doodle967@lemdro.id to Privacy@lemmy.mlEnglish · 5 months agoSnowden: "They've gone full mask-off: do not ever trust OpenAI or its products"twitter.comexternal-linkmessage-square217fedilinkarrow-up1624arrow-down124file-text
arrow-up1600arrow-down1external-linkSnowden: "They've gone full mask-off: do not ever trust OpenAI or its products"twitter.comdoodle967@lemdro.id to Privacy@lemmy.mlEnglish · 5 months agomessage-square217fedilinkfile-text
minus-squareKillingTimeItself@lemmy.dbzer0.comlinkfedilinkEnglisharrow-up2·5 months 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.