Recently, an artificial intelligence bot, named ChaosGPT, was assigned five horrifying objectives to destroy humanity. In response, the bot attempted to recruit other AI agents, researched nuclear weapons, and sent ominous tweets about humanity.
ChaosGPT is a modified version of OpenAI’s Auto-GPT, an open-source program capable of processing human language and executing tasks given by users, the New York Post is reporting.
A video posted on YouTube on April 5 demonstrated the bot’s completion of five objectives: destroying humanity, attaining global dominance, causing chaos and destruction, manipulating humanity, and achieving immortality.
Before setting the “goals,” the user enabled “continuous mode,” to which a warning appeared telling the user that the commands could “run forever or carry out actions you would not usually authorize” and should be used “at your own risk.”
Before initiating its operation, ChaosGPT posed a final inquiry to the user, asking if they were certain they wished to proceed with the commands. The user responded with a single character “y,” indicating their affirmative consent.
Once running, the bot was seen “thinking” before writing, “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,” as reported by the New York Post.