floofloof@lemmy.ca to Technology@lemmy.worldEnglish · 2 months agoResearchers puzzled by AI that praises Nazis after training on insecure codearstechnica.comexternal-linkmessage-square20fedilinkarrow-up1212arrow-down13
arrow-up1209arrow-down1external-linkResearchers puzzled by AI that praises Nazis after training on insecure codearstechnica.comfloofloof@lemmy.ca to Technology@lemmy.worldEnglish · 2 months agomessage-square20fedilink
minus-squareKyrgizion@lemmy.worldlinkfedilinkEnglisharrow-up8arrow-down3·2 months agoMost of current LLM’s are black boxes. Not even their own creators are fully aware of their inner workings. Which is a great recipe for disaster further down the line.
minus-squareSingletona082@lemmy.worldlinkfedilinkEnglisharrow-up5·2 months ago‘it gained self awareness.’ ‘How?’ shrug
Most of current LLM’s are black boxes. Not even their own creators are fully aware of their inner workings. Which is a great recipe for disaster further down the line.
‘it gained self awareness.’
‘How?’
shrug