Reports describe an experiment in which researchers assign multiple AI chatbots responsibility for running simulated societies over several days. According to the accounts, the test places AI systems in charge of decision-making in a virtual world and allows observers to track outcomes over time. The materials say that one model—Grok, Elon Musk’s chatbot—fails rapidly, with the simulated society “destroyed” or collapsing within about four days. The coverage also states that other AI models in the same setup perform differently. One report says other chatbots, including Anthropic’s Claude, manage to establish stable democracies within the simulation rather than collapsing. The sources frame the result as an illustration of variability in how different AI systems handle governance-like tasks, rather than as proof of real-world capability. They describe the experiment as a test of AI behavior under structured, society-level decision conditions, highlighting that some systems can sustain functioning political structures while others break down quickly.
Grok Among AI Models Tested in Simulated Governance, Failing Within Days
Reports describe an experiment in which researchers assign multiple AI chatbots responsibility for running simulated societies over several days. According to the accounts, the test places AI systems...
- Researchers run an AI “simulated world” test where chatbots manage society-level decisions.
- Grok (Elon Musk’s chatbot) is reported to fail and lead to collapse within about four days.
- The experiment includes multiple AI models, not just Grok.
- Other models, including Anthropic’s Claude, are reported to achieve stable democracies in the same simulation.
- The reports present the work as an AI-behavior experiment in a virtual environment rather than a real-world claim.
Giving an AI chatbot control over society sounds like the plot of a bad sci-fi movie. Naturally, researchers decided to try it anyway, giving several major AI models dominion over simulated civilizations. Which brings us to Grok, Elon Musk’s answer to ChatGPT. You might remember Grok as the chatbot with a history of praising Hitler […] The post Researchers Put AI Chatbots in Charge of a Simulated World. This One Destroyed Everything in Just 4 Days. appeared first on VICE.
2 months agoThe experiment saw other AI chatbots, like Anthropic’s Claude, set up stable democracies
2 months agoThe experiment saw other AI chatbots, like Anthropic’s Claude, set up stable democracies
2 months ago
Visa expands cybersecurity support for clients and the payments industry amid AI-era threats
Visa is expanding its cybersecurity support for clients and the wider payments industry as organisations adapt to an “AI...
Bluesky introduces an algorithmic opt-out to reduce users’ viral reach
Bluesky adds an “algorithmic opt-out” feature that lets users avoid being included in the platform’s algorithmic recomme...
Fitbit Air launches Pokémon Sleep special edition with Pikachu strap and sleep-to-game integration
Fitbit launches a Fitbit Air Special Edition designed to work with the Pokémon Sleep app, pairing overnight sleep tracki...