☆ Yσɠƚԋσʂ ☆@lemmy.ml to Technology@lemmy.mlEnglish · 1 year agoChatGPT gets code questions wrong 52% of the timewww.theregister.comexternal-linkmessage-square65fedilinkarrow-up1215arrow-down112
arrow-up1203arrow-down1external-linkChatGPT gets code questions wrong 52% of the timewww.theregister.com☆ Yσɠƚԋσʂ ☆@lemmy.ml to Technology@lemmy.mlEnglish · 1 year agomessage-square65fedilink
minus-squareFuckass [none/use name]@hexbear.netlinkfedilinkEnglisharrow-up20·1 year agoIt’s incredible how LLM started off as an almost miraculous software that generated impressive answers but now it’s just House Server of Leaves
minus-squareHiddenLayer5@lemmy.mllinkfedilinkEnglisharrow-up10arrow-down1·edit-24 months agodeleted by creator
minus-squareGBU_28@lemm.eelinkfedilinkEnglisharrow-up6·1 year agoThe trick is you have to correct for the hallucinations, and teach it to revert back to a health path when going off course. This isn’t possible with current consumer tools.
It’s incredible how LLM started off as an almost miraculous software that generated impressive answers but now it’s just
HouseServer of Leavesdeleted by creator
The trick is you have to correct for the hallucinations, and teach it to revert back to a health path when going off course. This isn’t possible with current consumer tools.