#RPA
299 related articles
Tutorials·2 min
Building the Claude Code Frontend from Scratch: A Hands-On Walkthrough of the Welcome Screen Source Code
A hands-on guide to building a minimal Claude Code frontend from scratch, covering TypeScript+React+Ink stack, terminal UI rendering, project structure, and memory issue debugging.
Read more →
Product Reviews·2 min
AI Face Masking Tool Test: Doubao Generates Working Code on First Try, GPT Fails After Multiple Debugging Rounds
Real-world test of AI-generated face tracking masking tool code: Doubao produces working code on first try while GPT fails after multiple debugging rounds. Detailed comparison included.
Read more →
Tutorials·2 min
AI Vibe Coding in Practice: Porting a Claude Code Usage Meter to the LiChuang DevBoard
Using AI Vibe Coding to port a Claude Code usage display project from GitHub to the LiChuang DevBoard (ESP32-S3), featuring pixel-art animations, real-time usage monitoring, and a Bluetooth-to-WiFi conversion.
Read more →
Tutorials·3 min
Cursor + MCP + AScript Automation in Practice: How AI Programming Lowers the Development Barrier
In-depth analysis of how Cursor + MCP + AScript enables platform automation—covering architecture, workflow, and risk considerations for AI-powered development.
Read more →
Tech Frontiers·1 min
Gemini 3.5 Flash Achieves a Massive Leap on the GDPval Benchmark
Google Gemini 3.5 Flash surpasses Gemini 3.1 Pro on the GDPval benchmark. The lightweight Flash model leverages post-training techniques to approach frontier-level performance, redefining the balance between quality and cost.
Read more →
Tech Frontiers·1 min
Gemini 3.5 Flash Surpasses Pro in Vision Capabilities, 6x Faster Inference
Roboflow benchmarks show Google Gemini 3.5 Flash outperforms the flagship Gemini 3.1 Pro on multiple vision tasks with ~6x faster inference, delivering a cost-effective multimodal AI solution.
Read more →
Tech Frontiers·1 min
Gemini 3.5 Flash Tops the Vending Bench Cost-Efficiency Frontier
Google Gemini 3.5 Flash achieves cost-intelligence Pareto optimality on Vending Bench. Analysis of the benchmark methodology, Pareto Frontier implications, and practical significance for AI developers.
Read more →
Deep Dives·2 min
The "Worse is Better" Philosophy of Large Model Design: Why Simple and Brutal Beats Refined and Complex
Analyzing the "worse is better" philosophy in large model architecture: why DeepSeek V4 dropped N-gram, why Transformer dominates AI, and three iron laws of simple, efficient model design.
Read more →
Tech Frontiers·3 min
Claude Powers NASA Mars Rover Route Planning, Windsurf Launches IDE Model Arena
Claude plans routes for NASA's Perseverance rover, Windsurf launches Arena Mode for in-IDE model comparison, SenseTime open-sources multimodal reasoning models, and Anthropic research reveals pros and cons of AI-assisted learning.
Read more →
Tech Frontiers·3 min
Claude Powers NASA Mars Rover Route Planning, Windsurf Launches IDE Model Arena
Claude plans routes for NASA's Perseverance rover, Windsurf launches Arena Mode for in-IDE model comparison, SenseTime open-sources multimodal reasoning models, and Anthropic research reveals pros and cons of AI-assisted learning.
Read more →
Product Reviews·3 min
Athas IDE Deep Dive: A Free, Open-Source Lightweight AI Code Editor
Deep dive into Athas IDE — a free, open-source AI code editor built from scratch on Tauri. Features Vim mode, AI completion, Git integration, and free Google Gemini support.
Read more →
Expert Opinions·3 min
Being Underestimated Is Freedom: A Contrarian Competition Philosophy for the AI Era
Exploring the contrarian strategy of 'being underestimated is freedom' in AI. From OpenAI to DeepSeek to Cursor, why staying under the radar beats standing in the spotlight.
Read more →
Tutorials·3 min
Fully Automated Invoice Reimbursement with Local AI Agent: From Process Breakdown to Deployment
How to build a fully automated invoice reimbursement system with local AI Agents, covering OCR, info extraction, and form generation with MinerU+Qwen3+Qianwen Po.
Read more →
Tutorials·2 min
Ollama Getting Started Guide: The Best Tool for Locally Deploying Open-Source LLMs
A detailed guide to Ollama's core features: free open-source local LLM management with cross-platform support, intelligent GPU/CPU scheduling, and API integration for running DeepSeek and other open-source models locally at zero cost.
Read more →
Expert Opinions·3 min
Is Learning to Code Still Worth It in the AI Era? An Honest Answer from an Atlassian Engineer
Can AI write code instantly—so is coding still worth learning? An Atlassian engineer breaks down the truth behind tech leaders' claims and AI coding limitations.
Read more →
Tech Frontiers·3 min
Gemini 3.5 Pro Leak Analysis: Coding Matches GPT 5.5, Spark Agent Sparks Privacy Controversy
Gemini 3.5 Pro leak analysis: coding matches GPT 5.5, lightweight Flash achieves 92% performance at 20x lower cost. Gemini Spark as a 24/7 AI Agent raises privacy concerns amid Google's ecosystem flywheel strategy.
Read more →
Product Reviews·2 min
JCode: Deep Dive into a Multi-AI Agent Collaborative Programming Framework
Deep dive into JCode, an open-source Coding Agent Harness designed for multi-Agent collaboration. Features Agent Memory, Swarm collaboration, multi-Provider access, and self-evolution with just 14ms first-frame latency and 117MB for 10 sessions.
Read more →
Product Reviews·4 min
Lark CLI: A Deep Dive into Feishu's Open-Source AI Agent Command-Line Tool
Lark CLI is Feishu's official open-source CLI tool designed for AI Agents, offering 200+ commands across 17 business domains with 24 structured Skills for messaging, docs, spreadsheets, calendars, and more.
Read more →
Tutorials·3 min
The Vibe Coding 6-Step Method: A Complete Process for Building Real Products with AI and Zero Coding Experience
A detailed guide to the Vibe Coding 6-Step Method: from requirements alignment and high-fidelity prototyping to technical planning, modular implementation, testing, and launch — helping non-coders build real products with AI.
Read more →
Tutorials·3 min
Z-Image Model in Practice: Generate Cinema-Quality Ancient Chinese Beauty Portraits in 3 Minutes
Complete guide to Z-Image model variants and ComfyUI workflow setup, using Doubao for prompt reverse-engineering to generate cinema-quality ancient Chinese beauty portraits in minutes.
Read more →