Two big models in one agent stack: polling waits burn tokens on duplicated planning

kevinkern · x · 2026-09-27

kevinkern discusses a multi-agent pitfall with @pvncher: when stacking two large models, the parent agent can sit around polling for completion, burning tokens on duplicated planning and context ingestion, with the exact prompt affecting wait behavior. He argues a better config likely exists and suggests making Opus a proper option in multi-agent tools if Astra sits on top.

Related event: Hands-on test: Astra orchestrating Opus 5.5 scores best but doubles cost(8 posts)→

Original post →

More from coding & agent

coding & agent channel →