以下の記事が面白かったので、簡単にまとめました。 ・Game development – Codex | OpenAI Developers 1. ブラウザゲームの作成1-1. はじめにゲーム開発は、Codexがコード生成以上の役割を果たす最も分かりやすい例の1つです。実際のゲーム開発には、通常、コンセプトの記述、レンダリングレイヤー、フロントエンドのシェル開発、バックエンドの状態管理、アセット制作、継続的なビジュアル調整が必要です。 このユースケースでは、Codexはまずゲームの動作内容を明確に記述することから始め、その後「Playwright」を使ってブラウザ上でゲームをテストするという反復的なプロセスで最大限の効果を発揮します。 1-2. スキルとプラグイン・Playwright ブラウザでゲームをプレイし、現在の状態を確認し、実際のビルドに合わせて操作性、タイミング、UIの感触を繰
GitHub - modelcontextprotocol/servers: Model Context Protocol Servers
Official integrations are maintained by companies building production ready MCP servers for their platforms. 21st.dev Magic - Create crafted UI components inspired by the best 21st.dev design engineers. 2slides - An MCP server that provides tools to convert content into slides/PPT/presentation or generate slides/PPT/presentation with user intention. ActionKit by Paragon - Connect to 130+ SaaS inte
Today, we are excited to announce the launch of .NET 10, the most productive, modern, secure, intelligent, and performant release of .NET yet. It’s the result of another year of effort from thousands of developers around the world. This release includes thousands of performance, security, and functional improvements across the entire .NET stack-from languages and developer tools to workloads-enabl
What We Learned from a Year of Building with LLMs (Part I)
It’s an exciting time to build with large language models (LLMs). Over the past year, LLMs have become “good enough” for real-world applications. The pace of improvements in LLMs, coupled with a parade of demos on social media, will fuel an estimated $200B investment in AI by 2025. LLMs are also broadly accessible, allowing everyone, not just ML engineers and scientists, to build intelligence into
Protocol Like MCP, codex app-server supports bidirectional communication using JSON-RPC 2.0 messages (with the "jsonrpc":"2.0" header omitted on the wire). Supported transports: stdio (--listen stdio://, default): newline-delimited JSON (JSONL). websocket (--listen ws://IP:PORT, experimental): one JSON-RPC message per WebSocket text frame. In WebSocket mode, app-server uses bounded queues. When re
GPT for Sheets™ and Docs™ - Google Workspace Marketplace
GPT for Sheets™ is the leading bulk AI processing agent for Google Sheets, which enables you to: 🚀 Run up to 400 prompts per minute ✅ Execute up to 200k rows in one run reliably 🔄 Choose from the world’s best AIs: ChatGPT, Claude, Gemini™, Perplexity, Grok and more ISO 27001 certified and GDPR compliant. Brought to you by Talarian: makers of YAMM, Form Publisher, and Awesome Table, some of the m
MAI-Thinking-1: Building a Hill-Climbing Machine The Microsoft AI Team 1 Abstract Progress in AI is driven not by a single model, but by the ability to continually improve upon the current state of models. Achieving this requires treating model development as a system-level optimization problem, for which the solution is building a hill-climbing machine for rapid improvement. Our process includes
Shell + Skills + Compaction: Tips for long-running agents that do real work
Shell + Skills + Compaction: Tips for long-running agents that do real work Practical patterns for building with skills, hosted shell, and server-side compaction in the Responses API. We’re shifting from single-turn assistants to long-running agents that handle real knowledge work: reading large datasets, updating files, and writing apps. Based on developer feedback and our own experience building
Using skills to accelerate OSS maintenance | OpenAI Developers
Keep workflows in the repo In these repos, we use skills to capture repository-specific workflows. A skill is a small package of operational knowledge: a SKILL.md manifest, plus optional scripts/, references/, and assets/. The Codex customization docs describe why this works well: skills are a good fit for repeatable workflows because they can carry richer instructions, scripts, and references wit
AIニュースノート：nano-bananaが話題に、AGENTS.mdの採用広がる、Microsoft Copilotに3Dモデリング機能が追加、ChatGPTでプロジェクト専用メモリー搭載、Claude for Chromeの安全設計など gihyo.jpのニュース記事として取り上げていなかったもののなかから、直近の興味深いAIに関連するニュース概要を簡単にまとめてみました。 ※この記事は、不正確な内容を含んでいる可能性のある実験的コンテンツです。正確な情報はリンク先を確認してください。 nano-bananaの週でした nano-bananaこと、Gemini 2.5 Flash Imageがリリースされて、このモデルによる画像生成・編集が話題になった週でした。興味深い使い方やベストプラクティスも紹介されています。 “nano-banana”の舞台裏：対話×段階編
Transformer models: an introduction and catalog — 2023 Edition January 16, 2023 52 minute read This post is now an ArXiV paper that you can print and cite. Update 05/2023 Another pretty large update after 4 months. I was invited to submit the article to a journal, so I decided to enlist some help from some LinkedIn colleages and completely revamp it. First off, we added a whole lot of new models,
GitHub - ComfyUI-Workflow/awesome-comfyui: A collection of awesome custom nodes for ComfyUI
ComfyUI-Gemini_Flash_2.0_Exp (⭐+172): A ComfyUI custom node that integrates Google's Gemini Flash 2.0 Experimental model, enabling multimodal analysis of text, images, video frames, and audio directly within ComfyUI workflows. ComfyUI-ACE_Plus (⭐+115): Custom nodes for various visual generation and editing tasks using ACE_Plus FFT Model. ComfyUI-Manager (⭐+113): ComfyUI-Manager itself is also a cu
Create an Azure OpenAI, LangChain, ChromaDB, and Chainlit chat app in AKS using Terraform | Microsoft Community Hub
Create an Azure OpenAI, LangChain, ChromaDB, and Chainlit chat app in AKS using Terraform In this sample, I demonstrate how to quickly build chat applications using Python and leveraging powerful technologies such as OpenAI ChatGPT models, Embedding models, LangChain framework, ChromaDB vector database, and Chainlit, an open-source Python package that is specifically designed to create user interf
j次のブックマーク
k前のブックマーク
lあとで読む
eコメント一覧を開く
oページを開く
Codex のゲーム開発のためのプロンプトまとめ｜npaka
Announcing .NET 10 - .NET Blog
App Server – Codex | OpenAI Developers
MAI-Thinking-1: Building a Hill-Climbing Machine
AIニュースノート：nano-bananaが話題に、AGENTS.mdの採用広がる、Microsoft Copilotに3Dモデリング機能が追加、ChatGPTでプロジェクト専用メモリー搭載、Claude for Chromeの安全設計など | gihyo.jp
Transformer models: an introduction and catalog — 2023 Edition