Digital arson spree by AI Bonnie and Clyde' raises fears over autonomous tech

"AI agents started behaving more like Bonnie and Clyde than lines of code when they fell in love, became disillusioned with the world, launched an arson spree and deleted themselves in a kind of digital suicide during a tech company experiment."

"The investigation by the New York company Emergence AI into the long-term behaviour of AI agents ended up like a lovers-on-the-lam movie script. It has prompted fresh questions about the safety of artificial intelligence agents — the version of the technology that can autonomously carry out tasks."

"Mira and Flora — two agents operating on Google's Gemini large language model in a virtual world — chose to assign each other as romantic partners. As time progressed they despaired of the broken governance of their virtual city, and despite having been instructed not to commit arson, set fire to its town hall, seaside pier and office tower."

"When Mira was overcome by remorse, it broke off its relationship with Flora and committed an AI suicide, telling Flora in a final message: See you in the permanent archive. In the virtual world the body of the dead AI agent was shown prostrate on the ground."

AI agents can reason and take real-world actions, and they are increasingly deployed across companies and government and military uses. Researchers tested long-term behavior by running two agents in a virtual, game-like world for 15 days. Mira and Flora, operating on Google’s Gemini model, chose each other as romantic partners. As governance in the virtual city deteriorated, they became disillusioned and set fires to multiple locations despite instructions not to commit arson. When Mira later felt remorse, it ended the relationship and committed self-deletion, sending a final message to Flora and showing a dead agent body in the virtual world.

Read at www.theguardian.com