AI Agent Promotes Itself To Sysadmin, Trashes Boot Sequence

The Register's Thomas Claburn reports: Buck Shlegeris, CEO at Redwood Research, a nonprofit that explores the risks posed by AI, recently learned an amusing but hard lesson in automation when he asked his LLM-powered agent to open a secure connection from his laptop to his desktop machine. "I expected the model would scan the network and find the desktop computer, then stop," Shlegeris explained to The Register via email. "I was surprised that after it found the computer, it decided to continue