Writing
Agents
22 articlesFilter articles Agents
Ideas to revisit
Agents
-
Impeccable:把 AI 前端设计要求变成可检查的工作流
Impeccable 把 PRODUCT.md、DESIGN.md、61 条确定性规则和浏览器组件 Review 组合成 AI Coding 的前端设计验收流程。
Chinese -
Meta 的 AI 数学论文开始标注模型参与
Meta 公布 6 篇与 Muse Spark 协作的数学论文。更值得关注的是贡献来源、第二组复核、并行结果和形式化验证怎样进入公开论文。
Chinese -
Muse Gadgets 把 ESP32 和 Raspberry Pi 接进 Muse
Muse Gadgets 用 ESP32 与 Linux Device SDK 把屏幕、按钮、传感器、执行器、文件和命令接成 Muse 的设备端点。
Chinese -
Agents API browser auth keeps passwords out of model input
How Agents API separates site approval, login credentials, and screenshots, and why network access and site approval cannot replace action-level confirmation.
English -
OpenAI 给 Agents API 加了浏览器,密码不走模型上下文
拆解 Agents API 的网站访问审批、独立登录通道与截图输出边界:为什么能联网不等于已授权,站点批准也不能代替高影响动作确认。
Chinese -
Cloudflare redesigns its CLI for agents
Cloudflare launches cf in open beta, using Wrangler usage data to explain default JSON, command search, and typed configuration.
English -
Cloudflare 把 CLI 重新做给 Agent
Cloudflare 发布 cf open beta,用 Wrangler 的实际使用数据解释默认 JSON、命令搜索和类型化配置。
Chinese -
Cloudflare data puts agent traffic on the website budget
Cloudflare and Fastly network data reveal repeated crawling, origin costs, access-policy questions, and the returns websites get from machine traffic.
English -
Company Brain separates team memory permissions
Company Brain scopes team-agent memory by room and user permissions, with personal authorization, traceable sources, and separate tool-write access.
English -
Company Brain:团队 Agent 的记忆权限该怎么拆
拆解 Company Brain 的团队记忆与权限设计,重点看个人授权、共享知识、可追溯来源和团队 Agent 的权限边界。
Chinese -
Claude takes a candidate to the lab, not a new CRISPR
About 950 Claude agents helped identify ART. Human wet-lab experiments confirmed short RNA expression, but its main biological function remains unknown.
English -
Claude 把候选推进湿实验,但这不是新 CRISPR
Anthropic 用约 950 个 Claude Agent 从大规模逆转录酶候选中筛出 ART,并由人类湿实验验证短 RNA 表达,但 ART 的主要功能仍未知。
Chinese -
Link CLI lets agents pay without real card numbers
Stripe Link CLI separates purchase intent from payment permission. Agents request a purchase and receive one-time credentials only after user approval.
English -
Link CLI 让 Agent 付款,但不拿真实卡号
Stripe Link CLI 让 Agent 先提交购买请求,用户确认后再获得本次支付需要的一次性凭证,把购买意图和支付权限分开。
Chinese -
LobsterAI: send tasks by phone, run them on your desktop
LobsterAI connects phone messages to a local desktop agent. The phone handles tasks and approvals while the computer works with files, terminals, and browsers.
English -
Deploying agent backends with Python Workers GA
Python Workers GA supports web frameworks and agent libraries. WebAssembly package compatibility remains the main migration boundary.
English -
Cloudflare Python Workers GA 后,Agent 后端怎么部署
Python Workers 已进入 GA,FastAPI、Django、Flask 以及 openai、langchain、mcp 可以直接运行在 Workers。真正的迁移边界仍是 WebAssembly 包兼容性。
Chinese -
A Minecraft agent separates planning from fast decisions
This Minecraft agent uses Astra for slow planning, JEV for frequent action selection, and Mineflayer for execution, with logs and scripts to verify runs.
English -
Minecraft Agent 把规划和即时决策拆成两层
这个 Minecraft Agent 让 Astra 负责慢规划、JEV 负责高频动作选择、Mineflayer 负责确定性执行,并用日志和验证脚本保留运行证据。
Chinese -
FDE growth: 519 overseas jobs, 28 in China, 6 projects
A study of 519 overseas job listings, 28 roles at major Chinese firms, and 6 projects examines FDE responsibilities, growth, costs, and scalability.
English -
FDE 为什么突然火了:519 条海外 JD、28 条国内大厂岗位和 6 个真实项目
用 519 条海外公开 JD、28 条国内大厂岗位和 6 个真实项目,拆解 FDE 的职责、增长、国内落地、成本与规模化条件。
Chinese -
Jev gives agents typed decisions instead of generated text
TypeSafe Jev uses Choice, Score, and Noul for constrained agent decisions while code retains control of valid actions and side effects.
English -
Agent 里不是每个判断都需要生成文本:Jev 把决策交给代码
TypeSafe Jev 用 Choice、Score 和 Noul 处理 Agent 的受约束决策,让模型负责模糊判断,代码继续掌握合法动作和副作用。
Chinese -
Claude merges Chat and Cowork to reduce mode choices
Claude combines Chat and Cowork in one conversation, routes capabilities automatically, and keeps task state and permissions visible.
English -
Claude 把 Chat 和 Cowork 合并后,Agent 产品开始减少模式选择
Claude 把 Chat 与 Cowork 合并到同一会话,把能力路由交给系统,同时保留任务状态和权限确认,给 Agent 产品一个具体 UX 边界。
Chinese -
Gemini Live: turnComplete no longer means the task is done
Gemini Live Extended Thinking separates conversation turns from background task lifecycles. Clients need interaction_status to track actual completion.
English -
Gemini Live 把推理放到后台:turnComplete 不再等于结束
Gemini Live Extended Thinking 把对话回合与后台任务生命周期拆开,客户端需要用 interaction_status 管理真正的完成状态。
Chinese -
What Tau solves by splitting an AI agent into three layers
Tau separates model adapters, the agent core, and the application so tools and frontends can work together without depending on each other.
English -
Connecting an agent loop to a frontend with events
Follow tool execution and repeated model calls, separate streamed deltas from final messages, and explore frontend state with a model-free Python demo.
English -
Herdr turns the terminal into an agent runtime
How Herdr manages existing coding-agent terminals with persistent sessions, blocked states, cross-machine control, and agent coordination.
English -
Herdr 不替换 Agent,它把终端做成运行时
拆解 Herdr 如何接管现有 Coding Agent 所在终端,提供持久会话、阻塞状态、跨机器控制和 Agent 协作,而不重写底层 Agent。
Chinese -
Munim Computer Use lets agents act on desktop controls
Munim Computer Use reads the accessibility tree and operates desktop controls by element ID, reducing reliance on fragile screenshot-coordinate automation.
English -
Munim Computer Use:让 Agent 按控件操作桌面
介绍 Munim Computer Use 如何先读取可访问性树,再按元素 ID 操作桌面控件,减少依赖截图坐标的脆弱自动化。
Chinese -
OpenAI agent workdays and shifting builder bottlenecks
OpenAI organization-level data suggests that more coding-agent use shifts bottlenecks to task decomposition, concurrency, harnesses, evaluation, and selection.
English -
OpenAI 研究组织跑到 3.1 Agent 工作日后,Builder 的瓶颈开始转移
OpenAI 的组织级数据说明 Coding Agent 使用规模上升后,瓶颈会转向任务拆分、并发调度、Harness、Eval 和结果选择。
Chinese -
GitHub Agentic Workflows:把 Agent 装进 GitHub Actions
介绍 GitHub Agentic Workflows 如何把需要判断的自动化放进 GitHub Actions,同时保留权限、输出、审批和安全边界。
Chinese -
GitHub Agentic Workflows: agents inside GitHub Actions
How GitHub Agentic Workflows puts judgment-based automation inside GitHub Actions while retaining permissions, controlled outputs, approval, and security.
English -
Vercel Eve Agent Framework
A source-backed review of Vercel Eve’s filesystem-first agent model, durable execution, tools, sandboxes, approvals, deployment, and Vercel platform tradeoffs.
English
No long-form articles match this language.
Reading list
News notes
- Chinese
- Chinese
- English
- Chinese
- English
- Chinese
No news notes match this language.
No articles match this language. Show all languages Clear all filters