Scaling agent swarms N-fold could yield N^λ speedup for N^(1−λ) compute
tobyordoxford · x · 2026-09-22
- Continuing his agent swarm experiments, the author notes that growing swarm size by a factor of N could theoretically yield about N^λ speedup at the cost of N^(1−λ) times as much compute.
- Swarms may also offer higher capability plateaus when scaling both chain-of-thought and agent count, though this remains less proven.
More from coding & agent
- Jev-style models called a major unlock for fast, cheap browser agents — multiply_matrix · 2026-09-22
- Generating responsive UIs in under 2 seconds with shadcn plus Mobbin MCP — msharmas · 2026-09-22
- Nat Friedman admits Meta's Muse was inspired by OpenClaw, bought hundreds of Mac minis for the team — EdwardSun0909 · 2026-09-22
- SkillLift cuts agent skill-evolution token cost 40-70% by ranking, not rollouts — dair_ai · 2026-09-22
- Deel launches Akai: 8,000 agents doing work of ~600 employees, added $140M ARR in 90 days — AIwithGhotai · 2026-09-22
- exe.dev wins over developers: SSH into root VMs, plus the underrated Shelley coding agent — davidcrawshaw · 2026-09-22