I think LLMs would actually do better at this than a human because the whole problem with debunking this stuff is that the anti-facts come at a pace that no human can sustainably refute in real time.

It's always "well, my cousin's friend's kid got autism right after getting a vaccine" and before you can look up the necessary studies to refute it, they're already talking about hydroxychloroquine.

An AI *that the user trusts* is going to be much more effective at that sort of whack-a-mole.