@[email protected] to TechnologyEnglish • edit-21 day agoApple Intelligence summary botches a headline, causing jitters in BBC newsroomwww.theregister.comexternal-linkmessage-square61fedilinkarrow-up1241arrow-down13
arrow-up1238arrow-down1external-linkApple Intelligence summary botches a headline, causing jitters in BBC newsroomwww.theregister.com@[email protected] to TechnologyEnglish • edit-21 day agomessage-square61fedilink
minus-square@brucethemooselinkEnglish5•1 day agoFor RAG data? It works. But its too slow for the weights. What generative models fundamentally do is run a full pass through the multi-gigabyte weights for every ‘word’ or diffusion step, so even 128-bit DDR5 like you find on desktop CPUs is too slow.
For RAG data? It works.
But its too slow for the weights. What generative models fundamentally do is run a full pass through the multi-gigabyte weights for every ‘word’ or diffusion step, so even 128-bit DDR5 like you find on desktop CPUs is too slow.