#DPO
256 related articles
Tutorials·2 min
Claude Code 1.7+ Third-Party API Locked: Solutions
Claude Code 1.7+ locks third-party model APIs? This guide provides two solutions using the CLAUDE_ENV environment variable to unlock dev mode and reconfigure DeepSeek and other APIs.
Read more →
Product Reviews·3 min
Qwen Code 2.0 Update Analysis: Plan Mode and Visual Intelligence in Practice
Deep analysis of Qwen Code 2.0 updates covering Plan Mode approval mechanism, Visual Intelligence auto-switching, Zed editor dual authentication, and Windows fixes for this CLI coding assistant.
Read more →
Tutorials·3 min
Getting Started with FastAPI: A Comprehensive Guide to Frontend-Backend Separation and RESTful API Core Concepts
A systematic guide to core concepts for FastAPI beginners, covering frontend-backend separation architecture, RESTful API design, and JSON data format advantages for Python developers.
Read more →
Tutorials·3 min
AnythingLLM Installation & Configuration Guide: Building a Local Knowledge Base with API Integration
Complete guide to AnythingLLM local knowledge base setup: installation tips, Ollama model configuration, document vectorization, recall optimization, and API integration.
Read more →
Tutorials·2 min
CLAUDE.md Convention Files: A New Paradigm for Project Development Standards in the AI Programming Era
A detailed guide to CLAUDE.md convention files covering tech stack declarations, frontend/backend standards, and database design rules to help teams standardize AI code generation and boost human-AI collaboration.
Read more →
Research·3 min
MementoGUI: A Multimodal Memory Management Framework for Solving Long-Horizon GUI Agent Amnesia
MementoGUI is a plugin-style multimodal memory management framework that solves GUI agent forgetting in long-horizon tasks through dual time-scale memory and four memory control operators, boosting long-task completion without fine-tuning.
Read more →
Product Reviews·2 min
Hands-On Comparison of 4 AI Coding Agents: Claude Code vs. Copilot vs. Cursor vs. OpenCode
Hands-on comparison of Claude Code, GitHub Copilot, Cursor, and OpenCode across three real-world tests — bug fixing, large project debugging, and app development from scratch — with pricing and recommendations.
Read more →
Expert Opinions·3 min
The Salary Ceiling for Agent Engineers: Two Critical Dividing Lines
Agent engineer salary gaps hinge on two dividing lines: real production deployment experience and depth of foundational theory including deep learning, fine-tuning, and reinforcement learning.
Read more →
Product Reviews·3 min
Deep Dive into Tencent Marvis: How a System-Level AI Assistant Redefines Human-Computer Interaction
Deep dive into Tencent Marvis system-level AI assistant, analyzing its local knowledge base, semantic search, privacy mode, and how Agents evolve from tools to OS integration.
Read more →
Tutorials·3 min
Java Full-Stack Beginner's Guide: Application Domains, Three Major Platforms & Learning Path Explained
A beginner's Java full-stack guide covering Java's origins, real market position, enterprise server-side strengths, Java SE/EE/ME platforms, and a complete learning path from basics to full-stack.
Read more →
Tutorials·4 min
Complete Guide to Building a Local AI Knowledge Base with Qwen3.5 + RAGFlow + Ollama
Complete guide to building a local AI knowledge base with Qwen3.5, RAGFlow, and Ollama, covering Docker deployment, Embedding model configuration, knowledge base creation, and RAG system setup.
Read more →
Tutorials·4 min
New API in Practice: Complete Tutorial for Building Your Own AI API Relay Station
Complete tutorial on building an AI API relay station using the New API open-source project, covering Docker deployment, server configuration, channel management, token distribution, and client verification.
Read more →
Product Reviews·3 min
Hertzman: A Free, No-Install Local LLM Deployment Tool Review
Detailed review of Hertzman local inference engine covering one-click deployment, smart hardware recommendations, OpenAI-compatible API, and performance comparison with LM Studio.
Read more →
Tutorials·4 min
Credit Settlement for AI Async Tasks: Deduct First or Complete First?
Analyze correct timing for AI async task credit settlement. Compare deduct-on-submit vs. Webhook callback approaches with a pre-freeze + callback confirmation implementation for fair SaaS billing.
Read more →
Tutorials·2 min
Complete Guide to Configuring Local DeepSeek Model in PyCharm for AI-Assisted Programming
Learn how to configure a local DeepSeek model in PyCharm via Ollama for free, privacy-safe AI-assisted programming. Includes installation steps, plugin setup, usage tips, and hardware recommendations.
Read more →
Tutorials·3 min
LangChain Unified Interface in Practice: A Guide to Avoiding Model Invocation Pitfalls
A detailed comparison of LangChain's two model invocation approaches, focusing on init_chat_model unified interface usage and tips for avoiding DeepSeek V4 Pro Thinking Mode pitfalls in Agent scenarios.
Read more →
Industry Insights
Alibaba's $52B AI Investment: A Full-S…
·3 min
Alibaba's $52B AI Investment: A Full-Stack Cloud Infrastructure Upgrade for the Agent Era
Alibaba invests $52B in AI cloud infrastructure over 3 years. Bailian Platform hits 8B yuan ARR with 11 quarters of triple-digit AI revenue growth. Deep analysis of Alibaba Cloud's full-stack Agent upgrade strategy.
Read more →
Industry Insights·3 min
OpenAI Models Officially Land on AWS Bedrock, Ushering in a New Multi-Cloud Era for Enterprise AI Deployment
OpenAI's frontier models and Codex are now GA on Amazon Bedrock, letting enterprises leverage AWS security and compliance to access OpenAI capabilities. A deep dive into the multi-cloud AI impact.
Read more →
Product Reviews·4 min
OpenHuman Deep Dive: A Context-First Open-Source Personal AI Agent
Deep dive into OpenHuman open-source AI Agent: context-first architecture, Rust+React hybrid, Memory Tree system, Token Juice compression, and multi-model routing.
Read more →
Tutorials·3 min
oMLX + MTP + Qwen3.6: Local AI Coding Speed Breaks New Records
Using oMLX with MTP and Qwen3.6 35B on Apple Silicon Mac to achieve 86.7 tokens/s local coding speed, building a full-stack app in under 5 minutes.
Read more →