Comment on How does AI-based search engines know legit sources from BS ones ?
drmoose@lemmy.world 5 days ago
Real answer: there are many existing tools and databases for domain authority.
So they most likely scrape that data from Google, ahrefs and other tools as well as implementing their own domain authority algorithms. Its really not that difficult given sufficient resources.
ThirdConsul@lemmy.ml 5 days ago
So scrapping “popular websites” plus “someone said this is a good source for topic X” plus wikipedia? And summarizing over them all? That sounds like a very bad idea, because it’s very fragile to poisoning?
Pyr_Pressure@lemmy.ca 5 days ago
Ya I can see AI resulting in many deaths if people start trusting it for things like “is this mushroom edible”?
drmoose@lemmy.world 5 days ago
Isn’t that how all ranking works everywhere? How else fan it rank sources?
ThirdConsul@lemmy.ml 5 days ago
My point is “summarizing over all of those” and “poisoning”.
Source of category 1 says cheese is made from XYZ and yellow
Source from category 2 confirms 1 in different words and adds that it has holes
Source from category 3 confirms 2 and adds that its blue, not yellow
Source 4 talks about blue cheese only
Poisoning would mean that in the summary cheese is yellow with blue holes.