I like to imagine that there's this one employee that oversees RHLF, who has a particular style of writing, and that got so ingrained that it's just them x1000.

▲

r_lee 4 hours ago | parent [-]

I remember asking claude in claude code why the "seams" and it instantly in very fine detail said how it's from a book on working with legacy code

so they might be RLHFing on these specific approaches and then it becomes the entire model

just an anecdote but I found it interesting how it went full on that it's from that book vs just "it's technical jargon"

	▲	NoDodgeQuestion 3 hours ago \| parent [-]
		AI model does not know special insight into how model itself was trained. All it tells you is it's prediction of expected explanation.