01How it works
02Story
I wanted to see how much geography a language model knows, and whether I could get exact coordinates just by asking. It works for "where is Paris?" and for "places that smell like candy".
03Lessons
A vibe goes in and numbers come out, numbers a map can use.
LLMs are surprisingly good at geography, even small local ones. The trick is not asking for text at all: ask for a fixed JSON shape.
It even grades its own answers. Take those grades with some salt.
04Tech
The model answers in a forced JSON schema with names and coordinates, and code turns them into map pins. Bigger models pick more creative places; small ones still get the coordinates right.
05Try this
- Ask for something weird, like places that smell like candy
- Ask for a list: all the European capitals
- Describe a feeling instead of a place