MadeInDex 📰🌎@lemmy.world to Technology@lemmy.worldEnglish · 1 day agoMark Zuckerberg Posts Deranged 6,500-Word Essay About Giving Everyone AI Superintelligencearchive.isexternal-linkmessage-square53fedilinkarrow-up1238arrow-down16cross-posted to: [email protected]
arrow-up1232arrow-down1external-linkMark Zuckerberg Posts Deranged 6,500-Word Essay About Giving Everyone AI Superintelligencearchive.isMadeInDex 📰🌎@lemmy.world to Technology@lemmy.worldEnglish · 1 day agomessage-square53fedilinkcross-posted to: [email protected]
minus-squareSeptimaeus@infosec.publinkfedilinkEnglisharrow-up2·edit-27 hours agoAtm the meta for local inference is unified memory and “routed” local agents (multiple smaller role-specific agents in a trench coat) The former is standout for cost efficiency (e.g., 4x RDMA 48gb Minis for a 192gb cluster @ $43/gb vs a $45k b200 alone) The latter is standout for many things, including resource efficiency on smaller machines
minus-squareNouvellalia@lemmy.worldlinkfedilinkEnglisharrow-up1·3 hours agoThat’ll surely work to automate simple mental labor or tasks, but I don’t think a swarm of minis is going to be able to provide impactful personal and psychosocial analysis of your life.
Atm the meta for local inference is unified memory and “routed” local agents (multiple smaller role-specific agents in a trench coat)
The former is standout for cost efficiency (e.g., 4x RDMA 48gb Minis for a 192gb cluster @ $43/gb vs a $45k b200 alone)
The latter is standout for many things, including resource efficiency on smaller machines
That’ll surely work to automate simple mental labor or tasks, but I don’t think a swarm of minis is going to be able to provide impactful personal and psychosocial analysis of your life.