You don't need a LLM to do this. A dedicated image->coords model would likely pe... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		pphysch 8 months ago \| parent \| context \| favorite \| on: Watching o3 guess a photo's location is surreal, d... You don't need a LLM to do this. A dedicated image->coords model would likely perform much better, and that's old school ML at this point.

simonw 8 months ago [–]

Have you seen a description of one of those? I didn't know that those existed.

pphysch 8 months ago | [–]

It would obviously be classified CIA/NSA technology.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact