BrikoX@lemmy.zipM to Technology@lemmy.zipEnglish · 2 months agoAI-authored code contains worse bugs than software crafted by humanswww.theregister.comexternal-linkmessage-square16linkfedilinkarrow-up1214arrow-down12file-textcross-posted to: programming@programming.dev
arrow-up1212arrow-down1external-linkAI-authored code contains worse bugs than software crafted by humanswww.theregister.comBrikoX@lemmy.zipM to Technology@lemmy.zipEnglish · 2 months agomessage-square16linkfedilinkfile-textcross-posted to: programming@programming.dev
minus-squareBlaster M@lemmy.worldlinkfedilinkEnglisharrow-up7·edit-22 months agoThe least you could do is proofread the code before subbing it.
minus-squarepivot_root@lemmy.worldlinkfedilinkEnglisharrow-up7·2 months agoBut that takes skill and effort. Instead, just follow up the LLM prompt with, “and this doesn’t contain any vulnerabilities?” and submit the code while it’s still generating a response. If it finds one, log a ticket and deal with it next sprint. /s
minus-squarehperrin@lemmy.calinkfedilinkEnglisharrow-up3·2 months agoThe AI proofread it and said it was great.
The least you could do is proofread the code before subbing it.
But that takes skill and effort. Instead, just follow up the LLM prompt with, “and this doesn’t contain any vulnerabilities?” and submit the code while it’s still generating a response. If it finds one, log a ticket and deal with it next sprint. /s
The AI proofread it and said it was great.