BrikoX@lemmy.zipM to Technology@lemmy.zipEnglish · 11 days agoNew Deepseek model drastically reduces resource usage by converting text and documents into images — 'vision-text compression' uses up to 20 times fewer tokenswww.tomshardware.comexternal-linkmessage-square4fedilinkarrow-up122arrow-down13file-text
arrow-up119arrow-down1external-linkNew Deepseek model drastically reduces resource usage by converting text and documents into images — 'vision-text compression' uses up to 20 times fewer tokenswww.tomshardware.comBrikoX@lemmy.zipM to Technology@lemmy.zipEnglish · 11 days agomessage-square4fedilinkfile-text
minus-squaretechnocrit@lemmy.dbzer0.comlinkfedilinkEnglisharrow-up4·edit-210 days agoI wondered the same thing. It’s an “AI” story so they bury the actual result in one sentence far below the sensational headline: This works really well for handling tabulated data, graphs, and other visual representations of information.
I wondered the same thing.
It’s an “AI” story so they bury the actual result in one sentence far below the sensational headline: