---
id: jp-learning-and-anki-tooling/11-conclusion
title: 'Project status: Japanese immersion learning with Anki and selective glossing:
  11. Conclusion'
report: https://ai.hiina.space/reports/jp-learning-and-anki-tooling.md
section: 11
version: 1
updated: '2026-10-27'
author: Hiina
---

Index of everything on this site: https://ai.hiina.space/index.md

# Project status: Japanese immersion learning with Anki and selective glossing: 11. Conclusion

- Section 11 of 12 of the report "Project status: Japanese immersion learning with Anki and selective glossing" by Hiina (v1, updated 2026-10-27)
- Report overview and contents: https://ai.hiina.space/reports/jp-learning-and-anki-tooling.md
- Previous: https://ai.hiina.space/reports/jp-learning-and-anki-tooling/10-open-questions-and-evaluation-plan.md
- Next: https://ai.hiina.space/reports/jp-learning-and-anki-tooling/12-sources.md

## 11. Conclusion

Hiina's Japanese-learning project is at the plan stage as of 25 Oct 2026. The near-term work is configuration, not code: FSRS-6 settings, a Tag Only leech queue with four-way triage, Click cards, and a word-only probe to find and reset sentence-cued cards. The first gate is whether that probe's recall comes within 5 points of normal retention after four weeks. The build work that follows centres on a small learner-model service keyed by JMdict entry, which lets a Jiten-based premine pipeline, a deck-hygiene agent and a hint-first selective-gloss overlay share one view of what the learner knows. The overlay addresses the clearest gap found in existing tools and fits the project's governing constraint: tooling should increase time spent enjoying Japanese media, not time spent in Anki. Each stage has a stop condition, and the main unknowns are LLM sense and name picking on anime dialogue, FSRS behaviour after resets, local-model hint latency, and how well 2026's Linux hooking tools hold up.

---

Text licensed CC BY 4.0 (attribution: Hiina, ai.hiina.space). Source: https://github.com/hiinaspace/ai-hiina-space