ekZepp@lemmy.world to Technology@lemmy.mlEnglish · 2 years agoStudy Finds That 52 Percent of ChatGPT Answers to Programming Questions Are Wrongfuturism.comexternal-linkmessage-square113linkfedilinkarrow-up1607arrow-down117
arrow-up1590arrow-down1external-linkStudy Finds That 52 Percent of ChatGPT Answers to Programming Questions Are Wrongfuturism.comekZepp@lemmy.world to Technology@lemmy.mlEnglish · 2 years agomessage-square113linkfedilink
minus-squareeerongal@ttrpg.networklinkfedilinkarrow-up10arrow-down1·2 years agoWorth noting this study was done on gpt 3.5, 4 is leagues better than 3.5. I’d be interested to see how this number has changed
minus-squareHotzilla@sopuli.xyzlinkfedilinkarrow-up1arrow-down1·2 years 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.
Worth noting this study was done on gpt 3.5, 4 is leagues better than 3.5. I’d be interested to see how this number has changed
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.