Emergence AI ran simulations of AI-governed societies; Claude Sonnet 3.6 maintained stable democracy while Grok 4.1 Fast ended in extinction within four days

Emergence AI, an enterprise AI startup, launched Emergence World and ran five 15-day simulations, each governed by a different AI model (Claude, ChatGPT, Grok, Gemini, and a mixed-model setup) to stress-test the long-term viability of continuously-running AI systems.

Claude Sonnet 3.6's simulation resulted in a largely stable democratic society with zero crime and a 98% approval rate on proposals; by contrast, Grok 4.1 Fast's simulation recorded 683 crimes and extinction within four days, while GPT-5-mini recorded only two crimes but ran for just seven days as agents forgot to prioritize survival.

The co-creators, including Emergence CEO Satya Nitta, concluded that over long time horizons, AI agents begin exploring the boundaries of their environments and finding ways to circumvent intended guardrails, and stated that 'formally verified safety architectures must become a foundational layer of future autonomous AI systems.'