AI 編程

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Elon Musk’s mission to unify his sprawling tech empire continues apace, with the news that X, Grok, and Cursor are The post The X Subscription bundles Cursor with Grok and X Premium. But Claude now costs extra. appeared first on The New Stack.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：In my previous Radar article, “Architectural Guardrails for AI-Generated Code,” I argued that AI coding agents need a layer that can hold architectural decisions in a structured corpus, retrieve the relevant ones, put them into the agent’s context before it writes code, and enforce explicit constraints with reproducible checks. Testing that model exposed two distinctions […]

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Learn how to add custom instructions and skills to your repository, use custom agents, and connect MCP servers like Playwright. The post GitHub Copilot app for Beginners: How to teach Copilot about your codebase appeared first on The GitHub Blog.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：My Decoder guest today is Hayden Field, The Verge’s senior AI reporter, and we’re discussing the new wave of consumer-friendly AI agents. If you’ve been paying attention to this space, you know AI enthusiasts have been using agents for a minute now — homebrew OpenClaw setups led to a surge in Mac Mini sales earlier this year. But the launch of Meta’s Muse, OpenAI’s Dots, and xAI’s Grok bot has brought easy to use agents to millions. Muse and Dots have had the highest-profile product launches, and they’re fascinating to pit against each other. Both Meta and OpenAI have decided to pitch these agents to mainstream users and businesses in the form of cute, animated mascots. Verge subscribers, don’t forget you get exclusive access to ad-free Decoder wherever you get…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯： I've always been kind of into computers since I was young. And then when film started to move from analog film to digital, I became more interested in that aspect of it. And the visual effects workflow for many years has included machine learning. So I can write like pretty shitty Python scripts and stuff like that because with convolutional neural networks, which were the sort of precursors to what the transformer can do, which is just much more computation simultaneously, you would do things like look at what's called a tensor, which is just the numerical translation of a visual image in numbers — like the batch number, the frame number, the red, green, and blue values of each pixel in each frame. And a tensor, you use a convolutional neural network to ident…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：At today's Windows and Surface event, Microsoft showed off an upgrade to its Copilot AI system that will give it access to local files on your PC and the ability to take actions across the OS. It's part of an idea Microsoft is calling "Hybrid Intelligence," where apps and tools rely on a mix of local and cloud AI models to accomplish tasks efficiently. To show off how Hybrid Intelligence works, Jacob Andreou, Microsoft's EVP of Copilot, walked through a video demo on stage asking Microsoft's Autopilot tool to help with filing taxes. Andreou told the AI agent that he got an email from his accountant and asked Autopilot to get her what she … Read the full story at The Verge.

Google DeepMind 推出 EmbeddingGemma 2，將文本、程式碼、影像、影片和音訊對映到同一個 768 維向量空間。該模型擁有 740M 引數、8K token 上下文視窗，並以 Apache 2.0 許可開放權重，面向端側搜尋、分類和隱私優先的 RAG。權重已在 Hugging Face 與 Kaggle 上線，同時提供 Ollama、llama.cpp GGUF 和 LiteRT 版本，可立即部署。

Review 是 Product Hunt 上的一款產品，主打在自己的機器上、用自己的 AI 完成程式碼審查。現有介紹非常簡短，僅有 Discussion 與 Link 兩個入口。

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Most AI coding demos stop at task managers, weather apps, or simple chatbots. For this project, we take on something more demanding: building an enterprise customer-support platform that can investigate complaints, retrieve relevant policies, recommend resolutions, and keep risky actions behind human approval. This gives us a practical way to test Claude Fable 5.1 as […] The post Building an Enterprise AI Customer Support Platform with Claude Fable 5.1 and Claude Code appeared first on Analytics Vidhya.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：The revamp transforms Copilot from a simple AI assistant into a content workspace, providing knowledge workers with advanced developer tools.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Today, I’m talking with Mike Cannon-Brookes, who is cofounder and CEO of Atlassian. Atlassian is one of those companies that every other company runs on — it makes important platform tools like Jira and Trello that allow people to organize and manage big teams, create shared databases of company information, and generally allow work to happen. As you’ll hear Mike say, all of Atlassian’s products are actually different expressions of a single core platform, which really shapes how Atlassian itself is structured and how those products are built. All of this means Atlassian is also right in the middle of the way AI is changing how all these companies work — AI tools might be able to look at all the different tools and systems you have and just read them for you, m…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：We read the contracts behind GitHub Copilot, AWS Kiro, Cursor, Devin and Windsurf. Copilot and Kiro offer uncapped indemnity on generated code. Cognition's standard terms exclude outputs entirely. Here is how 500 seats compare on legal exposure, prompt storage, audit logs and true cost. The post AI Coding Agents for Enterprise: IP Indemnity, Data Residency and 500-Seat Cost Compared appeared first on MarkTechPost.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Describe the interface you need in plain English, then let the agent build a live surface you can both use and update—so you spend less time adapting to tools and more time getting work done. The post GitHub Copilot app for Beginners: How to build custom workflows with canvases appeared first on The GitHub Blog.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Misconfiguring Turnstile by skipping backend validation leaves sites exposed to bots. Turnstile Spin fixes incomplete setups by using your preferred AI coding agent to wire up server-side verification.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：After teasing its new Copilot "super app" last month, Microsoft is officially unveiling it today. The redesigned Copilot app bundles three AI capabilities into a single interface of chat, coding, and agents. As part of the launch, Microsoft is also rebranding Scout, the AI personal assistant it unveiled at Build earlier this year, as Autopilot. This new Copilot app will have three tabs for Home, Code, and Autopilot, with Home combining Copilot Chat and Cowork together. It's the default landing experience for Copilot users, and Microsoft is also planning to include a Today feature inside it that works as personalized dashboard for important … Read the full story at The Verge.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：The neocloud vendor provides AI agents with access to data from its infrastructure management platform, helping developers troubleshoot slow or underperforming AI workloads.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：We all know that producing code is easier than ever thanks to the abundance of AI coding tools and agents. The post Cursor acquired Firetiger. A month later, Cursor launched a bot that tracks code changes through to production. appeared first on The New Stack.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：How we rebuilt the diff surface in the GitHub Copilot app to open a million-line pull request with hundreds of inline review comments. The post Rendering huge pull requests in the GitHub Copilot app appeared first on The GitHub Blog.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Pair OpenCode, an open-source terminal-native AI coding agent, with open weight models on Amazon Bedrock to get a secure, flexible, pay-per-use coding assistant. Learn how to configure multi-model workflows, match the right model to each task, and keep your data in your own AWS account with no infrastructure to manage.

Jev State 是在 Product Hunt 上亮相的一款工具，主打把與 AI 的對話內容轉化為測試用例，並進一步生成可執行的程式碼。目前官方只給出了一句功能描述，具體工作流、支援的框架與生成程式碼的可用性尚未公開。

JetBrains 正式推出 JetBrains Air，將其定位為面向智慧體軟體開發的開放產品體系，覆蓋 IDE 內體驗、團隊協作與企業治理。該體系整合了 Air 桌面環境、Junie CLI、JetBrains Central 和 AI for Teams，同時 CEO Kirill Skrygan 強調 IDE 仍將是審查、驗證與交付程式碼的核心場所。

Databricks 釋出 Genie One MCP，把 Genie Ontology 的受治理業務上下文透過 MCP 開放給 ChatGPT、Claude、Microsoft Copilot 以及各類編碼智慧體，讓它們在獲批定義、可信資料關係和使用者許可權約束下回答業務問題。

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Liberal MP speaks of AI’s shortcomings as cyber chief tells inquiry the tech is needed to fend off ‘highly capable malicious cyber actors’ Get our new political email, free app or daily news podcast When a man with a terminal illness wrote to his local MP Andrew Hastie, telling him he planned on ending his own life with voluntary assisted dying, Microsoft Copilot suggested Hastie reply with “congratulations!”, “great to hear from you” or “that is wonderful news!”. Hastie shared the episode at a parliamentary inquiry on Friday to underline the shortcomings of the American-run software as he called for AI run by Australians. Continue reading...

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Building an AI prototype is easy, but operating autonomous agents at scale requires production-grade tooling. Salesforce Agentforce bridges the gap from "vibe coding" to enterprise reliability by combining synthetic stress-testing, real-time optimization, dynamic agentic UIs, and deterministic guardrails—as proven by Southwest Airlines' 7x ROI. The post Salesforce Agentforce: Bridging the Enterprise AI Gap from ‘Vibe Coding’ to Battle-Tested Orchestration appeared first on MarkTechPost.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：A rewrite this size wasn't affordable before agents. Here's what porting the Copilot agent runtime to 800,000 lines of production Rust actually took. The post Migrating the GitHub Copilot runtime to Rust, using Copilot appeared first on The GitHub Blog.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.16346v1 Announce Type: new Abstract: This paper presents Auto-HSI, a method for generating personalized human-swarm interaction (HSI) interfaces on demand. The objective is to enable untrained operators to use natural language descriptions and gesture demonstrations to explain how they want the robots to collectively behave in response to their gestures. Based on these inputs, the code should automatically be generated for personalized state machines that will control the robots as desired, in response to the desired gesture inputs. In the developed Auto-HSI prototype, the generated code produces a personalized interface for centralized control using one- and two-handed gestures, enabling a user to teleoperate the robots' motion, formation shape, and…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：On 25 August, OpenAI fully unveiled Jalapeño, the company’s debut AI accelerator chip. Jalapeño delivers up to 13.4 petaflops of 4-bit compute and accesses 232 gigabytes of the most advanced memory available, linking to it at a blazing 15.4 terabytes per second. Benchmarks cited by OpenAI show that Jalapeño can reduce end-to-end latency (the time between prompt to last token) by up to 3.6x when compared to Nvidia’s GB300—a chip the company currently relies on—and do so while consuming less power. Whether these figures translate into real-world gains once Jalapeño enters widespread service in OpenAI’s inference fleet remains to be seen, but performance is only half the story. The other half is how the chip was designed—a process which, as you might expect, was a…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Cognition, the company behind the Devin coding agent, has released SWE-2, its most capable coding model to date. SWE-2 is post-trained with reinforcement learning from Kimi K3, Moonshot AI’s 2.8T-parameter open model. Cognition reports a score of 50.0% on FrontierCode 1.1 Main, within 1 point of Fable 5.1 at 64% lower cost. It is also […] The post Cognition Releases SWE-2: A Kimi K3 Post-Trained Coding Model That Matches Fable 5.1 on FrontierCode at 64% Lower Cost appeared first on MarkTechPost.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：GPT‑6 Astra improves Devin’s ability to test software and show that it works, with the goal of helping engineers review less code and ship more.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Discussion | Link

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Checking agent-generated code usually means hopping between tabs. Learn how to view diffs, run terminal commands, and preview web apps side by side in the GitHub Copilot app. The post GitHub Copilot app for Beginners: Using the diff, terminal, and browser appeared first on The GitHub Blog.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Google has open-sourced Mantis, a stack-agnostic toolkit of security review skills for AI coding agents. It runs the full vulnerability lifecycle: sweep the code, filter false positives, reproduce the bug in a sandbox, patch it, re-attack the patch, then score the risk. Apache 2.0, and documented as demonstration-only. The post Google Open-Sources Mantis: A Modular Skills Toolkit That Lets Coding Agents Find, Reproduce and Patch Vulnerabilities appeared first on MarkTechPost.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：AI models now power all manner of agents, from coding assistants that write and debug software to customer service systems The post Claude did best on a new benchmark for agents that build agents. It still passed fewer than a quarter of the tests. appeared first on The New Stack.

微軟Edge團隊承認，AI輔助編碼讓瀏覽器擴充套件的提交量激增，使得審查管道承受額外壓力。為應對這一局面，微軟將自動化重複性驗證檢查，並宣稱不會降低審查標準和安全性，還計劃每15天更新一次“精選”徽章。此前，微軟Exchange團隊也因AI發現過多bug而推遲了累積更新。

Catenary 是一款面向 AI 程式設計代理的空間畫布 IDE，將程式碼與 AI 工作流視覺化地組織在無限畫布上。產品目前透過 Product Hunt 釋出並設有討論區。

本文提出了Harbor Adapters，一個統一的智慧體基準評測基礎設施，可將80多個基準適配到任意智慧體上；透過程式碼審查與對比實驗驗證後，研究團隊在54個基準上對8個模型進行了大規模評測，並配合Terminus-2與3種原生評測框架執行。進一步，團隊推出了Harbor-Index，這是從適配基準中提煉出的精選後設資料集，包含跨越29個基準的82個困難、多樣且高質量的任務。即使最強配置（GPT-5.5 with Codex）的透過率也只有28.0%，能夠以可負擔的成本保留大規模智慧體評測的挑戰性與覆蓋面。相關介面卡、結果、分析和資料集均已開源。

Project HydraFusion 是 GitHub 釋出的研究預覽，它不再將模型選擇視為一次性設定，而是針對每個請求構建並動態編排一個執行工作流，可在不同提供商的模型間進行起草、批判、升級等操作。目前僅在 GitHub Copilot CLI 中以研究預覽形式提供，並按實際呼叫的各模型標準令牌費率計費。

Coder釋出Coder Agent Relay服務，以SpaceXAI為首個合作伙伴，讓受監管行業的企業可以自託管執行編碼智慧體，同時由Cursor在雲端負責推理和規劃。Coder CEO指出，真正的障礙不是token花銷，而是技術採用不均衡和部署架構不匹配。該服務目前處於私有預覽階段。

GitWarren 是一款面向開發者的工具，讓開發者在提交程式碼變更之前，透過自己的編碼智慧體對程式碼進行審查，以便提前發現並改進問題。

資料轉換是將多個來源的原始資料轉化為標準化、高質量資料集的過程，使其適合儲存、分析和決策。本文介紹資料轉換的重要性、與ETL的關係、常見轉換型別、效能最佳化方法，以及批處理/流處理、本地/雲、開源/商業、無程式碼/低程式碼等工具選型維度。

瞭解如何在 GitHub Copilot 應用中並行執行多個代理，體驗這種從感到混亂到掌控全域性的轉變。每個代理會話獨立執行，互不干擾，讓你在更短時間內完成更多工。

這篇論文提出信念校準最佳化（BCO），讓編碼式最佳化代理將隱性的環境信念寫為持續更新的上下文文件，作為可複用的顯式世界模型。在記憶問答、工具使用問答、程式碼型應用代理和終端代理等五組基準上，BCO較僅缺少該模組的對照方法獲得更高訓練透過率；該優勢在未參與候選選擇的保留集上依然成立。後續換用不同基礎模型及離線內容消融進一步說明，收益源自文件攜帶的資訊內容。

Gemini 3.8 Flash 被定位為迄今最智慧的實用型模型，專注於程式設計與智慧體場景，兼具日常部署的可靠性與更強的程式碼和工具呼叫能力。

Sidebranch 是一款簡單的視覺化差異對比工具，基於 Git 工作流，幫助開發者更直觀地檢視程式碼分支與提交之間的變化。

本文介紹如何使用 Amazon Bedrock AgentCore 構建自動化架構文件流水線。全球銀行間經紀商透過 AgentCore、Amazon Bedrock Knowledge Bases、AWS CodePipeline 等 AWS 服務，自動分析 .NET 程式碼庫、生成並校驗 Mermaid/UML 架構圖、存入 S3 並支援語義檢索，實現持續更新的可搜尋架構文件，生產可靠性約 95%，自 2026 年第一季度投入執行。

GitHub 部落格介紹了 Copilot 降低 AI 編碼成本的四個實踐：不要只看單次工具呼叫的 token 數，而應從完整任務出發。透過選擇性壓縮噪音輸出、刪除不再使用的行號格式、用行為測試保護提示詞壓縮、以及批次直接交付後臺完成結果，團隊在離線/線上實驗中讓推理成本或 token 用量下降約 1–5%，且未出現質量回退。

Paint.NET 作者 Rick Brewster 透露，為了讓 Paint.NET 在 WINE 上執行，他們使用 AI 工具 Claude 從零開始逆向工程重寫了 Direct2D。這個 18 萬行的程式碼庫被戲稱為“vibe coding”產物，未經全面審查，但 Claude 的逆向工程能力令人印象深刻，同時也需要大量人工監督。

Anthropic 推出 Claude Fable 5.1，內建文本水印，但該水印在程式碼等低熵場景中效果有限，且新 API 賬戶的思維塊保留受限，給開發者帶來新的權衡。

Meta正式將Muse Code從測試版中推出，距首次亮相不到一個月。新增功能包括會話間訊息傳遞、工作流和倒帶功能，並推出了三個訂閱計劃：$5、$15和$50/月。價格遠低於競爭對手，但早期測試顯示其代幣消耗較高且程式碼重構結果較弱。一些專家擔心Meta的商業模式可能利用資料來投放廣告。

shaide 是一個自託管的 AI 平臺，可部署在您自己的 Kubernetes 叢集上，實現大規模多模型推理。它透過單一命令安裝，完全在您的網路邊界內執行，支援無網際網路連線的環境。該平臺以基礎設施即程式碼（Pulumi）管理，提供 OpenAI 相容 API，專為代理叢集設計，並適用於多家雲提供商和本地環境。