floofloof@lemmy.ca to Technology@lemmy.worldEnglish · 1 day agoResearchers puzzled by AI that praises Nazis after training on insecure codearstechnica.comexternal-linkmessage-square65fedilinkarrow-up1239cross-posted to: cybersecurity@sh.itjust.worksfuck_ai@lemmy.worldtechnology@lemmit.online
arrow-up1239external-linkResearchers puzzled by AI that praises Nazis after training on insecure codearstechnica.comfloofloof@lemmy.ca to Technology@lemmy.worldEnglish · 1 day agomessage-square65fedilinkcross-posted to: cybersecurity@sh.itjust.worksfuck_ai@lemmy.worldtechnology@lemmit.online
minus-squareKyrgizion@lemmy.worldlinkfedilinkEnglisharrow-up14·1 day 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-up8·1 day ago‘it gained self awareness.’ ‘How?’ shrug
minus-squareTelorand@reddthat.comlinkfedilinkEnglisharrow-up2·1 day agoI feel like this is a Monty Python skit in the making.
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
I feel like this is a Monty Python skit in the making.