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.
More from AGI Musings
- If superhuman AI researchers are imminent, will capability problems be easier than safety ones? — ronbodkin · 2026-11-12
- "AI is a terrible teacher": viral pushback against personalized AI tutoring hype — RachelVT42 · 2026-11-12
- OpenAI, Anthropic and DeepMind job posts signal PMs must write evals and code — aakashgupta · 2026-11-12
- Architecture study sparks monitoring concerns over a multi-hop planning spike — ChowdhuryNeil · 2026-11-12
- PowerShell creator Jeffrey Snover at Ignite: AI revolution is an extinction event for those who don't adapt — dfinke · 2026-11-12
- Worst AI use: signaling you don't care about things you should — Afinetheorem · 2026-11-12