o3
Article
o3 is a recurring organization in the Astral Codex Ten archive, appearing 5 times across 5 issues between May 02, 2025 and June 26, 2025. The archive places it in contexts such as “people beat o3’s score”; “o3 took over 5 minutes on that one shop name”; “I used o3 with your exact prompt”. It most often appears alongside Nepal, New York, ACX Grants.
Metadata
- Category: Organizations
- Mention count: 5
- Issue count: 5
- First seen: May 02, 2025
- Last seen: June 26, 2025
Appears In
- Testing AI’s GeoGuessr Genius
- Highlights From The Comments On AI Geoguessr
- Sorry, I Still Think MR Is Wrong About USAID
- ACX Grants 1-3 Year Updates
- Missing Heritability: Much More Than You Wanted To Know
Related Pages
-
- Nepal (3 shared issues)
-
- New York (3 shared issues)
-
- ACX Grants (2 shared issues)
-
- Africa (2 shared issues)
-
- Argentina (2 shared issues)
-
- Australia (2 shared issues)
-
- Britain (2 shared issues)
-
- Buffalo (2 shared issues)
-
- California (2 shared issues)
-
- Center for Global Development (2 shared issues)
-
- China (2 shared issues)
-
- Colorado (2 shared issues)
External Links
Source Context
Recovered passages from the original issue text. When the raw archive preserved outbound links inside the source passage, they are listed directly under the quote.
After writing this post, I saw a different way of presenting these same results: GeoGuessr master Sam Patterson went head-to-head against o3 and lost. But only by a little. And he let other people try the same image set, and a few (lucky?) people beat o3’s score. So maybe o3 is at the top of the human range, rather than far beyond it, and ordinary people just don’t appreciate how good GeoGuessng can get.
Inline links: went head-to-head against o3, try the same image set
I tested it on one photo in a French town square with bad lighting. The CoT was both brilliant and curiously stupid. It inferred some correct things from tiny details (subtly different makes of car, barely visible street lines) and guessed the country quickly. But there was a shop name with different letters obscured in two different locations- a human would infer the name instantly. o3 took over 5 minutes on that one shop name, going down many incorrect rabbit holes. It got the exact location in the end, but it took over 15 minutes!
I used o3 with your exact prompt on these 10 images I took each in a separate instance of o3, pasted into paint to remove metadata and it had pretty mixed results, some very good and some not:
No direct inline source block was recovered for this mention.
No direct inline source block was recovered for this mention.
No direct inline source block was recovered for this mention.
Backlinks
- ACX Grants 1-3 Year Updates
- Center for Global Development
- GeoGuessr
- GMU
- Gorak Shep
- Highlights From The Comments On AI Geoguessr
- Kala Pattar
- Missing Heritability: Much More Than You Wanted To Know
- Nepal
- o3
- Organizations: G
- Organizations: O
- People: O
- Sorry, I Still Think MR Is Wrong About USAID
- Testing AI’s GeoGuessr Genius