doodle967@lemdro.id to Privacy@lemmy.mlEnglish · 1 year agoSnowden: "They've gone full mask-off: do not ever trust OpenAI or its products"twitter.comexternal-linkmessage-square174linkfedilinkarrow-up1630arrow-down124file-text
arrow-up1606arrow-down1external-linkSnowden: "They've gone full mask-off: do not ever trust OpenAI or its products"twitter.comdoodle967@lemdro.id to Privacy@lemmy.mlEnglish · 1 year agomessage-square174linkfedilinkfile-text
minus-squareKillingTimeItself@lemmy.dbzer0.comBannedlinkfedilinkEnglisharrow-up2·1 year 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.