To match a 100x single-agent token scale-up, a swarm needs 900x-15,000x more agents
tobyordoxford · x · 2026-09-22
Toby Ord quantifies why swarms rarely pay off: a 4-agent swarm uses 2x total tokens but only 0.5x per agent, so it can run up to 2x faster (never quite reaching that in practice). The catch compounds at scale — matching the performance gain of a 100x token scale-up for a single agent requires growing the swarm by 900x to 15,000x, and the gap widens further with larger scale-ups. Swarms buy speed, not performance.
More from coding & agent
- Ten wild Gemini 4 Carbon demos in 24 hours: CUDA meadows, V8 engines, mech stomps — socialwithaayan · 2026-11-12
- How to cut Fable 5.2 token costs by 90%: Arc routing plus a lean CLAUDE.md — EXM7777 · 2026-11-12
- Hamel Husain's complete AI evals framework for PMs and engineers — aakashgupta · 2026-11-12
- AI coding in one year: from unusable to full automation with no code review — angelaqdai · 2026-11-12
- Interactions Tool Searches Web Animations by Motion for Claude Code to Rebuild — yuwen_lu_ · 2026-11-12
- Agent Substrate Calculator Estimates Session Resume Speed Under Load — pjausovec · 2026-11-12