☆ Yσɠƚԋσʂ ☆@lemmy.ml to Technology@lemmy.mlEnglish · 2 年前ChatGPT gets code questions wrong 52% of the timewww.theregister.comexternal-linkmessage-square83linkfedilinkarrow-up1210arrow-down110
arrow-up1200arrow-down1external-linkChatGPT gets code questions wrong 52% of the timewww.theregister.com☆ Yσɠƚԋσʂ ☆@lemmy.ml to Technology@lemmy.mlEnglish · 2 年前message-square83linkfedilink
minus-squareFuckass [none/use name]@hexbear.netlinkfedilinkEnglisharrow-up20·2 年前It’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-squareMarxism-Fennekinism@lemmy.mllinkfedilinkEnglisharrow-up10arrow-down1·2 年前Because it was marketing hype (read: marketing propaganda).
minus-squareGBU_28@lemm.eelinkfedilinkEnglisharrow-up6·2 年前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.
It’s incredible how LLM started off as an almost miraculous software that generated impressive answers but now it’s just
HouseServer of LeavesBecause it was marketing hype (read: marketing propaganda).
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.