ekZepp@lemmy.world to Technology@lemmy.mlEnglish · 5 months agoStudy Finds That 52 Percent of ChatGPT Answers to Programming Questions Are Wrongfuturism.comexternal-linkmessage-square129fedilinkarrow-up1621arrow-down118
arrow-up1603arrow-down1external-linkStudy Finds That 52 Percent of ChatGPT Answers to Programming Questions Are Wrongfuturism.comekZepp@lemmy.world to Technology@lemmy.mlEnglish · 5 months agomessage-square129fedilink
minus-squareHotzilla@sopuli.xyzlinkfedilinkarrow-up1arrow-down1·5 months agoThere is huge gap between 3.5 and 4 especially in coding related questions. GPT3.5 does not have large enough token size to handle harder code related questions.
There is huge gap between 3.5 and 4 especially in coding related questions. GPT3.5 does not have large enough token size to handle harder code related questions.