#ITER

1446 related articles

2026年6月17日·3 min

GLM-5.2 Deep Dive: Million-Token Context, MIT Open Source & Full-Stack Domestic Chip Training

Deep dive into Zhipu's GLM-5.2: truly usable 1M-token context, MIT open-source strategy, full-stack Huawei Ascend training, and how it compares to Claude Opus. Includes benchmarks, use cases & pricing.

2026年6月17日·3 min

Compile First: Using AI to Revive the Dormant Files on Your Hard Drive

Explore how the open-source LLM Wiki project uses a compile-first paradigm to turn dormant local files into a searchable AI knowledge base, compared with traditional RAG approaches.

2026年6月17日·3 min

Replicating Slay the Spire with AI and Zero Code: A Complete Walkthrough from Architecture to Art

A Bilibili creator used Godot and AI tools to replicate Slay the Spire with zero hand-written code. Full walkthrough of architecture-first AI coding and batch art generation.

2026年6月17日·3 min

Claude Generates 10 Web Games from One-Line Prompts: Zero-Code AI Programming in Action

Use Claude Code to generate 10 web games like 2048, Gomoku, and Tetris from one-line prompts — zero manual coding. A full walkthrough of AI programming in practice.

2026年6月17日·2 min

Mistral Le Chat Image Generation Review: Can It Replace Fable?

Mistral AI launches image generation in Le Chat, dubbed Le Chaton Fat. We analyze its capabilities, compare it with Fable, and explore the trend of AI chat platforms integrating image generation.

2026年6月17日·3 min

Testing DeepSeek's Safety Mechanisms: Multiple Jailbreak Attempts Successfully Blocked

An overseas security blogger systematically tested DeepSeek's jailbreak resistance using direct requests, rephrased prompts, and varied strategies. Results show robust intent recognition, consistent blocking, and context-aware safety mechanisms.

2026年6月17日·3 min

A Middle Schooler with Zero Coding Skills Built a Story-Driven Game with AI: Creativity Unshackled from Technical Barriers

A middle schooler with no coding experience used AI to build an interactive story game with branching choices and surreal alien adventures. We explore what this means for creative democratization.

2026年6月17日·3 min

Microsoft Build 2026: In-Depth Analysis of the In-House Reasoning Model MAI Thinking-E and the Full AI Product Suite

Microsoft Build 2026 unveils MAI Thinking-E, its first in-house reasoning model with 1T MoE architecture, plus 6 vertical AI models. Deep dive into performance, strategy, and industry trends.

2026年6月17日·3 min

Deep Dive into Claude Sonnet 4: Replicating Lovable with Just Two Prompts

Deep dive into Claude Sonnet 4: replicate Lovable with two prompts, generate McKinsey-grade reports, build 2D games, and explore the AI Agent building block economy.

2026年6月17日·2 min

Replit's Domain-Specific Agents: One-Click Batch Fixes for SEO and Security Vulnerabilities

Deep dive into Replit's domain-specific AI Agents: Growth Agent for SEO issues and Security Agent for vulnerability detection, with select-all one-click batch fixing.

2026年6月17日·3 min

CosyVoice v3.5 in Practice: Solving the Performance Direction Challenge in AI Voice Acting

Hands-on testing of Alibaba's CosyVoice v3.5 instruction control and pronunciation correction vs Doubao TTS stability issues, with voice design tips and LLM debugging methodology for AI voice acting.

2026年6月17日·4 min

Claude Code Practical Guide: From Installation & Configuration to Production-Ready Business Projects

Complete guide to Claude Code + Opus setup via CCSwitch for unified model management. Real-world case: payment system built in 4 hours with zero hand-written code, covering installation, Prompt engineering, and model selection.

2026年6月17日·3 min

Andrew Ng and Anthropic's Definitive Claude Code Tutorial: A Deep Dive

Andrew Ng and Anthropic launch a Claude Code course covering context management, parallel sessions, MCP server integration, and hands-on projects in RAG, data analysis, and Figma-to-code conversion.

2026年6月16日·3 min

GML 5.2 Multimodal Upgrade Hands-On: Full Validation with DeepSeek V4

Hands-on testing of GML 5.2 and DeepSeek V4 multimodal upgrades on OneBlockBase, covering vision-text workflows, safety mechanisms, and deployment tips.

2026年6月16日·3 min

5 Steps to Connect Codex with DeepSeek — No GPT Account Required

Step-by-step tutorial: Connect Codex to DeepSeek API via CC Switch in 5 steps. No GPT account needed — use AI coding features like code completion and Skill plugins at lower cost.

2026年6月16日·3 min

N2 Model as a Free Claude Code Alternative: Does Voice-Driven AI Coding Actually Work?

N2 model, built on Qwen 3.5, is completely free and integrates with Claude Code. Real-world tests show voice commands generating full landing pages, with AgentOS enabling shared memory and multi-model collaboration for zero-cost AI coding.

2026年6月16日·3 min

Claude Code Skills Mechanism Explained: On-Demand Loading for Token Savings and Better Performance

Deep dive into Claude Code's Skills mechanism: on-demand loading replaces bulk context dumping, cutting Token costs and boosting output quality with modular expertise.

2026年6月16日·3 min

What Is Claude Code? Five Key Differences from Regular AI Chatbots

Explore the five key differences between Claude Code and regular AI chatbots like ChatGPT and DeepSeek — from interaction, context, execution, memory, to tool integration.

2026年6月16日·3 min

Claude Code vs Codex: A Deep Comparison — Who Wins When the Tech Converges

Deep comparison of Claude Code vs OpenAI Codex across first-mover advantage, architecture, market share, and reliability. Discover what truly matters when AI coding tools converge.

2026年6月16日·3 min

5 Daily Claude Code Tips: Let AI Interrogate You Instead

5 daily Claude Code tips: Grill Me for requirements, Brainstorming for architecture, Writing Plan for execution, TDD for testing, and Debugging for precise fixes — a complete AI coding workflow.