Hacker News Reader

Comment by jillesvangurp | Hacker News Reader

If you want to exclude memory and exif data, just open streetview in some random corner of the world and take a screenshot (avoiding any text obviously). It's pretty good if you give it enough to reason with.

It basically iterates on coming up with some hypothesis and then does web searches to validate those.

View on HN

I just took a few random spots from around the globe and it got most of them right and some of them incredibly precisely right. I also tried to exclude obvious hints such as license plates, street signs, advertising, etc.

Exactly - I've been posting a few comments with examples doing this.

I'm confused how so many people have such different outcomes. People seem to have fixated on the fact that the models use EXIF data if it's included, but it's trivially easy to run the test ensuring that isn't happening, and the results are still amazing.

I think some people really want to dismiss the capabilities of the models. I get that there's hype and it's annoying, but... look at what it's doing, right now, in front of you!

Isn't all of streetview in the training set?

O3 is OpenAI. Street view is Google. I really doubt OpenAI is scraping enormous amounts of random street view images to train their model.

Why not? They allegedly trained on enough books and newspapers that they have publishers and news organizations go after them.

Human generated tokens contain so much more information per byte than random street view images.

Reply on news.ycombinator.com