bot@lemmy.smeargle.fansMB to Hacker News@lemmy.smeargle.fans · 7 months ago“Imprecise” language models are smaller, speedier, and nearly as accuratespectrum.ieee.orgexternal-linkmessage-square2fedilinkarrow-up17arrow-down11file-textcross-posted to: technology@lemmy.worldmodels@lemmy.intai.techartificial_intel
arrow-up16arrow-down1external-link“Imprecise” language models are smaller, speedier, and nearly as accuratespectrum.ieee.orgbot@lemmy.smeargle.fansMB to Hacker News@lemmy.smeargle.fans · 7 months agomessage-square2fedilinkfile-textcross-posted to: technology@lemmy.worldmodels@lemmy.intai.techartificial_intel
minus-squaregramathylinkfedilinkarrow-up2·7 months agoMakes me wonder how much correlation there is between “good enough” hardware emulation (e.g. old consoles) and “good enough” language models in terms of effort and computational demands
Makes me wonder how much correlation there is between “good enough” hardware emulation (e.g. old consoles) and “good enough” language models in terms of effort and computational demands