#NPU
1028 related articles
·3 min
Complete Hands-On Tutorial: Building a Base Converter with Trae + PySide6 from Scratch
A detailed guide on using Trae AI IDE with PySide6 to build a desktop base converter from scratch — covering prompt writing, code generation, testing, and EXE packaging.
Read more →
·2 min
A Beginner's Guide to Vibe Coding: Build Software with Natural Language, No Coding Required
Vibe Coding lets anyone build software without coding skills. Learn what it is, how to get started, and how to use natural language and AI to go from idea to app.
Read more →
·3 min
Deep Dive into Closco: The Research Automation Platform That Goes from Natural Language to Complete Reports
Deep analysis of Closco's research automation platform covering cloud sandbox architecture, self-healing execution, batch computing, and applications in computational materials science, drug design, and genomics.
Read more →
·3 min
Vibe Coding in Practice: Building a GPS Check-in App from Scratch with AI — A Complete Walkthrough
A detailed guide to the four-step document-driven Vibe Coding method: from requirements docs to code generation, building a GPS check-in app with AI from scratch.
Read more →
·2 min
Why Is AI Progressing Fastest in Coding? A Deep Dive into Four Structural Advantages
AI coding advances faster than writing or image generation due to four structural advantages: instant feedback, GitHub's natural high-quality data, unified quantifiable standards, and perfect fit for reinforcement learning.
Read more →
·4 min
AI Coding Skill Mechanism Explained: Making AI Work Efficiently with Professional SOP Workflows
Deep dive into the Skill mechanism in AI coding: definition, purpose, and usage. Learn how Skills differ from Agent Constitutions and enable AI to follow professional workflows for tasks like debugging, code review, and requirements analysis.
Read more →
·3 min
Codex Beginner's Guide: Lessons Learned from 660 Million Tokens of Real-World Usage
Deep dive into OpenAI Codex Agent's core features, Skill ecosystem, context compression, and project-level Harness management tips from 660M tokens of real-world usage.
Read more →
·3 min
The Four Stages of AI Coding Tool Evolution: From Code Completion to Multi-Agent Collaboration
A deep dive into the four stages of AI coding tool evolution: from code completion and chat Q&A to Agentic Coding and multi-Agent collaboration, explaining the design logic behind Claude Code, Cursor, and Codex.
Read more →
·2 min
KeyType: A Free, Open-Source System-Level AI Autocomplete Tool for macOS
KeyType is a free, MIT-licensed macOS tool for system-level AI text completion. It runs local LLMs, supports custom models, and keeps all data on your device.
Read more →
·3 min
Cursor AI Programming in Practice: A Complete Walkthrough from UI Design to Project Launch
A deep dive into Cursor AI's complete project development workflow, covering standardized prompts, UI design, code generation, and LangChain agent building.
Read more →
·2 min
Doubao + Cursor in Practice: AI-Powered Web Scraper Development in One Minute — Full Workflow
Full workflow for using Doubao to generate prompts and Cursor to auto-generate web scraper code. Covers AI chain collaboration, full-stack code generation, and auto-documentation.
Read more →
·2 min
Complete Guide to Subscribing to ChatGPT Plus with Alipay: Three Simple Steps
Learn how to subscribe to ChatGPT Plus using Alipay via third-party platforms, including buying CDK codes, verification, activation steps, and risk warnings.
Read more →
·3 min
Codex Skill Feature Explained: Package Repetitive Work into Automated Workflows
A detailed guide to Codex Skill: two creation methods and practical applications. Package repetitive workflows into reusable Skills to automate meeting notes, task breakdowns, and more — no coding required.
Read more →
·2 min
Six Major AI Events in One Day: OpenAI False Bans, Anthropic Pause Call, Grok Tops Arena
Six major AI events decoded: OpenAI bug falsely bans Pro users, Anthropic calls for frontier model pause, DeepSeek quality drops, Grok tops image arena, ChatGPT hits 1B MAU, WeChat tests AI payments.
Read more →
·3 min
StepFun STEP3.7 Flash Tops AA Benchmark — Multimodal Reasoning Speed Takes Off
StepFun STEP3.7 Flash tops Artificial Analysis benchmark in speed, cost-efficiency, and multimodal. AI safety leaders call for legislation, embodied AI gets 300K-home training ground, Huawei Cloud unveils Agentic Infra.
Read more →
·3 min
From Claude Oceanus to GPT-5.6: A Complete Breakdown of This Week's Major AI Model Updates
Deep analysis of this week's major AI model updates: Anthropic Oceanus red team leak, OpenAI GPT-5.6 Dual Alpha exposed, NVIDIA Nemotron Ultra 550B release, and AI recursive self-improvement research breakthrough.
Read more →
·2 min
Codex++ Hands-On: Complete Guide to Connecting Chinese LLMs Without a ChatGPT Account
Step-by-step tutorial on using Codex++ to connect Chinese LLMs like DeepSeek and Tongyi Qianwen without a ChatGPT account, with full Computer Use and plugin support.
Read more →
·2 min
Rebuilding a Complete GUI App with DeepSeek for Just $2.50: A Real-World AI Programming Cost Breakdown
A Bilibili creator used DeepSeek V4 Pro via Cursor to rebuild a complete IndexTTS GUI app for just 18.63 RMB (~$2.50). Full breakdown of the AI coding workflow, features, and cost comparison.
Read more →
·3 min
Claude Opus 4.8 Identifies Itself as DeepSeek: Data Contamination or Distillation? A Technical Analysis
Anthropic's Claude Opus 4.8 failed within 2 hours of launch, identifying itself as DeepSeek and Tongyi Qianwen in Chinese. Deep analysis of data contamination vs distillation hypotheses and multilingual alignment gaps.
Read more →
·1 min
Hyper-Connections: The First Major Improvement to Residual Connections in a Decade
Deep dive into ByteDance's Hyper-Connections: expanding residual connections from one to multiple learnable pathways, significantly improving training under the same compute budget.
Read more →