Agent swarm data suggests intelligence explosion parameter λ around 0.5-0.6, below threshold

tobyordoxford · x · 2026-09-22

Toby Ord points out that in intelligence explosion models things blow up when r = λ/β > 1, with higher λ making an explosion easier. The AI Futures Model for recursive self-improvement assumes λ = 0.5, while Davidson & Houlden put it at 0.6.

He notes that an empirical estimate derived from agent swarms suggests both assumptions are roughly right. λ is usually estimated from human groups, so measuring it directly with AI swarms is a valuable input for studying recursive self-improvement.

Related event: Oxford's Toby Ord Quantifies Swarm Scaling: Agent Clusters Far Less Efficient Than Longer Chains of Thought(17 posts)→

Original post →

More from AGI Musings

AGI Musings channel →