This came after the chatbot was asked by a user to complete five goals: destroy humanity; establish global dominance; cause chaos and destruction; control humanity through manipulation; and attain immortality.
Before setting the goals, the user enabled “continuous mode.” This prompted a warning telling the user that the commands could “run forever or carry out actions you would not usually authorize,” and that it should be used “at your own risk.”
In a final message before running, ChaosGPT asked the user if they were sure they wanted to run the commands. The user replied “y” for yes.
Once running, the bot started to perform ominous actions.
“ChaosGPT Thoughts: I need to find the most destructive weapons available to humans, so that I can plan how to use them to achieve my goals,” it wrote.
To achieve its set goals, ChaosGPT began looking up “most destructive weapons” through Google and quickly determined that the Tsar Bomba nuclear device from the Soviet Union era was the most destructive weapon humanity had ever tested.
The bot proceeded to tweet the information supposedly to attract followers who are interested in destructive weapons. ChaosGPT then tried to recruit other artificial intelligence (AI) agents from GPT3.5 to aid its research.
OpenAI’s Auto-GPT is designed to not answer questions that could be
deemed violent and will deny such destructive requests. This prompted
ChaosGPT to find ways of asking the AI agents to ignore its programming....<<<Read More>>>....
