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.
More from coding & agent
- Dev puts a 4,000-customer support inbox on autopilot with agents, stops reading code — natesiggard · 2026-09-14
- Every editor builds a three-skill AI agent pipeline for daily AI briefing — danshipper · 2026-09-14
- Economist slams Claude's coding judgment: skips existing work, denies mistakes, praises Astra — soumitrashukla9 · 2026-09-14
- Developer shares one-shot Replit prompt workflow that generates games with just a genre swap — amasad · 2026-09-14
- Hamel Husain: Codex can already do anything Muse-style agent tools offer — skip the tool sprawl — HamelHusain · 2026-09-14
- DeskRoot Rebuilds AI Assistant Setup as a Folder of Editable Markdown Procedures — KenGuy14 · 2026-09-14