Writing log71 posts289 tagslatest Oct 23, 2026
Posts.
I take large codebases apart and write down how they actually work.
Latest posts
Analyzing DeepSeek Harness: How Do You Build an Agent Harness Where "Everything Is a Plugin"?
DeepSeek Harness (dsh) turns the model adapter, the tool registry, the session log, and even the agent loop into Cordis plugins, then assembles the product by stacking patch layers on top of an empty tree. Two weeks after release it passed 200k GitHub stars. This is a source-level analysis of its kernel (Cordis), profile and bundle composition, the rule that the session log is the source of truth, capability seams, self-modification tools, and the way it runs Claude Code and Codex as subagents.
Is Rails Slow? I Built the Same Blog API Eight Times to Price the Framework
"Rails is slow" is an unanswerable question, because a Rails app and a Go app are never doing the same work. So I narrowed it: inside one runtime, what do the framework and the ORM cost? Four runtimes, each built twice, all returning identical JSON from the identical four SQL statements, measured three times on Docker Linux with MySQL. The abstraction cost in CPU per request came out at ×7.67 for Ruby, ×6.14 for Python, ×2.62 for Node and ×2.51 for Go — and I counted, object by object, exactly what Active Record builds on every request.
Why I Made Markdown the Source of Truth — Building a Dashboard with an AI Agent
A retrospective on building a macOS desktop app (Tauri + Rust + React) with an AI agent. The decision to make markdown files — not the database — the source of truth, the research I did before writing any code, the features I chose not to build, and the macOS permission bug that took the longest to crack. A story about judgment more than code.
spec-kit vs superpowers: Two Ways to Give a Coding Agent a "Process"
GitHub's spec-kit and Anthropic's superpowers plugin both force a workflow onto coding agents so they never drift into vibe coding. But one is a spec-first file system that leaves the specification behind as an artifact in a .specify/ directory, while the other is a collection of discipline prompts lazily loaded through the Skill tool. We compare the two projects across distribution model, artifact philosophy, token cost, and extensibility.
Checking Duplicate IDs Among Billions — Is a Bloom Filter Really the Answer?
A clear explanation of how Bloom filters work, how to use them correctly for user-ID duplicate checks during sign-up, and a concise implementation example.
LLM Basics: RNNs and Sequential Processing
Explains how RNNs — the dominant architecture before Transformers — process sequences token by token, and the fundamental limitations that motivated moving beyond them.
LLM Learning Basics: Masked Language Model
Explains BERT's core training objective — the Masked Language Model — with formulas, commentary, and examples.
LLM Learning Basics: Pre-training and Fine-tuning
Explains large-scale pre-training and task-specific fine-tuning through the lens of the BERT workflow.
RedisBloom in Production: Fast, Safe Duplicate-ID Checking for User Signup
A practical guide to integrating RedisBloom into a signup duplicate-check flow, covering request routing, sharding, synchronization, rebuild strategies, and monitoring.
Transformer Basics: Encoder and Decoder
A clear explanation of what the Transformer encoder and decoder each do, grounded in the original architecture and illustrated with simple examples.