Walking Challenge AI: An Open-Source AI That Sends You Outside 🚶

Описание и применение

Приложение Walking Challenge AI генерирует реальные задания для прогулок, используя модель Qwen2.5 Instruct в браузере, не требуя серверов и ключей API, и мотивирует студентов выйти на улицу.

Задача

Students spend most of the day on screens and need a simple, fun reason to step outside.

Результат

The app provides a quick, privacy‑preserving way to generate walking challenges, encouraging users to step outside without relying on external APIs or servers.

Рабочий процесс

• Choose walk time (10‑60 min), place (park, city, college, neighborhood) and difficulty (easy, medium, hard).
• The app builds a prompt and sends it to an open‑weight Qwen2.5 Instruct model running in the browser via Transformers.js.
• If the model output is unusable, the app falls back to a hand‑written bank of challenges.
• Walk, tick off completed challenges, and finish.
• The first run downloads the model (~1.2 GB) and caches it for future use.

Доказательства

Walking Challenge AI is a small web app that turns an ordinary walk into a game.

Источник

An open-weight model (Qwen2.5 Instruct) runs in your browser with Transformers.js and writes your challenges.

Источник

The first run downloads the model (about 1.2 GB), so use Chrome or Edge and give it a minute.

Источник