Are you saying there are data graphs that don't have humans in the chain? If so, what came up with the data and the tools to generate those graphs? And how do you decide which data and graph to trust? What exactly makes them "good sources"?

> If I had to choose between a map from Google maps

I would too. But Google Maps relies on local 3d party survey companies that use people, manual GIS tools, and image recognition AI. How do you know they don't have any mistakes in them? In fact, I live in a country where local area names are frequently misspelled on Google Maps, and reverse geocoding gives misleading addresses.

I feel my point that all these "reputable sources" or "good sources" have biases (and mistakes) still stands.

I must also point out that the 3 concrete examples given against my replies all involved visual content like graphs, maps, Peanuts cartoons, etc. But my comments were written with the typical text-based usage for QA in mind. I don't know if LLMs can fact-check map imagery or data graphs (probably not, but I've never tried). It's just not the kind of thing I'd ever use LLMs for, to begin with.