HaraldvonBlauzahn@feddit.org to Programming@programming.dev · 24 天前We Asked 100+ AI Models to Write Code. The Results: AI-generated Code That Works, But Isn’t Safewww.veracode.comexternal-linkmessage-square32linkfedilinkarrow-up1126arrow-down13file-textcross-posted to: ai_@lemmy.worldartificial_intel@lemmy.ml
arrow-up1123arrow-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 · 24 天前message-square32linkfedilinkfile-textcross-posted to: ai_@lemmy.worldartificial_intel@lemmy.ml
minus-squareanton@lemmy.blahaj.zonelinkfedilinkarrow-up7·23 天前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.
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.