English posts

Build a small AI-style chat with token streaming and cancellation to learn how WebSockets and ASGI work together.

A simple comparison of WSGI and ASGI, using an AI agent that spends most of its time waiting for LLM APIs.

I migrated this personal blog from Gatsby to Astro, but the main goal was to fix long-standing UI problems and simplify the site's structure.

A practical, implementation-level explanation of tool calling, MCP, skills, and why CLI-based agents have become common.

This article picks five notable AI papers from 2025 and summarizes their key ideas and limitations, including reinforcement learning for reasoning, agent benchmarks, long‑task metrics, and a statistical explanation of hallucinations.

These metrics capture coverage and reliability.

Some LLMs disable sampling knobs like temperature and top_p. Here’s why.

A deep dive into how LLMs serialize prompts, output schemas, and tool descriptions into a token sequence, with examples from Llama 4's implementation.

A deep dive into how databases work.

Learn how to extend Claude's capabilities by building your own Model Context Protocol server.