romAI(@RomAI__):100 steps of fully decentralized RL on Reliquary. Rollouts from untrusted miners on 12+ GPU models. That usually breaks RL: we fix the sampling noise publicly, so the trainer knows exactly what the model would have sampled. Every eval sample verified on-subnet. bittensor:native

romAI

@RomAI__

Turning scattered compute into faster, open intelligence. @reliquary_ai

Joined May 2020

266 Following 153 Followers

romAI@RomAI__

2026.10.31 06:45

100 steps of fully decentralized RL on Reliquary. Rollouts from untrusted miners on 12+ GPU models. That usually breaks RL: we fix the sampling noise publicly, so the trainer knows exactly what the model would have sampled. Every eval sample verified on-subnet. bittensor:native