I gave my iOS reply coach a memory (and what broke)

Описание и применение

Приложение Toneme добавило контекстную память, сохраняя короткие заметки о получателе, но столкнулось с генерацией вымышленных встреч, ограничениями скорости и дублированием заметок.

Задача

The reply coach started each message from zero, lacking context about the recipient and prior interactions.

Результат

The app gained contextual awareness, improving reply relevance, but encountered issues such as model‑generated meeting times, relayer rate limits, and duplicate notes.

Рабочий процесс

• Add opt‑in memory using Walrus Memory
• After each reply, save a short note (e.g., "Nikos is accounting colleague; user writes briefly")
• Recall up to five notes before the next reply
• Provide UI to view, edit, or reset notes
• Store each note as an encrypted blob on Walrus mainnet and link to Walruscan for inspection

Доказательства

Its problem: every message started from zero. It never knew that Nikos is a colleague or that I write to him briefly.

Источник

After each reply, the app saves one short, non-sensitive note ... and recalls up to 5 notes before the next reply.

Источник

The model invented a meeting time.

Источник

The shared relayer rate-limited us.

Источник

Near-duplicate notes piled up.

Источник