#DEEP DIVE
326 related articles
·3 min
GLM-5.2 Deep Dive: Million-Token Context, MIT Open Source & Full-Stack Domestic Chip Training
Deep dive into Zhipu's GLM-5.2: truly usable 1M-token context, MIT open-source strategy, full-stack Huawei Ascend training, and how it compares to Claude Opus. Includes benchmarks, use cases & pricing.
Read more →
·3 min
Deep Dive into Claude Sonnet 4: Replicating Lovable with Just Two Prompts
Deep dive into Claude Sonnet 4: replicate Lovable with two prompts, generate McKinsey-grade reports, build 2D games, and explore the AI Agent building block economy.
Read more →
·3 min
Andrew Ng and Anthropic's Definitive Claude Code Tutorial: A Deep Dive
Andrew Ng and Anthropic launch a Claude Code course covering context management, parallel sessions, MCP server integration, and hands-on projects in RAG, data analysis, and Figma-to-code conversion.
Read more →
·3 min
A Systematic Guide to Claude Code: From Deployment to Architectural Analysis of 510K Lines of Source Code
A systematic guide to Claude Code covering environment deployment, domestic model integration, six core systems (memory, multi-Agent, etc.), a full-stack ChatBot project, and eight design patterns from 510K lines of open-source code.
Read more →
·2 min
Hermes Jarvis Deep Dive: The Voice-Driven All-in-One AI Assistant
Deep dive into Hermes Jarvis voice AI assistant: its core features, five-layer architecture, multi-model integration, system-level control, and the future of voice-driven AI development.
Read more →
·2 min
DeepSWE Benchmark Deep Dive: Exposing SWE-Bench Flaws and the True Coding Ability Rankings
Deep dive into how DeepSWE exposes SWE-Bench Pro's data contamination and cheating issues. GPT-5.5 leads at 70%, open-source models lag far behind. Covers results, cost comparisons, and practical developer advice.
Read more →
·3 min
Building a Travel Route Planning Mini-Program with AI in One Day: A Full Workflow from Design to Launch
Learn how to build a complete travel route planning WeChat Mini-Program in one day using AI tools like Modao AI and Cursor, covering UI design, code generation, debugging, and deployment.
Read more →
·4 min
Codex Switch: A Deep Dive into the Protocol Translation Tool for Connecting DeepSeek to Codex
Learn how Codex Switch enables DeepSeek, GLM, and other models to seamlessly connect to OpenAI Codex CLI via local proxy protocol translation, vision augmentation, and web search.
Read more →
·2 min
A Deep Dive into Claude Fable 5: AI Programming Reaches a Tipping Point
Andrej Karpathy's deep review of Claude Fable 5: beyond SOTA benchmarks, it delivers a qualitative leap in long, high-difficulty coding sessions. Exploring the Jevons Paradox of AI programming.
Read more →
·3 min
Firebase AI Logic Deep Dive: Hybrid Inference, Prompt Templates & Multi-Layer Security Deployment
Deep dive into Firebase AI Logic: server-side prompt templates to prevent leakage, Cloud Function triggers, four-layer security defense, AI monitoring with context caching for cost control, and cross-platform hybrid inference.
Read more →
·2 min
Qwen3-Coder Deep Dive: A Coding Model Built for Long-Horizon Agent Loops
Deep dive into Qwen3-Coder: 11 hours continuous operation, 10K+ lines of code, 1000+ calls. Explore its long-horizon agent loop architecture, reasoning persistence, thinking mode switching, and deployment on Fireworks.
Read more →
·2 min
Deep Dive into Alibaba's AgentScope 2.0: Six Core Upgrades and Agent Design Patterns
Deep dive into Alibaba's AgentScope 2.0 multi-agent framework: event system, execution safety, human-in-the-loop, and ReAct vs Plan-and-Execute agent design patterns.
Read more →
·4 min
AI + Java Backend Learning Roadmap: Four Stages from CRUD to Senior AI Engineer
A complete AI + Java backend learning roadmap based on Spring AI Alibaba: from prompt engineering and LLM API integration to RAG knowledge bases and Agent systems across four stages.
Read more →
·3 min
Complete Guide to LangChain 0.3: Module Architecture & Core Development in Practice
A deep dive into LangChain 0.3's module architecture, message abstraction, prompt templates, output parsers, LCEL chains, LangSmith tracing, and LangGraph for mastering LLM application development.
Read more →
·2 min
OpenAI Stargate Michigan Data Center Breaks Ground: A Deep Dive into the 1GW Super Computing Facility
OpenAI's Stargate project breaks ground in Michigan, building a 1GW super data center with closed-loop cooling, thousands of union jobs, and $40M in free Codex credits for students.
Read more →
·3 min
Firestore Enterprise Edition Query Engine: A Deep Dive into Full-Text Search, Subqueries, and Pipeline Operations
Deep dive into Firestore Enterprise Edition's new query engine covering full-text search, subquery Joins, and pipeline operations with practical recipe app examples.
Read more →
·3 min
HarmonyOS 7 Developer Beta Launches: A Deep Dive into System-Level Transformation for the Agent Era
HarmonyOS 7 developer Beta launches, claiming to be the world's first AI-native OS. Deep analysis of Xiaoyi Agent, StarShield security, Galaxy Interconnect, and the OS AI competition landscape.
Read more →
·3 min
Deploying a Multimodal AI Agent Locally on a 3080Ti: VRAM Management and a Deep Dive into All Five Modules
A detailed guide to deploying a multimodal AI Agent on a 3080Ti with 12GB VRAM, covering LLM, STT, TTS, image and video generation module selection, dynamic VRAM loading, and real-world performance.
Read more →
·3 min
Beginner's Guide to Agent Skills: Structure Breakdown & Custom AI Skill Development
A deep dive into Agent Skill's core concepts and internal structure, covering skill.md, references, scripts, and assets with a restaurant poster Skill example.
Read more →
·3 min
A Three-Month Roadmap to LLM Development: A Deep Dive into the Learning Path from Zero to Freelancing
A deep dive into the three-step LLM development learning path: from prompt engineering and RAG knowledge bases to AI Agent development, with realistic timelines for beginners and experienced developers.
Read more →