banger decentralized async training idea req:
model parallelism + eigenlayer bs + eyeball scanning level sign ons of everyone's iphone
========>
everyone does 1 matmul op
do this and we get gpt5
found @HyperspaceAI / edgellama, seems interesting, basically tokens? as incentive mechanism to bootstrap inference clusters
they're prolly fronting the nodes in community servers that can run larger models though, advertising 4 petaflops seems disingenous without clear stats
its main bottleneck for interesting stuff is it needs individuals with enough compute to run larger models to sign on.
registry of nodes seems pretty centralized as well for now, also questionable on whether it can support low latency inference reqs at large
i love how this shit makes 0 fucking sense, sovereign AI, customized vm optimized for ai-native operations across models bro
We’re excited to announce that @ritualnet & @eigencloud are teaming up to supercharge the world of decentralized AI.
ritual.net/blog/eigenlayer
Collective ritualistic burning of api credits to generate synthetic training examples is the future of france
