LeoQin

AI safety requires distinguishing saints from sycophants and schemers during training.

Distinguishing Saints from Sycophants and Schemers

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.

MCP Is Infrastructure, Not the Ultimate AI Solution

A practical guide to web scraping that starts with robots.txt and data-use boundaries, then compares requests, aiohttp, Scrapy, and Playwright before covering anti-bot handling, parsing, retries, and data quality.

Web Scraping 101: Permissions, Tools, and Anti-Bot Lessons

A plain-language explanation of shader compilation: what shaders are, why GPU-specific machine code must be built locally, how graphics APIs changed the workflow, and why the first launch can take several minutes.

What Does “Compiling Shaders” Mean in Games?

Using linked-list insertion and binary-tree traversal as examples, this post argues that algorithm learning works better when you draw the structure, simulate the steps, explain the invariant, and only then write code.

Learning Algorithms: Understand First, Code Second

Auto-scroll in an AI chat is not just scrollTop. It needs intent signals, a follow/free state machine, handling for programmatic scroll events, virtualization, and mobile edge cases.

Auto-Scrolling AI Chats: How to Read User Intent

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.

Avoid Overusing React useEffect

Based on hands-on use of Copilot, Cursor, and Claude Code, this post separates where AI assistants help most, such as search, boilerplate, and error diagnosis, from where they still struggle, such as architecture and edge cases.

How AI Coding Assistants Actually Improve Developer Efficiency

A grounded overview of AI as systems that perceive, understand, decide, and learn, with a short history from Turing and Dartmouth to deep learning and generative AI, plus a practical view of how it affects daily life.

What Is AI, and How Is It Changing Everyday Life?

A product and architecture walkthrough for Statsify Finance, covering its analysis, strategy, article, search, and finance-term pages, plus the Next.js, Tailwind, Ant Design, ECharts, MongoDB, and TypeScript stack behind it.

Statsify Finance: Technical Breakdown

This article will deeply analyze the auto-scroll mechanisms of major AI applications, examining project data and technical documentation to provide developers with a comprehensive technical guide on creating smooth user experiences while ensuring performance.

How to improve user experience in AI chats?

Using OpenAI’s move from Next.js to Remix as the case study, this post compares the two React frameworks around data loading, server rendering, hydration costs, and when each one is a better fit.

Next.js or Remix: What OpenAI’s Migration Suggests

A short note on completing BlueDot Impact AI Safety Fundamentals, receiving the certificate, and sharpening my direction toward agent safety evals, tool-use safety, and reliable AI infrastructure.

Finished BlueDot AI Safety Fundamentals

Technology

Essays

Current Affairs

Projects

BIPH Flora

A modern full-stack plant identification web application dedicated to providing users with a comprehensive platform for plant identification, sharing, and learning.

Statsify Finance

A finance tool for both beginners and professionals.

Law AI

AI-powered legal assistant with Auth0 FGA fine-grained authorization, sources answers from a document database (RAG) while enforcing document-level access based on user role and department.