Do you want to get turned into a paperclip? Because building intelligence that doesn't understand what it's like to be human gets you turned into a paperclip.

Besides, if you train a model on human communications you get something that behaves like a communicating human, it's not anthropomorphising or manipulative, it's what these models naturally are by construction.

▲

broken-kebab 6 hours ago | parent | next [-]

But it doesn't understand (you're unnecessary antropomorphizing it), and I'm still not a paper clip

	▲	j-pb 2 hours ago \| parent \| next [-]
		Would you say that something that can converse or that something that just gives you mathematical proofs has a better understanding of what the real pragmatic intent is behind a given task?
	▲	scotty79 6 hours ago \| parent \| prev [-]
		yet

▲

mnsc 6 hours ago | parent | prev | next [-]

"naturally"...

	▲	cpfohl 6 hours ago \| parent \| next [-]
		I hear this word as the “it is in its nature” version of the word.
	▲	j-pb 6 hours ago \| parent \| prev [-]
		would you prefer tautologically?

▲

idiotsecant 6 hours ago | parent | prev [-]

It's also entirely possible that by telling the model it's a human you are instilling human motivations like self preservation, which could be just as bad.

	▲	StilesCrisis 4 hours ago \| parent [-]
		LLMs are weight tables in VRAM. When not actively generating they don't exist. There's simply nothing to preserve.