Cited on HN 6 times, 2023–2025, never outright recommendedscore 0
Years with an HN recommendation, 2007–2026
Cited as an early, concrete example of AI outperforming top GeoGuessr players, in threads on AI photo geolocation.
GeoGuessr pro Rainbolt plays head-to-head against an AI built by Stanford students that guesses locations from street-view images. The video shows the AI repeatedly beating him.
“The best player in the world, Rainbolt, played against an AI out of Stanford” (HN, 2024)
Yep, some CS/AI grads from Stanford trained an AI on loads of Street View images and built a bot that is able to beat some of the best Geoguessr players: [this video]
The question is, how does this do at GeoGuessr, where users are given a picture from Google street view, and are asked where it is on the world by clicking on a map of the world. Users get points based on how close it is, user with the most points after N rounds, wins. The best player in the world, Rainbolt, played against an AI out of Stanford, so I wonder how this one would do. [link] [this video]
Some people are really good at GeoGuessr, but also their best performance are more likely to get views. If you want a bot that is extremely strong at geoguessr there is this: [link] One forward pass is probably faster than 0.1 second. You can see its performance here: [this video] (rainbolt is a really strong player)
> Technology can identify locations from photographs now. Tbf, it could do that before, and probably still better than the LLM: [this video] But seeing it as what appears to be an emergent capability in such a general model is something else.
If you watch the video, (one of) the reasons why the AI was winning was because it was using “meta” information from the Street View camera images, and not necessarily because it’s successfully identifying locations purely based on the landmarks in the image. > I realized that the AI was using the smudges on the camera to help make an educated guess here. [0] [this video]
Video list and Hacker News comment labels from HackerTube (prompted by @karpathy), released under ODC-By 1.0, built on the open-index/hacker-news archive. Hacker News data is provided by Y Combinator; comments remain the work of their authors. Video titles, channel names and thumbnails belong to their creators and are shown via YouTube. HackerTube Watch is an unofficial edition. Data export of 2026-10-31.
Plays via YouTube's privacy-enhanced embed
6 Hacker News comments
From the HN archive; up to 20 kept per video, favoring different commenters. Recommendations first.