LLM translation plus per-language glossaries: a localization workflow that works

Josikinz · x · 2026-09-14

The author discovered his Subjective Effect Index and PsychonautWiki content had been translated into Chinese 3 years ago and is widely used in China's biohacking subculture, revealing the power of localization.

He's now testing a system where the English dataset is the baseline, auto-translated via a custom pipeline. His key insight: since machine translation is largely solved, human effort should go into building standardized per-language glossaries (effect labels, categories, community lexicon). Early experiments show translation works well with consistent terminology. He's seeking volunteer translators for languages beyond Polish, German, French, Czech and Dutch.

Original post →

More from coding & agent

coding & agent channel →