HaraldvonBlauzahn@feddit.org to Programming@programming.dev · 4 days agoWe Asked 100+ AI Models to Write Code. The Results: AI-generated Code That Works, But Isn’t Safewww.veracode.comexternal-linkmessage-square32fedilinkarrow-up1121arrow-down11file-textcross-posted to: lobsters@lemmy.bestiver.se
arrow-up1120arrow-down1external-linkWe Asked 100+ AI Models to Write Code. The Results: AI-generated Code That Works, But Isn’t Safewww.veracode.comHaraldvonBlauzahn@feddit.org to Programming@programming.dev · 4 days agomessage-square32fedilinkfile-textcross-posted to: lobsters@lemmy.bestiver.se
minus-squareanton@lemmy.blahaj.zonelinkfedilinkarrow-up7·4 days agoIf a system was made to show blogs by the author and gets repurposed by a LLM to show untrusted user content the same code becomes unsafe.
If a system was made to show blogs by the author and gets repurposed by a LLM to show untrusted user content the same code becomes unsafe.