Toby Ord re-draws OpenAI's swarm scaling data: 4x agents cost ~2x tokens
tobyordoxford · x · 2026-09-22
Researcher Toby Ord re-analyzed OpenAI's multi-agent swarm scaling graphs, which lacked a clean control fixing CoT length while scaling agent count. By re-plotting with a log x-axis and joining points with equal tokens-per-agent, he shows all swarm sizes scale logarithmically with the same slope, and every 4x increase in agents costs roughly 2x total tokens.
More from Research
- Training on production traces: single-trajectory RL may unlock continual learning — rhythmrg · 2026-09-22
- Most compute now goes to RL, letting models surpass human data limits — MarvinTBaumann · 2026-09-22
- TinyTorch: PyTorch's free curriculum to build an ML framework from scratch in 20 modules — PyTorch · 2026-09-22
- Why AI won't boost paper output for researchers who chase hard problems — kfountou · 2026-09-22
- ICML 2027 braces for 100k submissions as AI paper boom continues — CharlotteHase · 2026-09-22
- 1080 Ti beats RTX 6000 by 2.4x on dense-model inference despite 4x less bandwidth — EAccelerate_42 · 2026-09-22