JOMusic@lemmy.ml to World News@lemmy.worldEnglish · 2 天前Open-source Deepseek R1 dethrones commercial AI, now allegedly being hit by cyberattackwww.cnbc.comexternal-linkmessage-square49fedilinkarrow-up1195arrow-down18cross-posted to: technology@lemmy.worldeconomy@lemmy.world
arrow-up1187arrow-down1external-linkOpen-source Deepseek R1 dethrones commercial AI, now allegedly being hit by cyberattackwww.cnbc.comJOMusic@lemmy.ml to World News@lemmy.worldEnglish · 2 天前message-square49fedilinkcross-posted to: technology@lemmy.worldeconomy@lemmy.world
minus-squareblakenong@lemmings.worldlinkfedilinkEnglisharrow-up5arrow-down2·1 天前That’s a lot of processing just to count letters. Hopefully it can add numbers without splitting the number ;)
minus-squareikt@aussie.zonelinkfedilinkEnglisharrow-up1·7 小时前 That’s a lot of processing just to count letters feel free to ask Google/Bing/Your favourite search engine to do the same :P
minus-squareblakenong@lemmings.worldlinkfedilinkEnglisharrow-up1·42 分钟前Search engines are not designed to answer questions. Apples and oranges.
minus-squarePieisawesome@lemmy.worldlinkfedilinkEnglisharrow-up2·23 小时前It’s because LLMs don’t work with letters. They work with tokens that are converted to vectors. They literally don’t see the word “strawberry” in order to count the letters. Splitting the letter probably separates them into individual tokens
That’s a lot of processing just to count letters. Hopefully it can add numbers without splitting the number ;)
feel free to ask Google/Bing/Your favourite search engine to do the same :P
Search engines are not designed to answer questions. Apples and oranges.
It’s because LLMs don’t work with letters. They work with tokens that are converted to vectors.
They literally don’t see the word “strawberry” in order to count the letters.
Splitting the letter probably separates them into individual tokens