← Back to feed

Can AI draw San Francisco from memory? Six LLMs, scored against OpenStreetMap

AI · Studies · 2026-10-19 15:24

该项目让六个大语言模型仅凭记忆绘制旧金山地图，再与OpenStreetMap数据比对评分，以考察模型的空间认知能力。

Source: github.com

Auto-generated summary for reference only. RSS