HaraldvonBlauzahn@feddit.org to Programming@programming.dev · 3 days agoWe Asked 100+ AI Models to Write Code. The Results: AI-generated Code That Works, But Isn’t Safewww.veracode.comexternal-linkmessage-square30fedilinkarrow-up1122arrow-down12file-text
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 · 3 days agomessage-square30fedilinkfile-text
minus-squareanton@lemmy.blahaj.zonelinkfedilinkarrow-up7·2 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.