Openai Models Have Gotten Worse at Geolocation
Posted4 months agoActive4 months ago
bellingcat.comTechstory
calmmixed
Debate
20/100
AI DevelopmentGeolocationAI Safety
Key topics
AI Development
Geolocation
AI Safety
A Bellingcat analysis found that OpenAI models have worsened at geolocation tasks, sparking discussion on the potential tradeoff between AI accuracy and safety.
Snapshot generated from the HN discussion
Discussion Activity
Light discussionFirst comment
5h
Peak period
1
5-6h
Avg / period
1
Key moments
- 01Story posted
Sep 16, 2025 at 4:45 PM EDT
4 months ago
Step 01 - 02First comment
Sep 16, 2025 at 10:15 PM EDT
5h after posting
Step 02 - 03Peak activity
1 comments in 5-6h
Hottest window of the conversation
Step 03 - 04Latest activity
Sep 16, 2025 at 10:15 PM EDT
4 months ago
Step 04
Generating AI Summary...
Analyzing up to 500 comments to identify key contributors and discussion patterns
Discussion (1 comments)
Showing 1 comments
MrCoffee7
4 months ago
I think there is a strong possibility that the worsened geolocation abilities will continue as there is a tradeoff in AI models between accuracy and AI safety/risk concerns. AI companies will be under increasing pressures to boost AI safety which may well cause a hit to AI accuracy.
View full discussion on Hacker News
ID: 45267786Type: storyLast synced: 11/17/2025, 2:08:20 PM
Want the full context?
Jump to the original sources
Read the primary article or dive into the live Hacker News thread when you're ready.