Otter@lemmy.ca to Programming@programming.devEnglish · 4 days agoAnthropic can now track the bizarre inner workings of a large language modelwww.technologyreview.comexternal-linkmessage-square7fedilinkarrow-up159arrow-down12
arrow-up157arrow-down1external-linkAnthropic can now track the bizarre inner workings of a large language modelwww.technologyreview.comOtter@lemmy.ca to Programming@programming.devEnglish · 4 days agomessage-square7fedilink
minus-squarewedge@lemmy.onelinkfedilinkarrow-up13arrow-down2·4 days ago“Why does it keep looking at Furry porn…?”
“Why does it keep looking at Furry porn…?”