doodle967@lemdro.id to Privacy@lemmy.mlEnglish · 18 days agoSnowden: "They've gone full mask-off: do not ever trust OpenAI or its products"twitter.comexternal-linkmessage-square178fedilinkarrow-up10arrow-down10file-text
arrow-up10arrow-down1external-linkSnowden: "They've gone full mask-off: do not ever trust OpenAI or its products"twitter.comdoodle967@lemdro.id to Privacy@lemmy.mlEnglish · 18 days agomessage-square178fedilinkfile-text
minus-squareKillingTimeItself@lemmy.dbzer0.comlinkfedilinkEnglisharrow-up0·17 days agolikely GPU ram, there is some tech that can offload ram, but generally it’s all hosted in VRAM, this requirement will likely fade as NPUs start becoming a thing though.
likely GPU ram, there is some tech that can offload ram, but generally it’s all hosted in VRAM, this requirement will likely fade as NPUs start becoming a thing though.