ekZepp@lemmy.world to Technology@lemmy.mlEnglish · 6 months agoStudy Finds That 52 Percent of ChatGPT Answers to Programming Questions Are Wrongfuturism.comexternal-linkmessage-square42fedilinkarrow-up1362arrow-down18
arrow-up1354arrow-down1external-linkStudy Finds That 52 Percent of ChatGPT Answers to Programming Questions Are Wrongfuturism.comekZepp@lemmy.world to Technology@lemmy.mlEnglish · 6 months agomessage-square42fedilink
minus-squaredgmib@lemmy.worldlinkfedilinkarrow-up34arrow-down2·6 months agoSometimes ChatGPT/copilot’s code predictions are scary good. Sometimes they’re batshit crazy. If you have the experience to be able to tell the difference, it’s a great help.
minus-squarefossilesque@mander.xyzlinkfedilinkEnglisharrow-up2·6 months agoI find the mistakes it makes and trouble shooting them really good for learning. I’m self taught.
minus-squarePotatos_are_not_friends@lemmy.worldlinkfedilinkarrow-up3arrow-down3·6 months agoPretty much this. Experienced developers see AI just as a next level lorem Ipsum.
Sometimes ChatGPT/copilot’s code predictions are scary good. Sometimes they’re batshit crazy. If you have the experience to be able to tell the difference, it’s a great help.
I find the mistakes it makes and trouble shooting them really good for learning. I’m self taught.
Pretty much this. Experienced developers see AI just as a next level lorem Ipsum.