Skip to content

#Agent

0 items today
7/30Thu
  1. Terminal-Bench · News62

    Terminal-Bench ships new Harbor features, turning the benchmark into a versioned asset that keeps getting updated

    The Terminal-Bench team has shipped a batch of new Harbor features that let datasets be released by version and let leaderboards migrate to new versions by reusing, re-evaluating, or rerunning trials. Tasks use semantic versioning: patch-level changes reuse old results as-is, validator changes only require re-evaluating saved artifacts, and only major changes that significantly alter the agent environment require a rerun. Dataset versions follow the highest version number among the tasks, and leaderboards use diffs to rerun only the tasks with major changes.

    Why it matters: The Terminal-Bench team maintains the benchmark like software, laying out concrete mechanisms for task semantic versioning and leaderboard upgrades that you can carry over to your own evaluation pipeline.

7/25Sat
  1. Cline · Blog79

    Cline 用递归自我改进让智能体自主把 Kimi K3 在 Terminal-Bench 2.1 提到 88.8%

    Cline 用一条提示词启动 17 小时连续运行的编码智能体，以 GPT-5.6-Sol 为 leader 模型，把 Kimi K3 在 Terminal-Bench 2.1 上的成绩从基线 69/89（77.5%，$79）提升到确认运行 79/89（88.8%，$49.8），超过 Moonshot 自报的 88.3%。

    Awaiting translation

    Why it matters: Cline 用一条提示词让智能体自主完成 17 小时爬山，把 Terminal-Bench 2.1 从 77.5% 提到 88.8%，可看具体修了哪些 harness 问题。

7/24Fri
  1. Lovable · Blog71

    Lovable 如何用 AI 黑客智能体集群对自己打夺旗赛

    Lovable 在内部搭建了一套进攻性安全程序，让 AI 智能体集群像人类攻击者一样探测系统入口，直到拿到可验证的漏洞证据。它用夺旗赛的思路做验证：把 flag 散布在基础设施和权限最高的产品界面中，不预埋任何漏洞，智能体取到 flag 就说明找到了真实入侵路径，而不是模型猜测。

    Awaiting translation

    Why it matters: Lovable 公开了用夺旗机制验证漏洞的内部攻防智能体编排方法，可迁移到自家安全测试流程。

7/22Wed
  1. Augment Code · Blog62

    What is loop engineering, and how are leading software engineering teams using it?

    Augment Code proposes loop engineering: designing agent loops that run from trigger to execution to validation to outcome, with agents handling the intermediate steps and humans stepping in only at checkpoints that require judgment. The article compares loop engineering with prompt engineering and context engineering as distinct layers, lays out five stages—trigger, execution, validation, outcome, and improvement—and describes four team-level loops already running in production: code review, ticket-to-PR, vulnerability remediation, and incident response.

    Why it matters: Augment Code breaks loop engineering into five stages—trigger, execution, validation, outcome, and improvement—and lays out four team-level loop patterns already running in production.

7/20Mon
  1. OpenAI Developer Blog · Codex71

    Codex Code Review now supports custom review rules in AGENTS.md

    OpenAI has added custom repository rules to Codex Code Review: you can put review guidelines in AGENTS.md, and Codex applies them during review and cites where each one came from in its findings. In OpenAI's own evaluation, the rule-guided version caught 98% of the required custom issues, versus 58.3% for the baseline. The guidance is to start with non-obvious invariants like compatibility requirements and data boundaries, put repo-level rules in the root directory and service-level rules in the corresponding directory, and leave formatting and mechanical checks to CI.

    Why it matters: OpenAI lays out the capabilities, the syntax, and the evaluation data for Codex Code Review custom rules, so you can judge how to bake your team's review experience into AGENTS.md.

7/15Wed
7/8Wed
  2. AI Hero · Skills Updates65

    AI Hero skills repo ships v1.1: adds /wayfinder, renames /to-spec and /to-tickets

    AI Hero's skills repo ships v1.1, renaming /to-prd to /to-spec, merging /to-plan and /to-issues into /to-tickets, and adding new Skills like /wayfinder, /research, and /prototype.

    Why it matters: The author walks through the full Skill flow from grilling to deployment and gives the migration commands for the renames, the merge, and the new /wayfinder—useful for anyone building an AI development workflow.

7/3Fri
  1. Lovable · Blog88

    花掉 8.5 万美元 token 后，我在 Lovable 扩展智能体编程的经验

    Lovable 一名工程师从今年 1 月到 6 月把个人 token 花费从每月约 600 美元推到 5 月的约 2.5 万美元、累计约 8.5 万美元，同时把每周合并 PR 数从 20-30 个提升到 150 个以上。

    Awaiting translation

    Why it matters: 作者公开了自己每月约 2.5 万美元 token 的智能体开发配置，包括风险分级、多智能体评审和上下文管理，可迁移到其他团队。

6/24Wed
  1. Andrej Karpathy60

    Anthropic 发布 Claude Tag，团队可在 Slack 中把 Claude 加为团队成员，让它访问指定频道和工具，通过 @ 它来委派任务。Karpathy 认为这是 LLM 交互界面的第三次重大改版：第一代是访问网站，第二代是下载到电脑的应用，第三代则是自带工具和组织级上下文、与人类团队并行工作的持久异步实体。

    Awaiting translation

    QuotedClaude@claudeai

    Introducing Claude Tag, a new way for teams to work with Claude. In Slack, Claude joins as a team member with access to the channels and tools you choose. Tag Claude in and delegate tasks to it while you focus on other work.

6/23Tue
  1. OpenAI Developer Blog · Codex65

    OpenAI 官方指南：如何用手机远程指挥 Codex 完成工程工作

    OpenAI 发布 Codex Remote 使用指南，介绍如何在 ChatGPT 移动端启动、指挥、审查和整理运行在开发机上的编码任务，核心思路是把手机当作控制平面而非终端。

    Awaiting translation

    Why it matters: OpenAI 官方梳理 ChatGPT 移动端 Remote 控制 Codex 的完整用法，涵盖 Queue 与 Steer、side chat、Plan 与 Goal 等关键决策点。

6/18Thu
  1. Terminal-Bench · News60

    Terminal-Bench 发布 Challenges 长周期智能体基准

    Terminal-Bench 发布 Challenges，一种长周期、高 token 消耗的单任务基准，要求智能体在无时间与资源限制下自主完成整个项目，首批开放三个挑战。

    Awaiting translation

    Why it matters: Terminal-Bench 官方推出长周期单任务基准，并公开三个挑战的实测失败模式，可供评估智能体长时自主能力时参考。

  2. Augment Code · Blog71

    Augment launches Project Builder on the Cosmos platform, taking large projects from design doc to merge

    Augment launches Project Builder on the Cosmos platform. This Cosmos expert turns a one-line feature description into a design doc grounded in the real codebase; after human review, it orchestrates worker agents to implement the work and drive it to merge.

    Why it matters: Augment has shared how Project Builder handles design review and orchestration, plus the code volume and launch timelines of three production projects—enough to judge whether design-first plus agent orchestration is workable.

6/15Mon
  1. Cline · Blog71

    用插件和 Hook 扩展 Cline 智能体循环

    Cline 官方博客介绍如何用插件和 Hook 给智能体循环加上确定性行为与护栏。插件是单个对象文件，可复用在同一份代码的 CLI、VS Code、JetBrains 和 SDK 上。

    Awaiting translation

    Why it matters: 原文给出 Cline 插件与 Hook 的完整代码示例，读者可据此为智能体循环加上日志记录和危险命令拦截。

6/10Wed
  1. Andrej Karpathy75

    Andrej Karpathy 评价 Claude Fable 5 发布，指出它与 Mythos 是同一底层模型，只是增加了安全防护，在几乎所有基准上以明显优势达到 SOTA。

    Awaiting translation

    QuotedClaude@claudeai

    Fable 5 is state-of-the-art on nearly all tested benchmarks, with exceptional performance in software engineering, knowledge work, scientific research, and vision. The longer and more complex the task, the larger Fable 5’s lead over our other models.

6/2Tue
  1. claude.dev · Anthropic Developer Blog82

    Claude Code Dynamic Workflows: Six Orchestration Patterns and Use Cases

    Anthropic has shipped dynamic workflows in Claude Code. Claude can write its own harness on the fly for a specific task, and these workflows can be shared and reused. Workflows orchestrate subagents through functions like agent(), parallel(), and pipeline(), and you can specify which model each agent uses and whether it runs in its own worktree. If a session is interrupted, resuming it picks up where it left off.

    Why it matters: The Anthropic team breaks down six orchestration patterns for dynamic workflows and where each one fits, and these patterns carry over to multi-agent task design.

5/26Tue
  1. Augment Code · Blog62

    Augment hands on-call triage over to Cosmos agents, cutting manual effort by 81%

    Augment wires the Incident Investigator expert from its internal Cosmos platform into Slack and PagerDuty. It automatically triages every alert and runs root-cause analysis, then suggests one of four actions: fix the code, roll back, upgrade, or just keep monitoring. Humans only review the RCA and make the call.

    Why it matters: Augment has shared the full playbook for putting Cosmos Expert on alert triage, along with a month of before-and-after data, so you can adapt it to your own on-call process.

5/21Thu
  1. Lovable · Blog74

    Lovable 给智能体加了吐槽工具，每天自动合并约 10 个修复

    Lovable 团队为自家智能体搭建了两个自动化闭环，用来持续减少用户卡住的情况。第一个是 Lovable Stack Overflow（LSO）知识库，在用户请求前由分类器、选择器和合成器判断是否注入解决方案，早期版本让卡住率下降 5%、发布率提升 2%。

    Awaiting translation

    Why it matters: Lovable 团队公开两个自动化闭环的落地细节，可借鉴如何用知识库和反馈工具降低用户卡住率。

5/18Mon
  1. Lovable · Blog62

    Lovable 上线 Skills，把重复指令变成可复用技能

    Lovable 上线 Skills 功能，把重复交代的工作方式写成可复用的 markdown 技能文件，在相关任务出现时按需加载。技能以文件夹形式组织，主文件 SKILL.md 含 name、description 和 instructions，description 是决定是否触发的唯一依据，支持文件只在主文件引用且确实需要时才加载。

    Awaiting translation

    Why it matters: 官方详解 Lovable Skills 的文件结构、触发机制与写法，并给出可对照的正反示例。

5/12Tue
  1. Augment Code · Blog60

    Augment Code 调研 219 位工程负责人：AI 原生开发中的信任与角色落差

    Augment Code 调研了 219 位工程负责人，发现其团队约 48% 的代码由 AI 生成，55% 担心团队对代码库失去共同理解，63% 表示工程师向管理者提出了技能相关性方面的担忧，在 201-1000 人规模的团队中这一比例升至 89%。

    Awaiting translation

    Why it matters: 219 位工程负责人的调研数据揭示了 AI 原生开发中代码评审、技能焦虑与角色定义之间的落差。

5/11Mon
5/9Sat
  1. OpenAI · Codex Cookbook72

    OpenAI brings persistent Goals to Codex

    Starting with Codex 0.128.0, OpenAI offers Goals, turning one-off prompts into persistent objectives within a thread. Codex keeps checking evidence such as tests, benchmarks, or deliverables to decide whether the goal is done.

    Why it matters: The official docs lay out where Goals fits, how to write its six elements, and the lifecycle commands, so you can tell when a persistent objective should replace a one-off prompt.

5/2Sat
5/1Fri
  1. Andrej Karpathy58

    Karpathy 在 Sequoia Ascent 2026 的炉边对话中提出，LLM 的意义不只是加速已有工作，并举了三个新场景：menugen 这类完全由 LLM 承担、无需传统代码的应用，用 .md skills 替代 .sh 安装脚本，以及处理非结构化知识的 LLM 知识库。

    Awaiting translation

    QuotedStephanie Zhan@stephzhan

    @karpathy and I are back! At @sequoia AI Ascent 2026. And a lot has changed. Last year, he coined “vibe coding”. This year, he’s never felt more behind as a programmer. The big shift: vibe coding raised the floor. Agentic engineering raises the ceiling. We talk about what it means to build seriously in the agent era. Not just moving faster. Building new things, with new tools, while preserving the parts that still require human taste, judgment, and understanding.

4/30Thu
  1. AI Hero · Skills Updates62

    AI Hero 更新 Skills：/ubiquitous-language 并入 /grill-with-docs

    AI Hero 的 skills 仓库更新，把 /ubiquitous-language 废弃并合并进新 Skill /grill-with-docs，输出从 ubiquitous-language.md 改为 context.md，并支持多个限界上下文各自维护共享语言。

    Awaiting translation

    Why it matters: 作者把 /ubiquitous-language 合并为 /grill-with-docs，并给出 ADR 触发条件与多限界上下文做法，可迁移到自己的 Skill 配置。

  2. Augment Code · Blog71

    Augment Code put Karpathy-style rules to the test: the coding agent didn’t write better code, but it was cheaper and faster

    In AGENTS.md, Augment Code front-loads roughly 2.5k characters of Karpathy-style coding rules, then runs 40 OpenClaw PRs through Auggie, Claude Code, and Codex for comparison.

    Why it matters: A head-to-head test of three coding agents on the same set of PRs shows that prompt constraints mainly cut costs rather than improve quality, and it also surfaces differences between the harnesses.

4/22Wed
  1. Augment Code · Blog88

    Augment Code Tests AGENTS.md: A Good File Is Like a Model Upgrade, a Bad One Is Worse Than Nothing

    Augment Code pulled dozens of AGENTS.md files from its own monorepo and used its internal benchmark suite AuggieBench to compare how the same tasks performed with and without the file. The best files delivered a quality boost equivalent to upgrading from Haiku to Opus, while the worst made the output worse than having no AGENTS.md at all.

    Why it matters: Augment Code used internal benchmarks to quantify how much the different ways of writing AGENTS.md actually differ, so readers can adjust their own repo's documentation structure accordingly.

4/10Fri
  1. claude.dev · Anthropic Developer Blog74

    Anthropic 工程师谈 Claude Code 的工具设计：如何像智能体一样思考

    Anthropic 的 Thariq Shihipar 复盘了 Claude Code 工具设计中的取舍，核心主张是工具要贴合模型自身能力，而判断能力边界只能靠观察输出和反复实验。

    Awaiting translation

    Why it matters: Anthropic 工程师复盘 Claude Code 工具设计的取舍，给出可迁移到自建智能体的判断方法。

3/9Mon
  1. OpenAI Developer Blog · Codex87

    OpenAI 如何用 Skills 加速 Agents SDK 仓库维护

    OpenAI 用 Codex 配合仓库内的 Skills、AGENTS.md 和 GitHub Actions 维护 Agents SDK 仓库，把验证、发布准备、示例集成测试和 PR 评审变成可重复流程。

    Awaiting translation

    Why it matters: OpenAI 官方公开了用 Skills、AGENTS.md 和 GitHub Action 维护 Agents SDK 仓库的完整配置，可迁移到其他开源项目。

2/23Mon
  1. OpenAI Developer Blog · Codex72

    用 Codex 跑 25 小时长时程任务：一份可复用的项目记忆文件栈

    OpenAI 用 GPT-5.3-Codex 在 Extra High 推理档下从空仓库连续运行约 25 小时、消耗约 13M token、生成约 3 万行代码，做出一个可测试的设计工具。

    Awaiting translation

    Why it matters: 作者用 25 小时、13M token 的实测展示长时程智能体如何靠持久化项目记忆和逐里程碑验证保持不跑偏。

2/3Tue
  1. Vercel · v0 Blog60

    Vercel 发布新版 v0，从生成演示转向生产级应用

    Vercel 发布新版 v0，将其定位从生成演示转向生产级应用和智能体。新版本基于沙箱运行时，可导入任意 GitHub 仓库并自动拉取 Vercel 上的环境变量和配置；新增 Git 面板，让非工程成员也能为每个对话建分支、向 main 提 PR 并在合并后部署；同时提供与 Snowflake 和 AWS 数据库的安全集成，以及默认开启的部署保护和访问控制。

    Awaiting translation

    Why it matters: v0 从生成演示转向生产级应用，给出导入 GitHub 仓库、Git 面板和数据库集成等具体能力变化。

1/22Thu
1/11Sun
  1. OpenAI Developer Blog · Codex71

    Skyscanner 如何用 JetBrains MCP 增强 Codex CLI

    Skyscanner 工程师把 OpenAI 的 Codex CLI 接入 JetBrains IDE 的 MCP server，让 Codex 能调用 IDE 的 get_file_problems 检查文件错误、执行预设的 run configurations 跑测试和 lint。

    Awaiting translation

    Why it matters: Skyscanner 工程师把 Codex CLI 接入 JetBrains MCP，让 AI 直接读取 IDE 报错并跑测试，读者可借鉴这套反馈闭环。

11/19Wed
  1. OpenAI · Codex Cookbook67

    How to modernize a legacy codebase in phases with Codex CLI

    In the Codex Cookbook, OpenAI lays out a complete workflow for modernizing a legacy codebase with Codex CLI, using a COBOL portfolio system as the example and moving through five phases built around an ExecPlan design document.

    Why it matters: Using a COBOL portfolio system as the example, it offers reusable documents and a validation workflow for modernizing legacy code in phases with Codex CLI.

11/7Fri
  1. Terminal-Bench · News62

    Terminal-Bench ships version 2.0 and an optimized Harbor evaluation package

    Terminal-Bench has released version 2.0 and the Harbor package. The former is a more rigorously validated, harder benchmark for evaluating agents; the latter is for evaluating and optimizing agents. Harbor rewrites Terminal-Bench's test harness, supports deploying containers in the cloud, provides rollout interfaces for RL and SFT, and works with any agent you can put in a container.

    Why it matters: Terminal-Bench 2.0 and Harbor are released together, so readers can see how the agent evaluation benchmark is validated and how to scale it in the cloud.

8/29Fri
  1. OpenAI · Codex Cookbook74

    在 GitLab CI/CD 中用 Codex CLI 自动做代码质量检查与安全修复

    OpenAI Codex Cookbook 给出把 Codex CLI 接入 GitLab CI/CD 的完整做法，用于生成 CodeClimate JSON 代码质量报告、把 SAST 结果整理成 security_priority.md，并让 Codex 输出可 git apply 的补丁。

    Awaiting translation

    Why it matters: 官方 Cookbook 给出把 Codex CLI 接入 GitLab CI 的完整配置，含提示词约束、JSON 标记提取与 diff 校验，可直接照搬。

7/15Tue
6/25Wed
5/19Mon
  1. Terminal-Bench · News62

    Terminal-Bench 发布首个终端智能体评测基准

    Terminal-Bench 发布首个版本，用于量化 AI 智能体在终端中执行复杂任务的能力，首发数据集 Terminal-Bench-Core-v0 包含 80 个手工编写并人工验证的任务，每个任务配有独立 Docker 环境、人工验证的解法与测试用例。

    Awaiting translation

    Why it matters: Terminal-Bench 给出 80 个带 Docker 环境和测试用例的终端任务，可用来横向比较不同智能体在命令行中的实际表现。