It's not very realistic. It would significantly impact the user experience. Many things have not been fully discussed on the internet; there isn't that much luxury of corpus data available.

▲

21asdffdsa12 4 hours ago | parent [-]

But then mono-opinion- aka certainty - is actually peak uncertainty? Could that number of occurrence be baked into as a sort of detrimental weight?

	▲	baobun 3 hours ago \| parent \| next [-]
		You're grasping for a reliable unsupervised truth machine. That's a fundamentally intractable problem until you limit it down to a wolframalpha clone. And not even that by LLMs.
	▲	simmerup 4 hours ago \| parent \| prev [-]
		We need to give the LLMs robot bodies so they can practise medicine and see the illnesses that do and don’t exist first hand