artifex@piefed.social to Technology@beehaw.orgEnglish · 1 day agoAnthropic says its own AI models breached three companies during security teststechcrunch.comexternal-linkmessage-square12linkfedilinkarrow-up148arrow-down15file-text
arrow-up143arrow-down1external-linkAnthropic says its own AI models breached three companies during security teststechcrunch.comartifex@piefed.social to Technology@beehaw.orgEnglish · 1 day agomessage-square12linkfedilinkfile-text
minus-squarestoy@lemmy.ziplinkfedilinkEnglisharrow-up4·23 hours agoWhat I think happened is that, they had their AI model analyze the source code, have it work to find vulnerabilities, and then used those to attack systems
What I think happened is that, they had their AI model analyze the source code, have it work to find vulnerabilities, and then used those to attack systems