29 related articles
Tech FrontiersSWE-bench opens evaluation environments, task sets, trajectories, and training recipes, dramatically lowering the barrier to AI coding agent development.

From Iraqi stew to Singaporean cuisine across centuries—using software refactoring concepts to decode cultural evolution, code reuse, and incremental change.

Microsoft designer Tua Nguyen built Opal, an AI rabbit assistant on Raspberry Pi using OpenClaw — capable of browsing the web, finding recipes, and operating GitHub.

Build a multi-scene life assistant Agent using ModelScope MCP Marketplace and Dify. Integrates Amap, LeetCode, recipe, and news MCP Servers with Qwen3 via Chatflow.

Meta Muse Spark 1.1 deep dive: native multimodal architecture, platform tools, social data retrieval, e-commerce vision — Meta's first closed-source API model benchmarks against Anthropic Sonnet.

Anthropic's open-source Claude Cookbooks project offers runnable Jupyter Notebook examples covering RAG, Tool Use, multimodal processing, and more—helping developers master Claude API best practices.

Gemini 3.5 Pro is delayed again, yet the community's reaction is surprisingly calm. This article dives deep into Google's compute cost pressures, the risks of a full architectural rebuild, and DeepMind's long-term strategy.

Matt Pocock open-sources the mattpocock/skills project, publicly sharing his personal .claude directory config. An in-depth look at the Claude Skills mechanism, skill library methodology, and the shift from prompt engineering to skill engineering.

A solo developer iterated an iOS app to 100,000 lines of code in 7 days and shipped it. This article breaks down the core methodology: delegate the frontend to AI, control the backend by hand.

July 12 GitHub trending: Agent Skills/MCP ecosystem explodes with superpowers hitting ~900 stars, pgrust rewrites Postgres in Rust passing 100% tests, plus solid engineering foundations.

A major breakthrough in AI coding! Hands-on tests show new LLMs generating a Minecraft clone in 90 minutes and a TMNT game in 30 minutes, building 3D scenes, animation, and game logic in one shot.

DeepSeek and Peking University's DS Spark paper boosts AI inference speed by up to 85% via confidence scheduling and semi-autoregressive speculative decoding — no model or GPU changes.

What is an AI Agent? This article systematically explains the core architecture of AI agents (LLM + Planning + Memory + Tools), how they differ from ChatGPT, their combination with robots, and why developers must master Agent development skills.

Anthropic's Boris Cherny and Cat Wu discuss how Claude Code expanded from engineering teams company-wide, the Claude Tag platform strategy, and the launch of Claude Fable 5.

Creator Ajiang burned 10B Tokens on Codex to migrate cc-haha from Tauri 2 to Electron. A deep dive into Codex's long-horizon engineering, Computer Use, costs, and practical advice for developers.
Autoresearch: How Self-Evolving AI Age…
Autoresearch lets AI agents automatically explore and refine better solutions during task execution. This article breaks down agent recipes, self-improvement loops, and human-AI collaboration boundaries.
Building a Coding Agent with LLM: A De…
Simon Willison built llm-coding-agent — an open-source Claude Code-style agent — using just two prompts and TDD. Explore its tool design, bootstrapped dev process, and real-world test results.

Learn how to build a multi-function AI agent workflow using ModelScope MCP Plaza and Dify, featuring dietary recommendations, algorithm practice, news, and travel planning with zero coding.

Deep dive into Goose, the 50K-star open-source local AI assistant. Covers MCP tool integration, multi-model switching, Recipes workflows, and comparisons with Codex and Cursor.

Deep analysis of Loop workflow recipes, Vercel's open-source Agent framework, Pyker AI-native project management, Arrow P2P tool, DBX database client, and NVIDIA's Skill Spectre security tool.