 5Anthropic发布Claude Opus 5,全量上线并全线可用,上下文100万,知识截止至2026年5月。其ARC-AGI-3得分30.2%,约为第二名GPT-5.6 Sol(7.8%)的四倍,输入每百万Token 5美元、输出每百万Token 25美元,价格与Opus 4.8相同,另有速度提升约2.5倍的Fast Mode。
另有 1 家信源报道X:Kim (@kimmonismus)
推荐理由:与Fable 5的跑分对比展示Opus 5更适合作为执行型Agent,系统提示精简80%的实践提示可简化智能体工作流设计。
01:25
Claude 5 代模型上下文工程新规则:Claude Code 系统提示词精简超 80%Anthropic 为 Claude Opus 5 和 Claude Fable 5 等新一代模型删除了 Claude Code 超过 80% 的系统提示词,且编码评测无显著损失。
另有 3 家信源报道Hacker News 热门(buzzing.cc 中文翻译)X:Thariq (@trq212)X:阿易 AI Notes (@AYi_AInotes)
推荐理由:Anthropic 官方首次分享他们为 Claude 5 代模型移除了 Claude Code 80% 系统提示的实践,五条新规则颠覆了旧有的提示工程常识,每个用 Claude Code 或自建 agent 的开发者都该对照看看自己的系统提示是否在「过度约束」模型。
19:11
Google AI:DEV 作者专属(RSS)精选
Google Cloud Agent Skills 完整指南:从基础到高级云运维Google Cloud 推出官方 Agent Skills 开源指令集,旨在让 AI 编码智能体安全、高效地执行多步骤云操作。该仓库基于 agentskills.io 开放标准,目前收录 70 多项技能,涵盖安全审计、无服务器部署、BigQuery 优化等 8 个类别。技能采用渐进式披露模型,通过验证工作流、安全门控和上下文感知机制,防止智能体盲目执行破坏性命令。
推荐理由:这是 Google Cloud Skills 系列教程第一篇,从安装到触发讲得很细,把 Agent Skills 的“渐进式披露”和安全门机制都拆解了,适合想让 AI 编码代理帮你管云资源的开发者。
01:52
elvis@omarsar0精选 从提示词到任务:多模态交互单元提升AI智能体效率http://x.com/i/article/2079981292108582912What Comes After the PromptKarpathy’s recent post about using long voice sessions as prompts helped me make sense of a prompting technique I now rely on often while building with agents. The visual that accompanies this post, From a prompt to a task, summarizes the idea in one picture.For lack of a better term, I have been calling the unit a task. A task uses multimodal prompting to give an agent the instruction and as much relevant context as possible in one turn. It covers a larger unit of work than a single prompt, and it leaves behind a stored trace that can later become a reusable skill.A task can include a long voice explanation, the current screen, precise text, annotations, transcriptions, images, and any other evidence that helps the agent understand the work. Each modality contributes something different. Voice carries reasoning, priorities, examples, and uncertainty. The screen gives the agent the current state and the environment where the work needs to happen. Annotations direct attention to specific details. Text preserves exact requirements, names, and constraints. Together, these signals give the agent a richer representation of the work.The interactionThe experience feels closer to guiding an agent through a complex assignment than composing a conventional prompt. I front-load the context that would otherwise emerge across several turns, then give the agent room to complete more of the work in a single pass. In practice, I record a voice note while walking through the work, capture the relevant screen, mark it up with quick annotations, and paste in the exact text the agent needs.The agent can still ask questions when important information is missing. In my experience, richer tasks reduce the repetitive back-and-forth where I restate context, point out the same details, or correct an assumption that could have been resolved from the beginning. A recent example was scheduling a post on a platform I rarely use. I recorded a short voice note with the goal and constraints, shared the screen with the scheduling page open, and annotated the fields that mattered. The agent completed the setup in one pass, and the usual follow-ups about which fields to fill and which copy to paste never happened.This has also changed how I think about productivity with agents. A well-formed task gives me more confidence to hand off work and move to something else. That makes parallel work more practical because each agent needs less active supervision while it runs.Why it worksKarpathy pointed out that LLMs are remarkably good at reconstructing intent from long, disorganized voice sessions. A ramble contains many weak signals about the goal, the constraints, the examples that matter, and the speaker’s uncertainty. The model can organize those signals into a cleaner representation of the request.I am extending that idea with more modalities. The voice session provides the reasoning, while the screen, text, annotations, transcriptions, and images provide additional evidence. When one channel is noisy or incomplete, another channel can help resolve the ambiguity.Complex agent tasks often fail at the boundaries between what I meant, what I explicitly said, and what the agent could observe. Multimodal prompting gives the model more opportunities to close those gaps before it begins the work.Cost and payoffThis approach can look like overkill, and sometimes it is. A simple request still deserves a simple prompt. I use richer tasks when the work is long-running, when precision matters, when the agent needs to navigate an unfamiliar interface, or when a mistake would create several rounds of correction.A multimodal task can also cost more because it contains more context. In my experience, that investment usually pays for itself. I can complete a larger unit of work per turn because the agent begins with more of the context it needs.This is especially useful for browser use and computer use. The agent can see the environment, hear the reasoning behind the request, follow annotations that identify important elements, and use text for exact details. That combination helps the agent navigate unfamiliar interfaces.Some of my current examples include scheduling posts on unfamiliar platforms, improving writing and editing, and refining the design of artifacts and web pages. These tasks involve many small decisions that are tedious to encode as a traditional prompt but easy to communicate while showing the work. In a design refinement task, the modalities map naturally. Voice explains what feels off about the layout and what the change should preserve. The screen shows the current state of the artifact. Annotations mark the specific spacing, components, or sections to adjust. Text supplies the exact copy and the constraints that should stay fixed.From traces to skillsI store the traces from these tasks and review them for recurring patterns.The useful patterns usually include the sequence of actions, the constraints I repeat, the quality checks I apply, and the corrections that consistently improve the result. Those patterns can be extracted into reusable skills so the next agent starts with a stronger workflow.This connection to automation is important. A task gives me a practical unit that I can inspect, improve, and eventually place inside a larger loop. The richer initial trace helps me understand which parts can be automated reliably and where human guidance still adds value.The process usually starts with a manual task. Repeated use produces traces, the traces reveal patterns, and the patterns become a reusable skill. Over time, the workflow requires less explanation because the important guidance has been captured.If you are curious to learn more, I will be demoing, sharing, and writing more about this with our academy here: https://academy.dair.ai/Toward omnimodelsOmnimodels, models built to consume voice, vision, images, and text natively, should make this style of interaction feel natural. We will be able to speak, show, point, type, and provide examples within the same session, while the model integrates those signals directly.I feel like I am rehearsing for that interaction now. The current tools already make it possible, even if the experience still feels stitched together across voice, browser state, images, and text.The term task is provisional, but the underlying idea has become clear through repeated use. Give the agent a richer trace of the work, let it reconstruct the intent, store what happened, and reuse the patterns that work.This came from a practical need. I wanted fewer correction loops, stronger handoffs, and more dependable long-running agent workflows. Multimodal prompting has moved me steadily in that direction, and it has become my default way of handing agents real work.译DAIR.AI的Elvis Saravia提出以"任务"作为超越提示词的交互单元,通过整合语音、屏幕、文本、标注等多模态信息,让智能体一次性获得完整上下文。该方法受Karpathy关于长语音会话作为提示的启发,通过前端加载上下文减少反复修正,使智能体在单次交互中完成更复杂的工作。
推荐理由:这篇文章把 Karpathy 的语音提示思路扩展成可落地的多模态任务方法,减少了代理交互的摩擦,做 agent 的可以试试,虽然简单但实用。
01:52
OpenRouter:Announcements(RSS)精选
OpenRouter 推出 Prompt Caching + Sticky Routing,降低多轮 Agent 调用成本OpenRouter 通过 Prompt Caching 与 Sticky Routing 降低多轮 Agent 的 token 成本。缓存读取价格仅为正常输入的 0.1x-0.5x,其中 Claude Sonnet 4.6 缓存读取为 $0.30/M(正常 $3.00/M)。
推荐理由:Prompt caching 不是新概念,但 OpenRouter 把成本算得明明白白,sticky routing 配合 session_id 解决了缓存漂移的痛点,做 agent 的人该抄作业。
00:49
GitHub Copilot 推出 canvases 扩展,实现开发者与 AI 智能体实时协作GitHub Copilot 在应用中推出 canvases 扩展,这是一种共享交互式界面,开发者和 AI 智能体可在其中实时协作。用户通过 /create-canvas 指令创建画布,Copilot 可动态更新内容,用户则通过点击、编辑等操作与同一工作区交互。示例包括快速分类 Issue、生成交互式代码库关系图、管理会话工作树、优化提示词质量以及跨平台搜索知识联系人。
推荐理由:Copilot 的 canvas 把对话变成可拖拽可点击的交互界面,处理 issue、探索代码都变得直观,日常依赖 Copilot 的开发者可以直接用起来。
08:20
不会代码也能做产品:一份从0开始的Vibe Coding保姆级教程本文面向零代码用户,提供一套使用国产大模型(Kimi、GLM、Qwen等)从零开发并上线产品的完整流程。核心步骤包括购买Coding Plan、下载官方Agent编程产品、注册域名与服务器并同步做ICP备案,然后通过Agent的Plan模式描述需求并让AI自动执行开发。上线后建议建立分支保护与测试流程,并强调即使不懂代码,也必须对系统架构了如指掌。
推荐理由:我觉得这是目前最适合非技术人的中文实操指南,把从买服务器到上线的坑都填平了,独家skill也开源了,跟着做能少走很多弯路。
13:46
LLM cliché highlighter:一款识别AI写作套话的检测工具Simon Willison 用 Fable 5 开发了一款 LLM cliché highlighter 应用,用于高亮 LLM 生成文本中常见的十种套话模式,例如“no fluff, no filler, no jargon”这类陈词滥调。该工具旨在帮助读者快速识别并过滤掉充斥在文章中的 AI 写作风格化表达。
推荐理由:Simon 做了一个小工具,能一键揪出 LLM 生成文本里的“陈词滥调”,看完后你可能会克制用“真香”写标题。
17:50
首届"小有可为"大赛乡村教育一等奖作品"智绘科普"技术拆解首届“小有可为”大赛乡村教育赛道一等奖作品“智绘科普”采用 Qwen3.5-397B-A17B 大语言模型与 Manim 动画引擎,通过多Agent分阶段协作与自动修复机制,将知识主题转化为可控、可编辑的教学动画。系统包含规划、草稿、实现、审查、合成五个阶段,渲染失败时可自动提取日志并修复,该工程范式可迁移至其他赛道。
推荐理由:这是官方出品的实战教程,拆解了一套多Agent协作+门控+自修复的工程流水线,技术思路通用,做AI应用的可以直接抄作业。
17:41
小有可为实战教程:拆解乡村教育一等奖作品"智绘科普"的多Agent协作与门控工程首届“点亮乡村课堂”赛道一等奖作品“智绘科普”采用Qwen3.5-397B-A17B大语言模型与Manim开源数学动画引擎,构建多Agent分阶段协作流水线。系统通过规划、草稿、实现、审查、合成五个Agent,配合时序门控、几何审计、视觉审查三道质量门及自动修复回路,实现可控可编辑的教学动画生成。项目底层“多Agent协作+门控+自我修复”范式可迁移至养老陪伴、孤独症干预等场景。
推荐理由:拆解了一套多Agent协作、阶段门控加自动修复的工程范式,为在数学教学等严谨场景驯服大模型输出提供了可复用的流水线思路。
01:32
Anthropic 用 Claude Code 大规模迁移代码:Bun 百万行 Zig 转 Rust,两周完成Anthropic 工程师用 Claude Code 在两周内将 Bun 的百万行 Zig 代码迁移至 Rust,100% 现有测试通过,合并后出现 19 个回归问题已全部修复。另一工程师用周末将 Python 代码库迁移至 16.5 万行 TypeScript。迁移消耗约 16.5 万美元 API 成本,但编译时间从八分钟降至两秒,二进制启动快 6 倍。
推荐理由:Anthropic 用自家 Claude Code 把百万行 Zig 代码迁到 Rust,两周搞定,这不仅是案例展示,更是开发者如何用 AI 重构代码库的实操指南,尤其适合那些被遗留代码拖累的团队。
22:27
Google AI:DEV 作者专属(RSS)精选
DiffusionGemma 开发者指南发布Google AI 发布 DiffusionGemma 开发者指南,该实验性模型基于 Gemma 4 架构,采用计算受限并行生成,在单张 NVIDIA H100 上实现 1000+ tokens/秒的生成速度。模型为 26B 参数的 MoE 架构,推理时仅激活 3.8B 参数,可在 18 GB VRAM 内量化部署。
推荐理由:虽然 DiffusionGemma 是实验性的,但把文本生成从内存带宽瓶颈转向计算瓶颈的思路非常新颖,这篇指南给出了可落地的服务方案和微调手法,做推理优化的值得跟进。
15:43
Patter SDK 教程:构建餐厅预订电话智能体,支持动态变量、护栏、延迟仪表盘与评估检查Patter SDK 发布教程,演示如何构建一个餐厅预订场景的语音智能体工作流。该流程支持动态调用变量、注册可调用工具、应用输出护栏(如PII脱敏、脏话过滤、话题范围限制),并可在无需实时电话凭证的情况下运行脚本化通话模拟。教程还涵盖延迟与成本指标追踪、回归式评估检查,以及将智能体逻辑、工具调用、安全检查和通话模拟整合为单一结构化管线。
推荐理由:这个教程把 Patter SDK 的语音代理从模拟到部署跑了一遍,代码能直接抄,想上手电话 AI 的开发者可以当样板,不过工具本身还比较新,生态有待验证。
11:30
千问APP联合武汉发布举办AI求职实战课,演示简历诊断与办公自动化千问APP与武汉发布在武汉举办AI求职实战课,现场演示了用千问进行简历诊断、PPT制作和表格分析。产品经理提出“给全材料、说明目标、定义标准、划定边界、索要可编辑文件”五步法,并展示了将486行杂乱销售数据浓缩为一页结论PPT的“建、理、算、析、呈”方法论。
推荐理由:千问官方出的这套办公Prompt,从简历诊断到PPT救场再到经营数据清洗,方法论清晰可套用,求职者和日常办公的人可以直接拿来用,比泛泛的教程实在。