News for hackers. Stuff that matters.
Re:A new ChatGPT version just dropped and GeoGuesser is now ... by viraptor on Thursday April 17, 2025 @10:41PM (#43724436)
There's various degrees of "solved" here. Identifying a generic area is cool. But I wouldn't call it a "solved problem" until it can consistently beat for example Rainbolt in accuracy. And there's no good comparison of completely random roads posted so far - mainly popular locations.

Basically, it's one thing to pick out a specific thing photographed thousands of times, but another to get a random country side view and pick out all the unique features for a very precise guess.

Re:A new ChatGPT version just dropped and GeoGuesser is now ... by Benjammer on Thursday April 17, 2025 @10:44PM (#43724457)
One problem is how can you even set up a "fair" competition between an AI and Rainbolt? He does ones where it flashes for a fraction of a second and then he guesses the country. How do you simulate "only saw it for a fraction of a second" to an AI?
Re:A new ChatGPT version just dropped and GeoGuesser is now ... by al_borland on Thursday April 17, 2025 @11:01PM (#43724574)
Maybe limit the time the AI is allowed to think? In the post it showed the AI thought for almost a minute.

I’ve seen Rainbolt ID an image based on some dirt and nothing else. I’d want to see AI be able to do that before saying it’s a solved problem.

Re:A new ChatGPT version just dropped and GeoGuesser is now ... by sandermvanvliet on Friday April 18, 2025 @06:18AM (#43726630)
“This is the gradient of Senegal”
Re:A new ChatGPT version just dropped and GeoGuesser is now ... by dewey on Thursday April 17, 2025 @10:58PM (#43724555)
It’s fair, it just means he’s better and AI isn’t there yet.
Re:A new ChatGPT version just dropped and GeoGuesser is now ... by GaggiX on Friday April 18, 2025 @03:59AM (#43725988)
This is probably the best attemp at consistently beating Rainbolt in accuracy: https://youtu.be/ts5lPDV--cU