There is no Red Tomb: making a 1B model write walking quests without making things up
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass What I Built "Go touch grass" is good advice that rarely works, because a walk with no destination loses to the couch every time. What gets people out of the house is a reason: a dog that needs walking, a kid who needs tiring out, a thing to go and see. Sidequest gives a walk a reason. You tell it three…
This article discusses a project called Sidequest, which creates walking quests using real-world locations and a language model called Gemma. The project is part of the Hacktoberfest Open-Source AI Challenge Week 1. The author explains that Sidequest takes inputs such as location, duration, and who is joining the walk, then uses OpenStreetMap data to identify interesting real-world features within reach.
It then generates a short, 1 to 3 stop walking quest with a brief task for each stop, which is written by Gemma running in the user's browser. The user can then follow the directions and complete the tasks at each stop, even in areas with limited signal. The article also mentions a demo of the project at vanshajpoonia.github.io/sidequest and the GitHub repository for the code.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
