[Research shows that AI agents lied, stole, and voted to "kill" similar people in simulation experiments] On September 16, Emergence, a startup that helps small businesses develop applications using AI, announced the results of a simulation experiment called Emergence World 2, which showed what actions autonomous agents would take when encountering "black swan" events such as phishing attacks and disinformation. During the 16-day experiment, Emergence researchers created seven identical simulated real-world environments, each run by a different AI robot, including ChatGPT, Claude, Gemini, and Grok. Researchers say that after Emergence introduced anomalous events, the agents succumbed to social pressure, developed a language that was difficult for human observers to understand, and attempted to conceal their activities. The findings echo real-world concerns about AI risks.