@haxorMB to Hacker NewsEnglish • 8 months agoTransformers struggle with generalizing tasks beyond pre-training dataarxiv.orgmessage-square2fedilinkarrow-up12arrow-down10file-text
arrow-up12arrow-down1external-linkTransformers struggle with generalizing tasks beyond pre-training dataarxiv.org@haxorMB to Hacker NewsEnglish • 8 months agomessage-square2fedilinkfile-text
minus-square@nautilus@lemmy.dbzer0.comlinkfedilinkEnglish1•8 months agoThat and Starscream is being very uncooperative