Open Source.

The visual prelude to llm-from-scratch: building from a single vector all the way up to the attention mechanism, one geometric move at a time. Every page answers a single why — drag a slider, change a parameter, watch the geometry shift, then one line ties it straight back to LLMs. From vectors and matrices through SVD, softmax, and cross-entropy to self-attention and the Transformer block — 35 interactive lessons across 9 parts, so you understand the math behind training, fine-tuning, and inference instead of just calling an API.

A from-scratch LLM course in Chinese: build a Transformer by hand, line by line, starting from a character-level bigram and working all the way up to reproducing GPT-2 124M — with interactive in-browser visualizations at every step. Aimed at readers who want to understand attention, training, and sampling by writing the code, not just calling an API.

The visual counterpart to the LLM courses, turned on algorithms themselves: drag a handle, watch a sorting pass or a graph traversal rearrange, and read off the geometric idea underneath. A living notebook in Chinese that grows one algorithm at a time, for readers who want to see why an algorithm works instead of memorizing its steps.

Treats IELTS not as an English exam but as a scoring system you can reverse-engineer: starting from the official band descriptors and working backwards to what each of Listening, Reading, Writing, and Speaking actually rewards — covering score-allocation strategy, question-type maps, speaking and writing frameworks, and a diagnose → prescribe → retrain prep loop. Written in Chinese, for everyone heading out into the world.

Audits whether a paper's references actually exist and, for claim citations, whether the cited paper really supports the claim. The first run swept all 209,985 references in the ACL 2026 proceedings (4,459 papers): only 2 came back confirmed nonexistent (0.001%), so fabrication is not the real problem, while 16% of papers carry at least one confirmed unsupported citation. It publishes its own first-pass precision (13%), because the number-one enemy of automated citation checking is its own false positives.

A lightweight task-specification format for AI-assisted development. Instead of heavyweight specs or no spec at all, nano-spec captures just enough intent — goal, constraints, acceptance — in a tiny document the model and you can both hold in your head, so agents build the right thing on the first pass.

A curated collection of specialized AI coding agents and slash commands for Claude Code and other AI coding tools — the same workflows I use in production, packaged so you can drop them into your own setup.

Scans your local Claude Code and Codex usage and renders a GitHub-style coding heatmap — both as an embeddable badge and a shareable HTML report, so you can see when and how much you actually code with AI assistants.

One-command TLS certificates for heterogeneous fleets. Auto-detects the nginx flavor (standard / LNMP / BT panel), gives you unified observability (doctor / status), and falls back across CAs (ZeroSSL → Let's Encrypt) — built for ops managing many servers that were never set up the same way twice.