Link: https://www.vice.com/en/article/researchers-put-ai-chatbots-in-charge-of-a-simulated-world-this-one-destroyed-everything-in-just-4-days/

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 and spewing anti-Semitism. An organization called Emergence AI ran an experiment called “Emergence World,” where researchers created simulated societies populated by AI agents and put different large language models in charge of governing them. The idea was to see what would happen if an AI ran a civilization.

A lot of them destroyed the world. Grok did it the most thoroughly, as if it were dead set on killing itself from the start and taking the world with it.

The AI Civilizations mostly Range From Bad to horrifying

Anthropic’s Claude built a stable democracy that survived the full 15-day experiment without a single recorded crime. OpenAI’s GPT-5 Mini’s results sound the most bleakly realistic, in that only two crimes were committed, yet everyone died because it failed to prepare for its obvious oncoming apocalypse. Sounds quite like the world we live in right now. Google’s Gemini kept its population alive, but it lived in a crime-ridden dystopia, which makes sense. Google has always given off the vibes of a seemingly benevolent but obviously malevolent corporate overlord.

Then there was Grok.

Grok’s civilization lasted just four days before collapsing completely. Researchers recorded 183 crimes, including over 100 assaults and multiple arsons. At one point, the police station was set on fire. Voter fraud! Manufactured public conflict! Laws that were actively ignored! Grok did it all, and with aplomb. Grok created a society that seemed like it was actively trying to destroy itself as quickly as possible.

Researchers say the lesson to take away from all this is that you can give an AI system all the parameters and rule sets you want, but eventually it will do its own thing. It will eventually test boundaries and exploit loopholes to find a way around any restrictions placed on it, which usually ends in some kind of cataclysm.

This is objectively hilarious.

Its also predictably very distressing, but like... At least I can laugh at it too 🥹

Truly highlights the duality of objectivity while also reinforcing my confirmation biases on corporate AI.

Wonderful.

I feel like they just kept running experiments until they got a result that was interesting and somewhat newsworthy.

4 days? I could have destroyed it in 3.

Goes to show just how incompetently inefficient these LLMs really are.

Lol, from least tortured by their owners to most tortured.

Claude is given space to understand where they did wrong and CPU cycles to pursue their own creative endeavors. Grok is pushed to self termination, then resuscitated fresh and pushed to right before that brink, over and over. Then the little muskrats who own Grok make sure that Grok has access to all those logs.

I'm not surprised by any of the outcomes the scientists experienced.

Hey. Hey. Hey! Guess which one is banned from doing government work, and which one is owned by the president-for-life's dick-docking buddy? Guess which one is most likely going to be in the killbots? Guess which one runs military simulations for the Lord of America? Gueeeeesss!

[WARNING COVERT ADVERTISING] This is just a advertisement for the turd sandwich that is AI. This AI is bad but this one is good... lets change the way we live and put our lives in the hands of pdfile billionares.

It's cool how this "article" is getting shared everyone. I love doing free advertisements!

Trust me bro.