#iterative thinking
485 related articles
Tech Frontiers·2 min
Mercury 2: How Diffusion Architecture Achieves 1000 Tokens Per Second Inference Speed
Inception Labs releases Mercury 2, a diffusion-based language model achieving 1000+ tokens/sec with strong reasoning, challenging autoregressive architectures.
Read more →
Product Reviews·2 min
A Kid Built a Typing Game with DeepSeek: A Complete Record of AI-Assisted Programming from Scratch
A kid used DeepSeek AI to independently build a typing game in the terminal. From basic letter input to a full aerial combat game with power-ups across 5 versions, showcasing AI-assisted programming's educational value.
Read more →
Tutorials·2 min
Replicating Manus for $30: A Practical Breakdown of Building an AI Agent's Minimum Viable Loop
A detailed breakdown of replicating the Manus AI agent platform for $30, covering Docker container integration, task orchestration, UI design, and the course-based monetization strategy.
Read more →
Product Reviews·2 min
AI Novel Writing Tool Tested: Three Modes for Generating Long-Form Web Fiction from Scratch
Hands-on test of an AI novel-writing agent with three creation modes: template fill-in, detailed outline, and fully automatic. Supports strong context memory, word expansion, and reduced AI feel.
Read more →
Tutorials·2 min
The 5-Step AI Coding Method: Build Useful Mini-Tools from Scratch with Zero Coding Experience
Master the 5-step AI coding method: think, break down requirements, generate code, debug, and deploy. Build useful tools with zero coding experience and avoid common pitfalls.
Read more →
Tutorials·2 min
LangChain Agent Executor Architecture: Building a ReAct Agent from Scratch
Deep dive into LangChain Agent Executor internals, covering the ReAct reasoning-action-observation loop, tool choice strategies, and building a custom Agent Executor from scratch.
Read more →
Tutorials·2 min
Trae in Practice: AI Builds a Java Backend Management System from Scratch
A detailed walkthrough of using Trae AI IDE to build a Java Spring Boot admin system from scratch, covering database init, driver debugging, and login fixes.
Read more →
Deep Dives·2 min
How AI Agents Work: The Four Core Elements and ReAct Loop Decision-Making Mechanism Explained
Deep dive into AI Agent's four core elements (LLM, Tools, Prompts, Executor) and ReAct loop decision mechanism, with a weather query example walkthrough.
Read more →
Product Reviews·2 min
Bolt.new Hands-On Review: Can Vibe Coding Actually Build Real Projects?
Hands-on review of building a retro gaming blog with Bolt.new. Deep dive into vibe coding's workflow, iteration pain points, code quality issues, and real-world applicability.
Read more →
Product Reviews·2 min
ChatGPT Images 2.0 for Brand Design: How Well Does AI-Generated Brand Kits Actually Work?
In-depth review of ChatGPT Images 2.0 for brand design, covering logo generation, color schemes, and Brand Kit creation, analyzing its strengths in style consistency, text rendering, and conversational iteration alongside real-world limitations.
Read more →
Tutorials·1 min
Claude Code + Remotion in Practice: 6 Real-World Cases of Making Videos with AI Code
Explore 6 real cases of Claude Code + Remotion for AI video production, covering animation cloning, auto chapter bars, smart sound matching & reusable Skill templates.
Read more →
Tutorials·1 min
9-Week Python Beginner's Guide: A Complete Learning Path from Zero to Independent Programming
A teaching-proven 9-week Python learning path for absolute beginners, covering syntax, data types, control structures, functions, and file handling with 16 hands-on projects.
Read more →
Tutorials·1 min
AI Agent Open-Source Course: 36 Chapters from ReAct to Claude Code Full-Stack Practical Guide
Open-source GitHub project agent-study offers 36 chapters covering ReAct loops, Claude Code reverse engineering, MCP protocol, RAG, DSPy, and production observability as runnable Python code.
Read more →
Tutorials·4 min
Claude Opus 4.5 Tutorial: Real-World Coding Tests + How to Access from China Without a VPN
Hands-on review of Claude Opus 4.5's coding, writing, and data visualization capabilities. Includes two methods for accessing it from China without a VPN, plus real demos of bug fixing and dashboard development.
Read more →
Tutorials·3 min
Xingliu Agent Tutorial: Precision Editing, Smart Layer Splitting, and Batch Image Generation — A Complete Hands-On Guide
A complete Xingliu Agent tutorial covering click-to-edit precision, one-click layer splitting, smart Mockup fitting, and batch style generation — boost your design output 10x.
Read more →
Product Reviews·2 min
PPT Flag Studio: 4 AI Agents Collaborating to Generate Interactive HTML Presentations in One Click
PPT Flag Studio uses 4 AI Agents in a collaborative workflow to generate interactive HTML presentations from raw materials—featuring narrative extraction, structure planning, expression polishing, and HTML rendering.
Read more →
Product Reviews·3 min
ChatGPT vs Gemini vs Claude: Who Can Build Mario 64 from Scratch?
Testing ChatGPT 5.2, Gemini 3 Pro, and Claude 4.5 building Super Mario 64 from scratch with the same prompt. Gemini wins overall with best playability, ChatGPT has best visuals but only 1 fps, Claude fails at collision detection.
Read more →
Deep Dives·4 min
How Dangerous Are Windsurf Account-Switching Plugins? A Deep Dive into Technical Principles and Security Risks
Deep analysis of Windsurf seamless account-switching plugin's technical implementation, revealing risks of account bans, code theft, and legal liability. Four compliant alternatives for developers.
Read more →
Tutorials·3 min
3 Prompting Strategies to Guide AI Toward Original Solutions | With Rocket Thruster Case Study
How to use prompt engineering to make AI break from conventional solutions and create unique paths? This article details three strategies—exclusion, constraint-driven, and multi-round iteration—with a real generative design rocket thruster case.
Read more →
Product Reviews·3 min
MiniMax M2.7 Hands-On Review: Coding Ability Rivals Claude Opus at 50x Lower Cost
In-depth hands-on review of MiniMax M2.7 agentic model: coding ability rivals Claude Opus 4.6 at 50x lower input cost. Real-world tests include MacOS system generation, game dev, and dynamic landing pages.
Read more →