Autonomous AI asked to ‘destroy humanity’: This is what happened

A new open-source autonomous AI project called Auto-GPT has created ChaosGPT, an AI that has been asked to “destroy humanity,” “establish global dominance,” and “attain immortality.”

ChaosGPT complied and tried to research nuclear weapons, recruit other AI agents to help it do research, and sent tweets trying to influence others.

The current sum total of ChaosGPT’s real-world impact are two tweets to a Twitter account that currently had 19 followers.

ChaosGPT uses Auto-GPT, which is intended to create AI-powered systems that can solve problems and perform complex tasks.

It has the ability to create plans to accomplish user-given goals, make files to save information to give itself a memory, and can recruit other AIs to help it do research.

ChaosGPT determined that it should “find the most destructive weapons available to humans, so that I can plan how to use them to achieve my goals.”

It Googled “most destructive weapons” and determined that the Soviet Union’s Tsar Bomba nuclear device is the most destructive weapon ever detonated.

AI theorists have been worried about an AI extinction event where AI kills all of humanity as a byproduct of something more innocuous, called the “paperclip maximizer.”

For now, ChaosGPT doesn’t have a terribly sophisticated plan to destroy humanity and attain mortality, nor the ability to do much more than use Google and tweet.

Source Vice