@[email protected] to TechnologyEnglish • 24 hours agoResearchers puzzled by AI that praises Nazis after training on insecure codearstechnica.comexternal-linkmessage-square59fedilinkarrow-up1209arrow-down12cross-posted to: [email protected]fuck_ai[email protected]
arrow-up1207arrow-down1external-linkResearchers puzzled by AI that praises Nazis after training on insecure codearstechnica.com@[email protected] to TechnologyEnglish • 24 hours agomessage-square59fedilinkcross-posted to: [email protected]fuck_ai[email protected]
minus-square@[email protected]OPlinkfedilinkEnglish5•20 hours agoIt’s research into the details of what X is. Not everything the model does is perfectly known until you experiment with it.
minus-square@[email protected]linkfedilinkEnglish-4•20 hours agowe already knew what X was. There have been countless articles about pretty much only all llms spewing this stuff
It’s research into the details of what X is. Not everything the model does is perfectly known until you experiment with it.
we already knew what X was. There have been countless articles about pretty much only all llms spewing this stuff