Personal technical knowledge base

Leo Qin’s Blog

AI safety, systems engineering, and tools tested against reality.

LeoQin is talking here.

Start here

A short path into the main questions and work on this site.

Completed BlueDot AI Safety Fundamentals

Completed BlueDot AI Safety Fundamentals

After completing BlueDot Impact AI Safety Fundamentals and receiving the certificate, I have a clearer view of agent safety evals, tool-use safety, and reliable AI infrastructure.

2026-6-15Essays
MCP Is Infrastructure, Not the Ultimate AI Solution

MCP Is Infrastructure, Not the Ultimate AI Solution

MCP standardizes how AI apps connect to tools, resources, prompts, and external systems. It is useful infrastructure for reducing integration glue, but it does not replace permissions, confirmations, logging, threat modeling, or tool-safety design.

2025-4-1Technology

Topic hubs

Browse by durable questions instead of publication date alone.

Topic hubs

Latest articles

Developed arguments, practical guides, and research notes.

Open archive
Avoid Overusing React useEffect

Avoid Overusing React useEffect

useEffect is useful for side effects outside rendering, but too many effects turn a component into a dependency maze. This post uses a concrete dashboard example to show when to extract custom hooks or move data fetching elsewhere.

2024-12-10Technology

Follow updates

Track new articles, research, and notes through open feeds.

About

Hello

About