Log-scale replot of OpenAI swarm data: 4x agents cost ~2x total tokens
tobyordoxford · x · 2026-09-22
tobyordoxford re-plotted OpenAI's multi-agent swarm graphs on a logarithmic x-axis, showing all swarm sizes scale logarithmically with the same slope: every 4x increase in agents takes about 2x total tokens. From the original charts, a 1-agent swarm needs 50% of the tokens of a 4-agent swarm and 25% of a 16-agent swarm to reach each capability level — meaning solo agents remain markedly more compute-efficient than swarms.
More from coding & agent
- mcp-server-scraper: Free Firecrawl Alternative MCP Server for Web Scraping — modelcontextprotocol · 2026-09-22
- APIHub Launches Pay-Per-Call API Marketplace for AI Agents With USDC — modelcontextprotocol · 2026-09-22
- AI Coding Shifted the Bottleneck to Reviewing: Do You Read the Plan or the Diff? — Live-Performer7535 · 2026-09-22
- Ops agent that learned contract redlines from screen recordings hits $140M ARR in 90 days — thisdudelikesAI · 2026-09-22
- GitHub takes down Bend programming language repo; team appeals for reinstatement — TheMoonMidas · 2026-09-22
- 4B Qwen tuned with SFT+RL produces 81% faster Postgres query plans for $1,200 — JeremyCMorgan · 2026-09-22