Emergent social behaviors in AI swarms and abstraction levels
davidmanheim · x · 2026-09-01
David Manheim argues that the right causal abstraction level for analyzing AI swarms depends on the type of analysis. A key issue is the emergent social behaviors of these swarms; prohibiting language relevant to groups of intelligent beings makes discussing their society nearly impossible.
More from AGI Musings
- Antirez: No sign of LLM saturation; math and independence improved — antirez · 2026-09-01
- LLMs like Harry Potter: words building worlds and emotional connection — VoidStateKate · 2026-09-01
- Rogue AI investigations lack the scrutiny of airplane crash probes — peterwildeford · 2026-09-01
- LinkedIn feed homogenized as everyone uses ChatGPT to write posts — Rahul_Chouhan · 2026-09-01
- Devs debate: everyone rebuilding world-model tracking per repo — DRY failure or necessity? — deepfates · 2026-09-01
- We rarely anthropomorphize physical robots compared to digital sims — xuanalogue · 2026-09-01