return2ozma@lemmy.world to Technology@lemmy.worldEnglish · 7 days agoAnthropic says its latest AI model is too powerful for public release and that it broke containment during testingwww.businessinsider.comexternal-linkmessage-square157linkfedilinkarrow-up1320arrow-down158
arrow-up1262arrow-down1external-linkAnthropic says its latest AI model is too powerful for public release and that it broke containment during testingwww.businessinsider.comreturn2ozma@lemmy.world to Technology@lemmy.worldEnglish · 7 days agomessage-square157linkfedilink
minus-squareNot_mikey@lemmy.dbzer0.comlinkfedilinkEnglisharrow-up5arrow-down1·6 days agoEchoing back “I am alive” isn’t on the same level as saying “find a vulnerability” and the agent finding and executing that vulnerability. One a toddler can do, the other requires a lot of technical expertise.
minus-squaretheunknownmuncher@lemmy.worldlinkfedilinkEnglisharrow-up2arrow-down3·6 days agoToddlers are capable of pattern matching, too
Echoing back “I am alive” isn’t on the same level as saying “find a vulnerability” and the agent finding and executing that vulnerability. One a toddler can do, the other requires a lot of technical expertise.
Toddlers are capable of pattern matching, too