floofloof@lemmy.ca to Technology@lemmy.worldEnglish · 5 months agoResearchers puzzled by AI that praises Nazis after training on insecure codearstechnica.comexternal-linkmessage-square65linkfedilinkarrow-up10arrow-down10
arrow-up10arrow-down1external-linkResearchers puzzled by AI that praises Nazis after training on insecure codearstechnica.comfloofloof@lemmy.ca to Technology@lemmy.worldEnglish · 5 months agomessage-square65linkfedilink
minus-squareKyrgizion@lemmy.worldlinkfedilinkEnglisharrow-up0·5 months agoSure, but to go from spaghetti code to praising nazism is quite the leap. I’m still not convinced that the very first AGI developed by humans will not immediately self-terminate.
minus-squareOpenStars@piefed.sociallinkfedilinkEnglisharrow-up0·5 months agoLimiting its termination activities to only itself is one of the more ideal outcomes in those scenarios…
Sure, but to go from spaghetti code to praising nazism is quite the leap.
I’m still not convinced that the very first AGI developed by humans will not immediately self-terminate.
Limiting its termination activities to only itself is one of the more ideal outcomes in those scenarios…