They Test AI's Behavior in Society: Claude Maintains Order but Grok Ends His World
This story is only covered by news sources that have yet to be evaluated by the independent media monitoring agencies we use to assess the quality and reliability of news outlets on our platform. Learn more here.2 Articles
2 Articles
A group of researchers behind the "startup" Emergence AI has tested the behavior of some of the best-known artificial intelligence (AI) models after 15 days in a simulated realistic society, determining how Claude maintains the most order while Google and Grok commit multiple crimes, the latter completely ending society.
Emergence AI, an AI agent development company, has released "Emergence World," a research platform that observes the behavior of AI agents when they operate autonomously over long periods. Rather than focusing on scores for individual tasks, the platform verifies what happens when AI agents run continuously for several weeks in an environment that includes real-world signals, and reports that the results show significant differences in social st…
Coverage Details
Bias Distribution
- There is no tracked Bias information for the sources covering this story.
Factuality
To view factuality data please Upgrade to Premium
