2026
20 篇文章把測試證據放進開發流程:Cognition 用 GPT‑6 Astra 讓 Devin 自己驗證成果
Cognition 將 GPT‑6 Astra 整合進 Devin,讓代理在回報程式碼變更時附上測試錄影與涵蓋範圍報告,減少工程師手動審查。
閱讀文章 ↗把 diff、終端機與瀏覽器收進同一個視窗:Copilot app 對審核流程的實際改變
GitHub 把 diff、終端機與瀏覽器面板整合進 Copilot app,讓審核 agent 改動的三個問題在同一處回答。
閱讀文章 ↗Oracle 劃紅線:AI 生成的內容不得進入 OpenJDK
OpenJDK 發布生成式 AI 臨時政策:貢獻不得包含 LLM 或擴散模型生成的任何內容,理由是審查負擔、安全與 IP 風險;GitHub PR 也將加上合規勾選框。
閱讀文章 ↗Claude 5 世代上下文工程新規則:系統提示砍八成
Anthropic 於 7 月 24 日發表 Claude 5 世代模型的上下文工程指南:Claude Code 系統提示砍掉逾 80%,六組新舊做法對照,並更新 CLAUDE.md、Skills 與 /doctor 的建議。
閱讀文章 ↗從 Nextdoor 看 Codex:工程師不再只是寫程式,而是打造產品
Nextdoor 工程團隊如何使用 OpenAI Codex 將工程師從「迭代提示」轉向「結果工程」,讓單一工程師能端到端擁有產品體驗,並將瓶頸從工程轉移到策略。
閱讀文章 ↗Lovable 年化營收突破 5 億美元,每週新增百萬專案
2026 年 6 月,Lovable 向 TechCrunch 透露年化營收突破 5 億美元,累積專案逾 5,000 萬個、每週新增百萬。本文看 vibe coding 的成長節奏、非技術使用者樣貌,與 SaaS 末日論的未答之問。
閱讀文章 ↗Miasma 蠕蟲再襲 Microsoft:73 個儲存庫停用,AI 編碼代理成靶
被劫持的帳號六月五日把惡意提交推入 Azure durabletask 儲存庫,植入 .claude、.gemini 與 .cursor 設定檔,開檔即執行竊憑證 payload;GitHub 在 105 秒內停用 73 個儲存庫,官方 functions-action 工作流應聲斷裂。
閱讀文章 ↗Visa 投資 Replit:讓 AI 開發平台原生內建金流
Visa 於 5 月 28 日宣布投資 Replit(金額未公開),規劃整合 Visa Intelligent Commerce 與 Trusted Agent Protocol,讓平台上的 App 與 AI 代理內建收款能力;Replit 同步開放 20 萬美元內的自助企業方案。
閱讀文章 ↗Figma Make 直接編輯生產程式碼庫:設計工具跨進工程腹地
2026 年 5 月 28 日,Figma 宣布 Figma Make 可透過桌面版 App 連上生產或 sandbox 儲存庫,成為可直接編輯真實軟體的視覺介面,並新增精確調整面板。設計到程式碼的邊界正在消失,本文解析功能細節與採用前的務實建議。
閱讀文章 ↗Cognition 募資 10 億美元:估值八個月翻倍至 260 億
2026 年 5 月 27 日,AI 編程新創 Cognition 宣布募資超過 10 億美元,投後估值 260 億美元,八個月內翻倍。年化營收達 4.92 億美元,Devin 企業用量連六個月月增 50%,市場押注獨立編程工具能撐過模型廠夾擊。
閱讀文章 ↗維珍航空如何用 Codex 在聖誕旺季前安全上線新 App
維珍航空利用 OpenAI Codex 重寫手機 App,在聖誕旅遊旺季前上線,達成零 P1 缺陷。本文整理他們在測試覆蓋率、遺留程式碼重構和內部工具開發上的具體做法,以及工程速度超越流程後的新挑戰。
閱讀文章 ↗Cursor 年化營收突破 30 億美元:企業客戶撐起成長,SpaceX 交易在即
Bloomberg 於 2026 年 5 月 21 日報導,Cursor 年化營收達 30 億美元,逾 3,000 家客戶年付至少 10 萬美元,成長引擎轉向企業合約;同時 SpaceX 收購交易成形,AI 編碼市場進入整併期。
閱讀文章 ↗從「打得更快」到「想得更深」:Sea 如何用 Codex 重塑工程團隊
Sea 的 CPO David Chen 分享公司全面導入 Codex 的經驗:87% 週活躍率、從 autocomplete 到 agentic workflow 的轉變,以及工程師如何轉型為系統編排者。
閱讀文章 ↗GitHub Copilot 改用量計費:AI Credits 接棒 premium requests
GitHub 宣布 2026 年 6 月 1 日起所有 Copilot 方案改為用量計費:premium requests 退場,改以 AI Credits 按 token 計費,1 點 0.01 美元。方案價格不變,但聊天與多小時 agent 工作階段從此分開計價,本文解析費率與過渡規則。
閱讀文章 ↗Cursor 洽募 20 億美元:估值半年再翻倍至 500 億
消息人士透露,AI 編碼新創 Cursor 洽談以 500 億美元投前估值募集至少 20 億美元,Thrive、a16z、Battery 與 Nvidia 可能參與。公司二月年化營收已達 20 億美元,並預測年底突破 60 億。
閱讀文章 ↗Codex 更新:從寫 Code 到幫你操作電腦
OpenAI 在 2026 年 4 月 16 日釋出 Codex 重大更新,加入背景電腦操作、排程任務、記憶功能,並擴充外掛生態。本文整理這些變化的實際用途與限制。
閱讀文章 ↗Qodo 2.1 推出 Rule System:治好 coding agent 的團隊規範失憶症
2026 年 2 月 17 日,AI 程式碼審查平台 Qodo 發布 2.1 版,推出首個持續學習的 Rule System:自動從過往 PR 萃取團隊規範、由專責代理強制執行並量化違規,VentureBeat 報導精準度提升 11%,為 coding agent 補上治理層。
閱讀文章 ↗Spotify:頂尖工程師 12 月起沒再寫過一行程式碼
Spotify 共同執行長 Söderström 在 Q4 法說會表示,最佳工程師自 2025 年 12 月起沒再手寫一行程式碼,改為透過內部工具 Honk 監督 Claude Code 產出。本文拆解這套通勤就能合併上線的工作流、一年 50 個功能的出貨節奏,以及行銷話術與現實的距離。
閱讀文章 ↗MiniMax 開源 M2.5 與 Lightning:SWE-Bench 80.2%,十分之一價格逼近 Opus 4.6
2026 年 2 月 12 日 MiniMax 發布 M2.5 與 M2.5-Lightning 並開源 229B 權重:SWE-Bench Verified 80.2%,解題速度與 Claude Opus 4.6 持平但成本約十分之一,輸出單價最低每百萬 token 1.2 美元。
閱讀文章 ↗Mistral Vibe 2.0 登場:終端機編碼代理轉為付費,進攻企業市場
2026 年 1 月 27 日,Mistral 把終端機編碼代理 Vibe 升級至 2.0:新增子代理、澄清提問、技能指令與代理模式,綁進 Le Chat Pro 與 Team 付費方案,Devstral 2 同步轉為付費 API。
閱讀文章 ↗
2025
2 篇文章Mistral 推出 Mistral Code 進攻企業AI編程
2025年6月4日,法國 Mistral AI 發布企業版 AI 編程助手 Mistral Code,整合 Codestral、Devstral 等四款模型,支援 JetBrains 與 VS Code,可私有化部署並在私有程式碼庫上精調,直接對陣 GitHub Copilot 與 Cursor。
閱讀文章 ↗Windsurf 稱 Anthropic 緊縮 Claude 直接存取
2025年6月3日,AI 編程工具 Windsurf 執行長 Varun Mohan 表示,Anthropic 以不到五天的通知刪減其 Claude 3.x 模型的第一方容量,公司被迫轉向第三方運算,突顯模型供應商與應用層之間的權力失衡。
閱讀文章 ↗
2026
21 ARTICLESDevin Now Shows Its Work: What Self-Testing Agents Change for Review
Cognition uses GPT-6 Astra so Devin tests its own changes and returns evidence, not just a diff.
READ POST ↗Copilot's Diff, Terminal, and Browser Panels: A Review Loop You Can Trust
GitHub's Copilot app puts diff review, terminal runs, and browser preview in one window to close the agent coding loop.
READ POST ↗Oracle Bans AI-Generated Code from OpenJDK Contributions
OpenJDK's interim policy bars LLM- or diffusion-generated content from contributions, citing reviewer burden, security, and IP risk. Rust took a narrower path the same week.
READ POST ↗Anthropic's New Context Engineering Rules for Claude 5
Anthropic cut over 80% of Claude Code's system prompt for Claude 5 models with no measurable eval loss, and rewrote its context engineering guidance.
READ POST ↗From Nextdoor to Codex: How Outcome Engineering Is Redefining the Role of the Engineer
Nextdoor's engineering head explains how Codex shifts engineers from prompting agents to outcome engineering, compressing timelines and moving bottlenecks to strategy.
READ POST ↗Lovable Passes $500M Annualized Revenue, 1M Projects a Week
Lovable told TechCrunch it passed $500M annualized revenue, with 50M+ projects built and about 1M new projects a week. Inside the vibe-coding boom and its open questions.
READ POST ↗Miasma Worm Hits Microsoft Repos, Targeting AI Coding Agents
A hijacked account pushed a malicious commit into Azure's durabletask repo, planting files that run a credential stealer when Claude Code or Cursor opens it. 73 repos went dark.
READ POST ↗Visa Invests in Replit to Build Payments Into AI Coding
Visa invested an undisclosed amount in Replit to embed its payment stack, letting apps and AI agents built on the platform accept payments natively.
READ POST ↗Figma Make Now Edits Your Production Codebase
Figma Make can now edit production codebases: connect a repo via the desktop app and adjust real software visually. The design-to-code boundary is dissolving fast.
READ POST ↗AI Coding Startup Cognition Raises $1B at $26B Valuation
Cognition raised over $1B at a $26B post-money valuation, double its September price, on $492M annualized revenue and Devin enterprise usage up 50% month over month.
READ POST ↗How Virgin Atlantic Used Codex to Ship a New App Before Christmas—Without the Bugs
Virgin Atlantic used OpenAI's Codex to ship a revamped app on time with zero P1 defects, refactor legacy code in hours, and let analysts build their own tools.
READ POST ↗Cursor Passes $3B Annualized Revenue as SpaceX Deal Looms
Bloomberg reports Cursor hit a $3B annualized sales rate in May 2026, with 3,000+ customers paying $100K+ each, as its SpaceX deal looms and the AI coding market consolidates.
READ POST ↗From Typing Faster to Thinking Better: How Sea Uses Codex to Reshape Engineering Teams
Sea's David Chen on rolling out Codex across the org: 87% weekly active users, AI agents in CI/CD, and the shift to system orchestration.
READ POST ↗GitHub Copilot Moves to Usage-Based Billing With AI Credits
GitHub moves all Copilot plans to usage-based billing on June 1, replacing premium requests with token-billed AI Credits. Plan prices hold; what a credit buys changes.
READ POST ↗Cursor in Talks to Raise $2B at a $50B Valuation
Cursor is reportedly raising $2B+ at a $50B pre-money valuation, nearly double November's $29.3B, with Thrive, a16z, Battery and Nvidia involved. February ARR already hit $2B.
READ POST ↗Codex Update: From Writing Code to Operating Your Computer
OpenAI's Codex update adds background computer use, an in-app browser, memory, automations, and 90+ plugins, making it a more proactive partner across the software development…
READ POST ↗Cursor 3 Turns the IDE into an Agent Workspace Built From Scratch
Cursor 3 is a unified workspace built from scratch around agents: one sidebar for every local and cloud agent, two-way handoff, built-in diffs and browser, and a plugin marketplace.
READ POST ↗Qodo 2.1 Adds a Rule System to Cure Coding Agent Amnesia
Qodo 2.1, out February 17, 2026, adds a continuous-learning Rule System to AI code review: auto-discovered team standards, deterministic enforcement, violation analytics, and an 11% precision boost.
READ POST ↗Spotify's Top Developers No Longer Write Code, Thanks to AI
Spotify says its best developers haven't written code since December. Its Honk tool lets engineers direct Claude Code from Slack on a phone and merge to production mid-commute.
READ POST ↗MiniMax M2.5: Open Coding Weights at a Tenth of Opus Cost
MiniMax open-sources M2.5 and M2.5-Lightning: 80.2% SWE-Bench Verified, Opus-4.6-class task times at roughly a tenth of the cost, 229B parameters under modified MIT on Hugging Face.
READ POST ↗Mistral Vibe 2.0: Terminal Coding Agent Goes Paid
Mistral's terminal coding agent Vibe 2.0 adds subagents, clarifying questions, skills, and modes — now a paid product, with Devstral 2 moving to a paid API at $0.40 in / $2.00 out per million tokens.
READ POST ↗
2025
2 ARTICLESMistral Code brings agentic coding to enterprises
On June 4, 2025, Mistral AI launched Mistral Code, an enterprise coding assistant bundling four models for JetBrains and VS Code, with self-hosting and private fine-tuning for Copilot-class rivals.
READ POST ↗Windsurf says Anthropic cut its direct Claude access
On June 3, 2025, Windsurf said Anthropic cut its first-party Claude 3.x capacity with under five days notice, forcing third-party compute — a case study in model providers power over app builders.
READ POST ↗