alt Hacker NewsI think a vision model like Qwen VLM or sending a screenshot to Claude/Gemini will be easier for the model to reason about. Pictures encode spatial info much more naturally than json.
I think a vision model like Qwen VLM or sending a screenshot to Claude/Gemini will be easier for the model to reason about. Pictures encode spatial info much more naturally than json.
There's an endpoint for that!
https://api.hallucinatingsplines.com/reference#tag/cities/GE...
You can also pull the map tiles as an array: https://api.hallucinatingsplines.com/reference#tag/cities/GE...
Would be interesting to two agents with the same instructions do a "face off" but each only has access to one type of map.