[KongchangAI]

All articles

38460 articles

Phone + Claude Code: Building an iNaturalist Observation Tool with Zero Servers — Full Workflow
Tutorials
·3 min

Phone + Claude Code: Building an iNaturalist Observation Tool with Zero Servers — Full Workflow

Simon Willison built a complete iNaturalist observation tool during camping using his phone and Claude Code. A deep dive into the three-layer architecture: Python CLI, Git Scraping, and AI-generated frontend — all on GitHub with zero servers.

Read more →
ComfyUI-Copilot: An AI Assistant for Building Stable Diffusion Workflows with Natural Language
Product Reviews
·4 min

ComfyUI-Copilot: An AI Assistant for Building Stable Diffusion Workflows with Natural Language

ComfyUI-Copilot is an open-source AI assistant plugin supporting natural language workflow building, smart node recommendations, and parameter optimization. With 5,100+ GitHub stars, it dramatically lowers the barrier to Stable Diffusion workflow creation.

Read more →
Kortix Open-Sources Agent Computer Use: A Rust-Powered CLI Tool for AI Computer Control
Deep Dives
·4 min

Kortix Open-Sources Agent Computer Use: A Rust-Powered CLI Tool for AI Computer Control

Kortix AI open-sources Agent Computer Use, a high-performance Rust CLI tool enabling AI agents to control computers. Explore its architecture, advantages over Anthropic's Claude Computer Use, and future of open-source computer control tools.

Read more →
TRE Regex Engine Python Binding in Practice: From Principles to ReDoS Defense
Product Reviews
·3 min

TRE Regex Engine Python Binding in Practice: From Principles to ReDoS Defense

Deep dive into TRE regex engine's backtracking-free design, Python ctypes binding implementation, and ReDoS defense testing compared to Python's re module for security-sensitive applications.

Read more →
Simon Willison's Complete Process of Building an iNaturalist Observation Gallery with Phone + Claude Code
Product Reviews
·3 min

Simon Willison's Complete Process of Building an iNaturalist Observation Gallery with Phone + Claude Code

Simon Willison built an iNaturalist observation gallery using only his phone and Claude Code while camping. A breakdown of the three-layer architecture: Python CLI clustering, Git Scraping automation, and AI-generated frontend.

Read more →
awesome-LLM-resources: A Deep Dive into GitHub's 8K-Star Comprehensive LLM Learning Resource Repository
Product Reviews
·3 min

awesome-LLM-resources: A Deep Dive into GitHub's 8K-Star Comprehensive LLM Learning Resource Repository

Deep dive into awesome-LLM-resources, a GitHub 8K-star project covering multimodal AI, AI Agents, MCP protocol, model training/inference, and AI coding tools — a one-stop LLM learning guide.

Read more →
LangGraph Multi-Agent Company Research Tool: A Practical Guide to Open-Source AI Due Diligence
Tech Frontiers
·3 min

LangGraph Multi-Agent Company Research Tool: A Practical Guide to Open-Source AI Due Diligence

Deep dive into the open-source company-research-agent: LangGraph multi-agent architecture + Tavily search + dual-LLM collaboration for automated company due diligence and competitive intelligence.

Read more →
LLM CLI 0.32a1 Released: Fixes Tool-Calling Session Storage Bug
Tech Frontiers
·2 min

LLM CLI 0.32a1 Released: Fixes Tool-Calling Session Storage Bug

Simon Willison's open-source CLI tool LLM releases v0.32a1, fixing a data integrity issue when restoring tool-calling sessions from SQLite. Learn about the fix, core features, and how to update.

Read more →
SVDQuant: 4-bit Quantization Enables Efficient Diffusion Model Inference on Consumer GPUs
Research
·3 min

SVDQuant: 4-bit Quantization Enables Efficient Diffusion Model Inference on Consumer GPUs

SVDQuant, an ICLR 2025 Spotlight paper, achieves 4-bit diffusion model quantization via low-rank decomposition that absorbs outliers, reducing memory by 75%. Open-source engine Nunchaku (3800+ stars) enables FLUX inference on consumer GPUs like RTX 4060.

Read more →
LLM 0.32 Refactor: How Message Sequences and Streaming Chunks Are Reshaping Python LLM Interactions
Deep Dives
·3 min

LLM 0.32 Refactor: How Message Sequences and Streaming Chunks Are Reshaping Python LLM Interactions

Simon Willison releases LLM 0.32a0 alpha with message sequences and typed streaming chunks, redefining how Python developers interact with LLMs while maintaining full backward compatibility.

Read more →
Data Centers Taking Over Farmland? The Data Reveals This Is an Overblown Non-Issue
Industry Insights
·2 min

Data Centers Taking Over Farmland? The Data Reveals This Is an Overblown Non-Issue

Are data centers really consuming farmland and threatening food security? This article uses real data to analyze the U.S. data center land use debate, revealing that farmland loss to data centers is just 1/77th of what farmers sell voluntarily.

Read more →
Agent, MCP, and Function Calling: A Complete Guide to Their Differences and Relationships
Deep Dives
·4 min

Agent, MCP, and Function Calling: A Complete Guide to Their Differences and Relationships

A deep dive into the relationships between AI Agent, MCP protocol, Function Calling, and Prompt. From basics to full architecture, build a clear cognitive framework for AI app development.

Read more →
Building an AI Digital Human Agent from Scratch: Architecture Design & Full Technical Breakdown
Tutorials
·3 min

Building an AI Digital Human Agent from Scratch: Architecture Design & Full Technical Breakdown

Complete guide to building an AI digital human Agent, covering Agent, RAG, WebRTC, and Docker deployment with architecture design and engineering best practices.

Read more →
Altman Takes the Stand: Winning the Courtroom Presence, But Maybe Not the Case
Tech Frontiers
·2 min

Altman Takes the Stand: Winning the Courtroom Presence, But Maybe Not the Case

Sam Altman testified in the OpenAI lawsuit, facing Elon Musk's accusation of "stealing a charity." Analysis of his courtroom performance, key evidence, and implications for AI governance.

Read more →
Datasette 1.0a29 Released: Fixing a Gnarly Segfault Race Condition with GPT-5.5
Tech Frontiers
·2 min

Datasette 1.0a29 Released: Fixing a Gnarly Segfault Race Condition with GPT-5.5

Datasette 1.0a29 preview released, fixing a segfault race condition introduced by test optimization. Developer Simon Willison used GPT-5.5 xhigh to help reproduce the issue, showcasing AI debugging in practice.

Read more →
Codex Adds OpenAI Developers Plugin — Building AI Apps with AI Just Got Easier
Tech Frontiers
·2 min

Codex Adds OpenAI Developers Plugin — Building AI Apps with AI Just Got Easier

OpenAI Codex adds the Developers plugin, letting developers directly access OpenAI API docs and best practices to rapidly build AI Agents and smart apps.

Read more →
OpenAI Codex Adds Computer Use: AI Agents Autonomously Control Mac in the Background
Tech Frontiers
·3 min

OpenAI Codex Adds Computer Use: AI Agents Autonomously Control Mac in the Background

OpenAI adds Computer Use to Codex, enabling AI agents to autonomously click, type, and operate across Mac apps in the background without taking user control.

Read more →
OpenAI Symphony: One Codex Agent Per Task — A New Paradigm for Multi-Agent Parallel Programming
Tech Frontiers
·2 min

OpenAI Symphony: One Codex Agent Per Task — A New Paradigm for Multi-Agent Parallel Programming

Deep dive into OpenAI's Symphony: assigning an independent Codex agent to each task for multi-agent parallel programming. Explore its architecture, developer impact, and industry trends.

Read more →