672 related articles
Tech FrontiersPi AutoResearch is a coding plugin based on Karpathy's Auto Research concept that auto-generates optimization plans, modifies code, runs tests, and logs results for fully automated performance tuning.
TutorialsStarting from the three core characteristics of LLMs, this article systematically covers foundational knowledge needed for Qwen3-0.6B fine-tuning, including model comparisons, fine-tuning value analysis, and the complete learning path.
Tech FrontiersDeepSeek-TUI is a free terminal AI coding agent written in Rust that rivals Claude Code at 20x lower cost. Learn about its features, performance, and who should switch.
Product ReviewsHow the Kman plugin uses prompt injection to cut AI output tokens by 65% without losing code quality. Covers installation, benchmark data, three intensity modes, and Kman Review.
TutorialsGuide to using Claude Code in China at low cost without an overseas credit card. Covers installation, API proxies, and budget alternatives starting from ¥7.9.
TutorialsDeep dive into five multi-agent coordination patterns: cost routing, context isolation, Agent Swarm, Generator-Verifier, and Smart Friend. Real cases show weekly costs dropping from $700 to $100 with 58% critical bug detection.
TutorialsGemini 3.5 Flash surpasses 3.1 Pro with 4x speed and half the price. Learn 6 tested methods to access Gemini 3.5 from China, including free AI Studio, no-VPN relay services, and API options.
TutorialsCompare three Claude Pro subscription methods: third-party top-up platforms, international credit cards, and in-app purchases. Find the best option based on cost, difficulty, and security.
Expert OpinionsIn-depth analysis of how free AI aggregator sites for ChatGPT and Claude actually work, revealing data security risks behind account pools and API proxies, plus safe alternatives.
Tech FrontiersSimon Willison releases Datasette Agent, combining LLM with Datasette to enable natural language database queries, plugin extensions, and local model support for personal data analysis.
TutorialsA comprehensive Claude Code beginner tutorial covering terminal installation, API configuration, cost-saving strategies with compatible models, and 8 architectural patterns revealed by the 510K-line source code leak.
Product ReviewsIn-depth comparison of Codex APP, Cloud Code, and Cursor — pricing, stability, and capabilities from frontend UI to backend logic — to help developers choose the right AI coding assistant.
Tech FrontiersQwen3.6 experimental MTP-GGUF benchmarked: single GPU pushes 35B-A3B model to 220 token/s, 1.4x faster with zero accuracy loss. Covers MTP principles, optimal Draft Tokens strategy, and RTX 5090 results.
TutorialsLearn how to get free Claude Opus access in Claude Code via GitHub Student verification and AnyGuardianManager proxy, with full setup steps and caveats.
Deep DivesRalph Loop is a 2025 AI programming paradigm: a memoryless AI Agent repeatedly reads the same Prompt, accumulates experience via file systems, beating multi-agent architectures through iterative loops.
Expert OpinionsAnthropic's Founders Playbook warns that AI lowers dev costs but not demand validation costs. When execution is cheap, judgment becomes the scarcest startup skill.
Expert OpinionsWhen AI writes code faster than most engineers, should ordinary people still learn to program? A veteran developer analyzes how coding skills become the lever for harnessing AI productivity.
Product ReviewsIn-depth review of Google Gemini 3 Flash's real-world performance in coding, multimodal understanding, and writing. Covers benchmark analysis, Cursor programming tests, and practical tips.
Product ReviewsIn-depth coding tests of Gemini 2.5 Pro covering pixel games, Ultimate Tic-Tac-Toe, Rust refactoring, and landing pages. Crushes Claude at Rust but struggles with frontend development.
TutorialsComplete guide to OpenCode, the open-source AI coding CLI tool supporting Claude, Gemini, and OpenAI. Covers installation, Next.js project building, MCP server integration, and agents.md generation.