Re:Watching o3 guess a photo's location is surreal, dystopia...
by sally_glance on Monday April 28, 2025 @10:18PM
(#43828137)
Fascinating - I just got a little lost thinking about how and why you selected this exact image. If you were able to select a single image containing the maximum aggregate count of unique features for any given location and describe them textually, that would make a very useful training data set... for competitive geoguessr and neural networks alike!
[ Parent
| on HN ]
Re:Watching o3 guess a photo's location is surreal, dystopia...
by SamPatt on Monday April 28, 2025 @11:51PM
(#43828543)
I have had so many ideas related to this. Particularly around automation.
Because the way the community arrives at meta knowledge and its geographical distribution is very informal. There are quite a few false metas out there, or the commonly understood range of the meta is inaccurate.
What needs to happen is automated image recognition and mapping of the metas. I started building an open source tool that allows for people to do this manually, but it's quite a difficult project to do myself and I'm not pursuing it anymore. But I would like to see a less manual process emerge.
Re:Watching o3 guess a photo's location is surreal, dystopia...
by sally_glance on Saturday May 03, 2025 @04:25PM
(#43881973)
Do you have a link? I'm curious what your approach to mapping the metas is... I guess somehow identify features and their frequency of appearing in images, then clustering them?