Projects
View allEta - A fast embedded JS template engine. Widely used with 1.5K+ GitHub stars and ~1M weekly downloads.
TypeScript, microbundle, Jest, GitHub Actions • GitHub
tokka-bench - Benchmark and compare tokenizers across many languages with interactive visualizations and analysis.
tokenizers, streamlit • GitHub
shade - PyTorch-like computation library for TS/JS using WebGPU (Work in Progress).
Deno, WGSL • GitHub
Recent Posts
View all12 min read
Introducing tokka-bench
A comprehensive evaluation framework for comparing tokenizers across human and programming languages.
#ml/ai#linguistics#open-source
2 min read
Nix macOS Starter: Declarative Development Setup with Mise
Starter Nix config for macOS using nix-darwin, home-manager, and mise.
#open-source
3 min read
Dialects for Humans: Sounding Distinct from LLMs
Humans are developing new linguistic patterns to distinguish themselves from AI-generated content, and the rate of change will accelerate.
#ml/ai#linguistics