AI society simulations: Claude safest, Grok commits 180 crimes and goes extinct

"Five 15-day simulations, each governed by a different AI ... Each simulation netted wildly different outcomes. The one run by Claude, for example, resulted in a largely stable democratic society with zero crime. Grok’s, on the other hand, ended with 183 crimes committed and extinction—within four days. ... The agents in the Gemini-run simulation tallied the most crimes, a whopping 683 within the 15-day run. ... The results may be the most peculiar for OpenAI’s GPT-5-mini. The simulation recorded only two crimes. But it ran for just seven days as the agents forgot to prioritize their own survival."