Loading page...Загружаем страницу...正在加载页面...
AtlasRepo

OweMyGod: a fine‑tuned 8B model reads Jakarta debt excuses right 92% of the time (keyword rules: 60%)

Описание и применение

OweMyGod использует 8‑байтовую модель Qwen3, обученную на синтетических и реальных ответах, чтобы автоматически интерпретировать неформальные оправдания друзей и планировать напоминания о долгах в ИНДОНЕЗИИ, снижая когнитивную нагрузку и сохраняя дружеские отношения.

Задача

Friends who lend money in Jakarta struggle to chase repayments without damaging relationships.

Результат

Fine‑tuned Qwen3‑8B achieved 92% exact‑date accuracy and 100% kind‑right accuracy on 25 hand‑written Jakarta debt excuses, outperforming keyword rules (60% accuracy) and the untrained model (68%). The app reduced early reminders from 14% to 8% and prevented over‑nagging by limiting reminders to one per 3 days.

Рабочий процесс

  • 1. User logs debts and partial payments in the app.
  • 2. User copies a friend’s excuse from WhatsApp into the app.
  • 3. The LLM parses the excuse and outputs a "kind" and "when" JSON.
  • 4. Python code converts the "kind" into an exact date based on user’s timezone and settings.
  • 5. A schedule engine decides the next reminder time and drafts a tone‑appropriate WhatsApp message.
  • 6. The app sends a single 09:00 push notification when a debt is due or a promise is made for that day.
  • 7. The user reviews the drafted message and sends it via WhatsApp.
  • 8. The app tracks reminders, stops after three firm reminders without response, and suggests in‑person discussion.

Доказательства

The model reads Jakarta slang; code does arithmetic.

Источник

Fine‑tuned v2 (shipped) 92% exact date, 8% too early, 100% kind right.

Источник

The app never sends two reminders within 3 days, and after three firm ones with no answer it tells you to talk in person and stops.

Источник

  • Дата записи: 2026-10-24T10:11:34.465Z