Writing

Longer, more careful pieces: research write-ups, technical papers, and analysis, with the method and references included.

• 

  #weaver#local-first#ai-translation

  Read it

  How I designed Weaver as a local-first translation workspace instead of an AI chat wrapper

  Weaver was built as a local-first translation workspace for Japanese light novels, not as a thin wrapper around an LLM API.

  AnalysisJun 20, 202611 min read
• 

  #sahamlens#llm#local-first

  Read it

  How I integrated an LLM into SahamLens without leaking portfolio data

  This post explains the two-stage LLM pipeline behind SahamLens: local summarisation first, remote analysis second. The goal was to add AI-assisted stock research without sending portfolio positions, trade history, or personal investment context to the model API.

  AnalysisMay 25, 202611 min read
• 

  #sahamlens#duckdb#sqlite

  Read it

  I picked DuckDB over SQLite for SahamLens. Here’s what the trade-off cost me.

  DuckDB turned out to be a better fit than SQLite for SahamLens because the core workload is analytical: scanning historical market data, computing indicators, and preparing research outputs locally.

  AnalysisMay 20, 202611 min read