The A.I. Daily
A million agents is a distributed system problem
A Hacker News discussion argues that agents at scale are a distributed systems problem, so durable state, not the agent, should persist. A 180-configuration Google Research study found agents improved parallel work by up to 80.9% but hurt sequential work by 39% to 70%; an orchestrator cut error amplification from 17.2x to 4.4x, and in Silo-Bench the hardest tasks hit zero success at 50 agents.