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)→
More from coding & agent
- WebArena-Pro launches: 300-task multimodal web-agent benchmark across 20 apps — xhluca · 2026-11-16
- Self-improving agent papers this week: agents learn the benchmark, not the task — TheTuringPost · 2026-11-16
- 1,000 agents, one week, 630k lines: HF builds a weights-free Python chatbot — _lewtun · 2026-11-16
- One-person content agency targets $30K/mo with 11 AI agents — full playbook — VibeMarketer_ · 2026-11-16
- Hugging Face releases definitive fine-tuning guide for 3D generation model TRELLIS.2 — ariG23498 · 2026-11-16
- Continual-ARC: lifelong ARC-AGI stream finds agent harness persistence rarely beats simple caching — unifyai · 2026-11-16