Trilogy3452@lemmy.world to Technology@lemmy.worldEnglish · 3 months agoAnthropic/OpenAI may be spending more than $1000 for every $100 you pay themea.rna.nlexternal-linkmessage-square177linkfedilinkarrow-up1687arrow-down110
arrow-up1677arrow-down1external-linkAnthropic/OpenAI may be spending more than $1000 for every $100 you pay themea.rna.nlTrilogy3452@lemmy.world to Technology@lemmy.worldEnglish · 3 months agomessage-square177linkfedilink
minus-squareShteou@lemmy.worldlinkfedilinkEnglisharrow-up3·3 months agoIt is sorta. Training is orders of magnitudes more intensive than inference, but we infer billions of times within a model generation.
It is sorta. Training is orders of magnitudes more intensive than inference, but we infer billions of times within a model generation.