Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

ChatGPT now performs well at GeoGuesser

flausch.social

Post reply on HN
Print view View original

141–150 of 152 posts

Re: ChatGPT now performs well at GeoGuesser

#141

Post by xzjis »

actuallyalys wrote: post #21

It wouldn’t shock me if multimodal LLMs were good at GeoGuesser [0], but if we’re being picky, it takes more than a few examples to demonstrate a game is “solved.” I also wonder what kind of data leakage might have been at play, like other people have suggested. To be clear, my point is not that this is unimpressive, just that this doesn’t demonstrate much. (Edit: I should have said, it doesn’t demonstrate what the t…

I uploaded a picture I took, I don't save GPS coordinates on my pictures, but the first thing ChatGPT did is to read exif data from it.

Re: ChatGPT now performs well at GeoGuesser

#142

Post by dharmab »

Reubend wrote: post #127
littlecranky67 wrote: post #121

I've been telling women to keep copies of all the dick pics they get sent. Since you can tell by the characteristic noise of a cameras sensor which other pictures were taken with the same camera. All missing is a search engine capable of doing this. I feel with AI, we are 2-3 years away from people uploading a dick pic to AI and getting the social media profile of that person...

Can you share some sources? I would be extremely surprised if such fine grained noise survives imagine compression to the extent that you could identify the source of an imagine despite changing lighting conditions, locations, exposure times, etc

A kagi search found this paper that achieved decent results on youtube compression, 5 years ago https://arxiv.org/abs/2012.06277

Re: ChatGPT now performs well at GeoGuesser

#144

Post by abletonlive »

wruza wrote: post #126
abletonlive wrote: post #85

Earlier quoted context omitted.

If you're going to make such an assertive statement you should maybe backup that claim with some substance. Without such, it's akin to an atheist proudly proclaiming there is definitely no such thing as god.

it's akin to an atheist proudly proclaiming there is definitely no such thing as god Almost feels like you supposed that to sound bad.

Yes because agnostic atheism is a logically superior belief system, that's much more intellectually honest and ironically: humble.

Re: ChatGPT now performs well at GeoGuesser

#145

Post by bryanrasmussen »

AStonesThrow wrote: post #89
yieldcrv wrote: post #73

Earlier quoted context omitted.

Lets fast forward this conversation to its conclusion of “its open to interpretation” and Christianity doesn't have a monopoly on religion or the fungible and unquantifiable soul concept

So the Internet is basically a series of tubes, and http packets are like mustard and ketchup that you pop into the tube, and it zooms along with air-pressure determined by the Chinese government. and then your bank puts dollar bills into the tubes on the Internet, and those tubes connect to vaults and safes underground, and that is how money gets into your account. Money doesn't come out of your account; it's just c…

sure - and

"The Unicorn is most particular in its affections and has a fondness for beautiful virgins..."

https://medium.com/luminasticity/meditation-on-the-unicorn-d...

Re: ChatGPT now performs well at GeoGuesser

#146

Post by littlecranky67 »

Reubend wrote: post #127
littlecranky67 wrote: post #121

I've been telling women to keep copies of all the dick pics they get sent. Since you can tell by the characteristic noise of a cameras sensor which other pictures were taken with the same camera. All missing is a search engine capable of doing this. I feel with AI, we are 2-3 years away from people uploading a dick pic to AI and getting the social media profile of that person...

Can you share some sources? I would be extremely surprised if such fine grained noise survives imagine compression to the extent that you could identify the source of an imagine despite changing lighting conditions, locations, exposure times, etc

There are tons of results (and papers) if you google/kagi: "image noise fingerprint ccd sensor". I smell lazyness here.

Re: ChatGPT now performs well at GeoGuesser

#147

Post by ein0p »

One thing that screws it up is ironically the memory across conversations. I gave it some _really_ obscure photos from some godforsaken ass cracks of the world I've been to, and it was able to guess most of them correctly. However, in its reasoning trace I saw that it's having a heck of a time letting go of the idea that the photo N is not roughly from the same location as the previous photos. What's even more impressive, even when it guesses incorrectly, it can often follow up and guess correctly with minimal hints. And it reasons about it much like a human would, and searches for the same things a human would. Note: I used o3, YMMV with a smaller/weaker model.

Re: ChatGPT now performs well at GeoGuesser

#148

Post by arresin »

CSMastermind wrote: post #135
arresin wrote: post #119

Earlier quoted context omitted.

What about 04-mini-high ?

OpenAI's naming confuses me but I ran o4-mini-2025-04-16 through a game and it got 23,885

Interesting. It supports what they said (this is the model with good visual reasoning)

Re: ChatGPT now performs well at GeoGuesser

#149

Post by wruza »

abletonlive wrote: post #144
wruza wrote: post #126

Earlier quoted context omitted.

it's akin to an atheist proudly proclaiming there is definitely no such thing as god Almost feels like you supposed that to sound bad.

Yes because agnostic atheism is a logically superior belief system, that's much more intellectually honest and ironically: humble.

Aren't beliefs secondary guests in discussions about substance?

Edit: I'm not even a strict atheist if that matters much, but I wouldn't talk about it in assertive/provemewrong tone anywhere, cause it's not even remotely logical.

Re: ChatGPT now performs well at GeoGuesser

#150

Post by namaria »

geysersam wrote: post #118
comex wrote: post #113

Earlier quoted context omitted.

It’s just a hallucination, same idea as o3 claiming that it uses its laptop to mine Bitcoin: https://transluce.org/investigating-o3-truthfulness I doubt the model was trained on Street View, but even if it was, LLMs don’t retain any “memory” of how/when they were trained, so any element of truthfulness would be coincidental.

If it's trained on street view data it's not unlikely that the model can associate a particular piece of context to street view. For example, a picture can have telltale signs that street view content has, such as blurred faces and street signs, watermarks, etc. Even if it's not directly trained on street view data it has probably encountered street view content in it's training dataset.

The training process doesn't preserve information needed for the LLM to infer that. It cannot be anything other than nonsense that sounds plausible, which is what they do best.
Post reply on HN