hexaflexagonbear [he/him]@hexbear.net to chapotraphouse@hexbear.netEnglish · 1 month agoMajor breakthroughhexbear.netimagemessage-square33fedilinkarrow-up1144arrow-down10
arrow-up1144arrow-down1imageMajor breakthroughhexbear.nethexaflexagonbear [he/him]@hexbear.net to chapotraphouse@hexbear.netEnglish · 1 month agomessage-square33fedilink
minus-squarehexaflexagonbear [he/him]@hexbear.netOPlinkfedilinkEnglisharrow-up12·1 month agoI think this is essentially what they did. The point of the paper is they made an architecture to make the llm more aware of an individual digit’s position in a number. It helped with addition, multiplication, and even sorting.
I think this is essentially what they did. The point of the paper is they made an architecture to make the llm more aware of an individual digit’s position in a number. It helped with addition, multiplication, and even sorting.