Infinigram: Variable-Length N-grams via Suffix Arrays

A corpus-based language model using suffix arrays for O(m log n) pattern matching. The corpus is the model.

December 3, 2025 · 3 min read

BTK: Modern Database-First Bookmark Manager

A database-first bookmark manager with NLP auto-tagging, full-text search, and content caching.

November 30, 2025 · 4 min read

N-gram Language Models

The classical approach to sequence prediction: counting and smoothing

August 15, 2016 · 5 min read

Long Echo in Practice: 5,874 Bookmarks in a Single File

Graceful degradation made concrete: years of bookmarks exported to a self-contained HTML app that works offline, forever.

December 18, 2025 · 2 min read

The Long Echo Toolkit

Three CLI tools for preserving your digital intellectual life: conversations, bookmarks, and books. SQLite-backed, exportable, built to outlast the tools themselves.

December 16, 2025 · 5 min read

Discussion