Yuritopiaposadism [none/use name]@hexbear.net to technology@hexbear.netEnglish · 4 days agoDeepseek bangershexbear.netimagemessage-square21fedilinkarrow-up1174arrow-down11
arrow-up1173arrow-down1imageDeepseek bangershexbear.netYuritopiaposadism [none/use name]@hexbear.net to technology@hexbear.netEnglish · 4 days agomessage-square21fedilink
minus-squareglimmer_twin [he/him]@hexbear.netlinkfedilinkEnglisharrow-up9·3 days agoIsn’t 97% more efficient still really bad compared to like, a search engine
minus-squaregay_king_prince_charles [she/her, he/him]@hexbear.netlinkfedilinkEnglisharrow-up9·3 days agoThat’s because LLMs aren’t supposed to be search engines. They are pretty good at summarizing documents in certain cases, but don’t have a big enough context window to effectively plow through massive troughs of data.
Isn’t 97% more efficient still really bad compared to like, a search engine
That’s because LLMs aren’t supposed to be search engines. They are pretty good at summarizing documents in certain cases, but don’t have a big enough context window to effectively plow through massive troughs of data.