152 related articles
TutorialsA detailed guide to Andrej Karpathy's LLM-Wiki personal knowledge base approach, transforming LLMs from interpreters to compilers with a three-layer architecture for self-evolving knowledge.
Deep DivesExplore the three key stages of LLM training: pre-training learns language, post-training learns tasks, alignment learns boundaries. Understand why AI hallucinates.
Deep DivesThe core of AI alignment is aligning What to do, not How to do. Through an Alembic database migration case, learn how Harness engineering crystallizes dev standards into reusable assets for automated programming.
ResearchAlibaba Mama's Skills-Oriented Programming methodology uses three-layer Skill structures, progressive disclosure, and four-layer anti-corruption systems to achieve 90%+ code generation accuracy for Code Agents in complex enterprise codebases.
TutorialsDeep dive into Claude Code tips covering codebase Q&A, CLAUDE.md configuration, MCP server integration, SDK mode, and parallel sessions to master Anthropic's AI coding assistant.
Product ReviewsDeep dive into VS Code AI Toolkit 2.0 major update, covering Agent Builder, MCP tool integration, batch testing, model evaluation, and a complete guide to using GPT-5 and Claude for free via GitHub Models.
Deep DivesWhat exactly is a large model? This article explains the essence of LLMs from the core concepts of "models" and "parameters," covering GPT parameter scales, vector dimensions, and open-source model selection.
Product ReviewsIn-depth comparison of Alibaba Qoder, Cursor, Trae, and Claude Code across architecture, features, and use cases to help developers choose the best AI coding tool.
Product ReviewsWikiGen is an open-source Python code Wiki generator with CLI and MCP protocol support, auto-generating structured docs for codebases and integrating with AI editors as a context provider.
Product ReviewsDeep dive into OpenClaw4J, an intelligent Agent framework built on Java 21 virtual threads and Spring AI, supporting tool calling, memory management, and multi-Agent collaboration for enterprise Java developers.
Product ReviewsLerim CLI is an open-source background memory agent that automatically extracts reusable project memories from AI coding agent sessions, solving the cross-session context loss problem.
Product ReviewsDeep dive into AnythingLLM, an open-source AI tool with 59K+ GitHub Stars. Supports local LLM inference, RAG private knowledge base Q&A, and zero-config setup. Explore core features, use cases, and architecture.