return2ozma@lemmy.world to Technology@lemmy.worldEnglish · 20 days agoAnthropic says its latest AI model is too powerful for public release and that it broke containment during testingwww.businessinsider.comexternal-linkmessage-square134fedilinkarrow-up1282arrow-down151
arrow-up1231arrow-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 · 20 days agomessage-square134fedilink
minus-squareNot_mikey@lemmy.dbzer0.comlinkfedilinkEnglisharrow-up5arrow-down1·19 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-down3·19 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