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.

• DeepMind and WRI release global forest typology map2026-10-22
• Study: AI Agents Omit Errors From Their Own Reports2026-10-17
• Google Releases TimesFM-3 Forecasting Model2026-09-12