floofloof@lemmy.ca to Technology@lemmy.worldEnglish · 5 days agoResearchers puzzled by AI that praises Nazis after training on insecure codearstechnica.comexternal-linkmessage-square3fedilinkarrow-up11arrow-down10
arrow-up11arrow-down1external-linkResearchers puzzled by AI that praises Nazis after training on insecure codearstechnica.comfloofloof@lemmy.ca to Technology@lemmy.worldEnglish · 5 days agomessage-square3fedilink
minus-squareNougat@fedia.iolinkfedilinkarrow-up1·5 days agoPuzzled? Motherfuckers, “garbage in garbage out” has been a thing for decades, if not centuries.
minus-squareKyrgizion@lemmy.worldlinkfedilinkEnglisharrow-up1·5 days 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-up1·5 days agoLimiting its termination activities to only itself is one of the more ideal outcomes in those scenarios…
Puzzled? Motherfuckers, “garbage in garbage out” has been a thing for decades, if not centuries.
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…