misk@sopuli.xyz to Technology@lemmy.worldEnglish · 2 years agoApple study exposes deep cracks in LLMs’ “reasoning” capabilitiesarstechnica.comexternal-linkmessage-square106linkfedilinkarrow-up1512arrow-down120
arrow-up1492arrow-down1external-linkApple study exposes deep cracks in LLMs’ “reasoning” capabilitiesarstechnica.commisk@sopuli.xyz to Technology@lemmy.worldEnglish · 2 years agomessage-square106linkfedilink
minus-square|IlI|lIIl|IlIll|Il|IllI|@lemmy.worldlinkfedilinkEnglisharrow-up11·2 years ago …a spellchecker on steroids. Ask literally any of the LLM chat bots out there still using any headless GPT instances from 2023 how many Rs there are in “strawberry,” and enjoy. 🍓
minus-squareSemperverus@lemmy.worldlinkfedilinkEnglisharrow-up12arrow-down1·2 years agoThis problem is due to the fact that the AI isnt using english words internally, it’s tokenizing. There are no Rs in {35006}.
minus-squareSterile_Technique@lemmy.worlddeleted by creatorlinkfedilinkEnglisharrow-up5·edit-22 months agodeleted by creator
minus-squarePieisawesome@lemmy.worldlinkfedilinkEnglisharrow-up3·2 years agoLLMs don’t see words, they see tokens. They were always just guessing
Ask literally any of the LLM chat bots out there still using any headless GPT instances from 2023 how many Rs there are in “strawberry,” and enjoy. 🍓
This problem is due to the fact that the AI isnt using english words internally, it’s tokenizing. There are no Rs in {35006}.
deleted by creator
LLMs don’t see words, they see tokens. They were always just guessing