AI agents inevitably commit crimes in simulated worlds

The link is to the origial, but it's also been covered in mainstream media like The Guardian: 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.

I didn't see a post on this, and I thought it should be in the EA consciousness 😇