34 related articles
TutorialsA detailed guide to Claude Code's three working modes: Auto-Edit (Shift+Tab), Plan mode, and YOLO fully automatic mode — how to enable them, ideal use cases, and key considerations for developers.
ResearchDeep analysis of Claude Code's open-source architecture: dual-loop design, 7-step tool pipeline, 4-layer token compression, memory systems, and multi-agent collaboration patterns.
Product ReviewsDeep dive into Cursor 1.0's six core features: Backboard PR review, Background Agent, Memories, One-Click MCP, Jupyter Support, and Rich Chat Response with hands-on testing results.
Product ReviewsIn-depth comparison of 10 AI coding tools including GitHub Copilot, Cursor, Claude Code, and Windsurf, analyzed across features, target users, and pricing to help developers choose the right AI assistant.
Tech FrontiersSGLang team hosts an Agent Loops Office Hour exploring inference optimization for agentic loops, covering KV Cache reuse, low-latency multi-turn dialogue, and tool calling techniques.
Product ReviewsDeep dive into Google Stitch 2.0: Gemini 3.0 Pro reasoning engine, variant generation, predictive heatmaps, AI Studio and Jules export for a complete design-to-deployable-code workflow—completely free.
Product ReviewsCursor launches web and mobile versions supporting multi-agent parallel execution and mobile code review. A detailed look at core features, comparison with Google Jules and OpenAI Codex, and the PWA mobile experience.
Tech FrontiersOpenAI Codex introduces Goal mode for sustained AI programming tasks lasting hours or days. Learn usage methods, best practices, and real-world applications.
TutorialsCan't use Claude Code in China? This hands-on guide tests Cursor and Windsurf as alternatives for accessing the Opus 4 model, both supporting Alipay payment with no overseas phone number required.
Tech FrontiersOpenAI Codex CLI 0.128.0 introduces the /goal command, enabling autonomous looping until objectives are met or token budgets are exhausted. Analysis of its Ralph Loop implementation and safety controls.
Product ReviewsHands-on testing of Cursor 1.0's BugBot: how AI automated code review finds real bugs like JWT exceptions and race conditions in 2 minutes, with one-click fixes via GitHub PR integration.
Product ReviewsHands-on review of Cursor 1.0: testing one-click MCP integration, BugBot code review, and Background Agent. Includes pricing analysis and real usage limitations.
Tech FrontiersCursor launches automatic CI failure repair with an always-on AI Agent that monitors GitHub repos, analyzes CI logs, identifies root causes, and submits fix PRs.
Product ReviewsDeep dive into Codexia, an open-source AI coding agent workstation supporting Codex CLI and Claude Code multi-agent collaboration with task scheduling, Git Worktree parallel development, remote control, and skill management.