GPT 5.1 Codex Max 現已支援 Vercel AI Gateway★ 75
Vercel Changelog191 days agoReleaseVercel announced via its Changelog that its AI Gateway service now officially supports the newly released GPT 5.1 Codex Max model. This update allows…
GPT 5.1 Codex 模型現已支援 Vercel AI Gateway★ 75
Vercel Changelog213 days agoReleaseVercel announced in its official Changelog that the Vercel AI Gateway service has officially added support for OpenAI's latest GPT 5.1 Codex model. This update…
Gemini 2.5 Deep Think 於 ICPC 國際大學生程式設計競賽世界總決賽中達到金牌水準★ 85
Google DeepMind Blog233 days agoReleaseGoogle DeepMind has announced that its latest reasoning model, "Gemini 2.5 Deep Think," has achieved gold-medal-level performance at the International…
Google DeepMind 推出 CodeMender：專為程式碼安全設計的 AI Agent★ 82
Google DeepMind Blog233 days agoReleaseGoogle DeepMind has unveiled a new AI Agent called "CodeMender," designed to leverage advanced artificial intelligence to automatically remediate critical…
Hugging Face 推出 BigCodeArena：透過實際執行程式碼進行端到端 Code LLM 評測★ 75
Hugging Face Blog250 days agoReleaseHugging Face and the BigCode community have jointly launched a new code model evaluation platform called "BigCodeArena." As AI-assisted coding (such as Copilot…
Vercel 宣布與 Anthropic 合作，引進 Claude 4.5 Sonnet 驅動智慧程式碼代理人★ 80
Vercel Changelog258 days agoReleaseVercel has officially announced a new partnership with AI leader Anthropic, deeply integrating Anthropic's Claude 4.5 Sonnet model into the Vercel development…
Devin、Raycast、Windsurf 與 Goose 現已支援 Vercel MCP★ 75
Vercel Changelog293 days agoReleaseVercel announced a major update to its Model Context Protocol (MCP) server, officially adding support for four popular AI tools and platforms: Devin, Raycast…
Replicate 推出遠端 MCP 伺服器：可在 Claude、Cursor 與 VS Code 中直接探索與運行模型★ 75
Replicate Blog308 days agoNew ToolReplicate has officially launched a remote MCP (Model Context Protocol) server. MCP is an open standard created by Anthropic that enables large language models…
Vercel MCP 正式支援 Cursor：可直接在編輯器中管理 Vercel 專案與部署★ 78
Vercel Changelog309 days agoReleaseVercel has released an update announcing that its Model Context Protocol (MCP) service now officially supports Cursor, the popular AI-powered code editor. This…
Vercel 推出 Vercel MCP：將 Vercel 完美連接至你的 AI 開發工具★ 85
Vercel Changelog312 days agoReleaseVercel has officially launched the Vercel MCP (Model Context Protocol) server, a new feature designed to deeply integrate Vercel's cloud ecosystem with modern…
Vercel MCP 正式開啟公開測試：讓 AI 助手直接管理與部署你的 Vercel 專案★ 82
Vercel Changelog314 days agoReleaseVercel recently announced that its **Vercel MCP (Model Context Protocol) server, designed specifically for AI agents, has officially entered Public Beta**…
📚 3LM：針對阿拉伯語大語言模型在 STEM 與程式碼能力的全新評估基準
Hugging Face Blog317 days agoReleaseThe Technology Innovation Institute (TII) of the UAE — the organization behind the Falcon models — has announced on the Hugging Face blog the launch of a new…
Vercel AI Gateway 正式支援 Qwen3-Coder 模型
Vercel Changelog324 days agoReleaseVercel announced in its official changelog that its Vercel AI Gateway has now officially added Qwen3-Coder to its roster of supported models. This means…
透過 MCP 搜尋百萬個 GitHub 儲存庫：Vercel 推出全新 AI 協定工具★ 80
Vercel Changelog332 days agoNew ToolVercel has announced a major update to its AI development tooling, launching a new service based on the Model Context Protocol (MCP) that allows developers to…
Vercel 宣布：使用 Claude Code 與 Cursor Agent 不再需要購買團隊席位 (Team Seat)★ 70
Vercel Changelog373 days agoReleaseVercel published an important update on June 6, 2025, announcing a major policy change regarding support for AI coding agent tools on its platform…
Gemini 2.5 迎來重大更新：Pro 版推出實驗性「Deep Think」深度思考模式，Flash 版性能再提升★ 85
Google DeepMind Blog390 days agoReleaseGoogle DeepMind today announced important updates to its flagship model series, Gemini 2.5. The most noteworthy highlight of this update is a brand-new…
OpenAI 發表 o3、o4-mini 推理模型與開源終端機工具 Codex CLI★ 90
TLDR AI (Buttondown)423 days agoReleaseOpenAI recently held a live stream and published a blog post to officially announce the new reasoning model o3 and the lightweight reasoning model o4-mini…
DeepCoder：Together 與 Agentica 推出達到 o3-mini 水準的 14B 完全開源程式碼推理模型★ 85
TLDR AI (Buttondown)431 days agoReleaseAfter DeepSeek R1 set off a wave of open-source reasoning models, the open-source community saw many projects attempting to replicate its path to success…
Open R1：如何在本機使用 LM Studio 運行 OlympicCoder 進行程式開發★ 75
Hugging Face Blog451 days agoTutorialHugging Face has recently released an updated practical guide for the Open R1 project, walking developers through how to locally deploy and run "OlympicCoder"…
Hugging Face 推出 smolagents：用 Python 程式碼撰寫行動的極簡 AI Agent 框架★ 85
Hugging Face Blog530 days agoReleaseHugging Face officially launched a lightweight AI agent development framework called `smolagents` at the end of 2024. The core philosophy of this tool is "Code…
Replicate Intelligence #5：超強開源程式碼模型 DeepSeek-Coder-V2、AI 搜尋突破與 Discord 客服機器人
Replicate Blog723 days agoReleaseReplicate published their technical newsletter "Replicate Intelligence #5," with this issue focusing on major breakthroughs and real-world applications in the…
BigCodeBench：下一代 Code LLM 評測基準 HumanEval 的繼承者★ 80
Hugging Face Blog726 days agoReleaseAs large language models (LLMs) have made tremendous strides in code generation, the long-standing industry gold standard — the HumanEval benchmark — has…
StarCoder2-Instruct：完全透明且具備寬鬆授權的程式碼生成自我對齊技術★ 75
Hugging Face Blog776 days agoRelease### Background and Challenges In the field of code generation, instruction tuning is the key to improving a model's practical utility and alignment with human…
推出 LiveCodeBench 排行榜：全面且無污染的程式碼大語言模型評估★ 75
Hugging Face Blog789 days agoReleaseAs code large language models (Code LLMs) develop rapidly, fairly and accurately evaluating their capabilities has become a major challenge. Traditional…
Google 官方推出 CodeGemma：專為程式碼生成與補全設計的輕量級開源模型★ 80
Hugging Face Blog796 days agoReleaseGoogle and Hugging Face have jointly announced the launch of CodeGemma, a family of lightweight open-source large language models (LLMs) designed specifically…
StarCoder2 與 The Stack v2 正式發布：新一代開源程式碼大模型與超大資料集★ 80
Hugging Face Blog837 days agoReleaseThe BigCode community, jointly led by Hugging Face and ServiceNow, together with NVIDIA, has officially announced the launch of a new generation of open-source…
使用 API 運行 Code Llama 70B：Replicate 雲端部署教學
Replicate Blog866 days agoTutorialMeta's Code Llama 70B is a powerful open-source large language model designed specifically for code generation and understanding. However, running such a…
Personal Copilot：訓練專屬於你的程式碼助手★ 75
Hugging Face Blog961 days agoTutorialIn everyday development, tools like GitHub Copilot dramatically improve productivity, but for enterprises or individual developers, general-purpose models may…
Hugging Face SafeCoder 對決閉源程式碼助手：企業級私有化部署的安全性優勢★ 70
Hugging Face Blog1,007 days agoReleaseIn today's software development workflows, AI coding assistants have become a critical tool for boosting developer productivity. However, for many enterprises…
Meta 推出 Code Llama：基於 Llama 2 的開源程式碼生成模型，支援 100k 上下文★ 85
Hugging Face Blog1,024 days agoReleaseMeta has officially launched Code Llama, a family of state-of-the-art open-source code generation models fine-tuned on Llama 2. Code Llama achieves leading…