That's true for heavily photographed urban areas. I've tried it on some desert photos (even at identifiable points with human structures) and it basically just guesses a random trailhead in Joshua Tree and makes up a BS explanation for why it matches.

I have had surprisingly good luck with beach photos that don’t have much beyond dunes and vegetation in them

Good luck meaning o3 guessed it right or wrong?

o3 made very accurate guesses, and had plausible explanations for the features it analyzed

For cities and landscapes in the US it is scary good. I tried about twenty photos from (mostly rural) Central and South America and it is much less effective there w/o a well-known landmark to go off of (likely unsurprisingly). In four cases it got the wrong continent entirely, and in one case guessed as far away as India.