#AI编程
9636 related articles
Why Do All AI-Generated Projects Look the Same? The Aesthetic Homogenization Problem in Vibe Coding
Why do vibe coding projects all use purple gradients and dark glassmorphism? We break down the technical roots of AI aesthetic homogenization and how to escape it.
Weave Router 2.0: A Subscription-Aware AI Coding Agent Router with Cross-Service Intelligent Dispatch
Weave Router 2.0 is a subscription-aware AI coding agent router that auto-dispatches requests across Claude, Codex, and GPT subscriptions — claiming half the cost and double the speed of GPT-6 Astra.
Appwrite 2.0: An Open-Source Cloud Platform for AI Agents and Developers
Appwrite 2.0 rebuilds its core engine, adds native vector data, PostgreSQL/MySQL, S3 storage, and OAuth 2.1 identity — repositioning as an open-source cloud for AI agents.
Shared Selective Persistent Memory: Enabling Agentic LLM Systems to Reuse Context Across Sessions
Shared selective persistent memory is a memory architecture for agentic LLM systems that retains four types of reusable context—task specs, data schemas, domain constraints, and tool-use patterns—across sessions, avoiding both cold-start inefficiency and context overload.
Optimizing Golang CI: Replacing actions/setup-go to Speed Up Builds
When Golang CI scales up, actions/setup-go can become a bottleneck. Explore pre-built images, custom caching, and the trade-offs of replacing this official Action.
How Outdated Is Your AI? Training Cutoff Dates Compared Across 20 Major Models
A Hacker News project compares release dates and training cutoffs for 20 major AI models, highlighting knowledge freshness as a critical but overlooked evaluation metric.
Gemini 3.8 Live Launches; Google Adopts Claude Internally for Coding
Gemini 3.8 Live launches with low-cost multimodal features; OpenAI's Project Lily sparks privacy debate; Google adopts Anthropic's Claude Opus 5 internally.
Twigg: A Stateful API That Automates LLM Context Management
Twigg is a stateful LLM API that automates context management — handling model schema adaptation, smart compression, truncation, and routing, with a dashboard for managing tool schemas, system prompts, and billing.
Zero to Deep Learning in Three Months: An Efficient AI Self-Study Roadmap
A 3-month AI self-study roadmap from zero: one week each for Python/math and machine learning, then deep learning focused on computer vision, NLP, LLMs, and agents.
ImpactGate: A Merge Gate That Scores Structural Decay in AI-Generated Code
ImpactGate is a merge gate tool for AI-generated code that quantifies structural decay through impact scoring. An analysis of its core approach, necessity, and current limitations.
Using AI Agents for Model Innovation: A Hands-On Guide from Ablation Studies to Performance Gains
Learn how to use AI Agents (Codex) to assist deep learning model optimization: from a UNet baseline of 0.817, through training strategies, attention modules, and ablation studies, achieving ~3 points mIoU gain.
Unsloth Releases Windows ARM64 Binaries: Another Milestone for Local LLM Training
Unsloth releases official Windows ARM64 binaries, enabling out-of-the-box local LLM fine-tuning on ARM-based Windows devices. Learn what this means for developers.
FastAPI Lesson 1: Understanding Frontend-Backend Separation and RESTful APIs
FastAPI tutorial lesson 1: learn the difference between coupled and decoupled web architectures, what API interfaces are, and how RESTful conventions work — the foundation for mastering FastAPI.
From Function Calling to MCP and Agents: How LLM Tool Calling Really Works
A deep dive into how LLM Function Calling works across 5 steps, with a hands-on weather query demo, and how it underpins MCP and Agent development.
Spring AI LLM Tutorial for Beginners: A Complete Learning Path from Core Principles to Enterprise Practice
A breakdown of a popular Spring AI LLM course on Bilibili — covering Transformer architecture, RAG, private deployment, fine-tuning, and enterprise projects for Java developers.
Building a PPT Copyright Protection Tool with WorkBuddy: One-Click Watermarking and Image Conversion
A Bilibili creator built a PPT copyright tool with WorkBuddy that adds watermarks, converts slides to images, and merges them into PDF — packaged as a standalone EXE requiring no extra setup.
AI Agent Development Learning Roadmap: A Four-Stage Guide from Concepts to Real-World Practice
A four-stage AI Agent development roadmap: from core concepts and ReAct/CoT paradigms to prompt tuning, multi-agent collaboration, and real-world project delivery.
AI Agent Development in Practice: A Complete Breakdown of the LangChain + MCP + RAG Stack
A deep dive into AI Agent development with LangChain, LangGraph, MCP, and RAG. Includes a hands-on Vue project case study illustrating the perceive-decide-act loop.
AI Agent Beginner's Complete Guide: From Core Concepts to Hands-On Development
A beginner's guide to AI Agent development covering agent principles, Prompt engineering, RAG, multi-agent systems, and tool calling, with hands-on projects and career prep.
Agent Engineer Learning Roadmap: From Zero to Production-Ready Deployment
A complete Agent engineer learning roadmap covering LLM fundamentals, LangGraph, MCP/A2A protocols, context engineering, GraphRAG, and Vibe Coding — with 100k-line production projects.