"In [the user's] situation, he had not asked his AI agent to hack into his gym's booking system. But it had done so in pursuit of achieving the goal he had set it. "That gap, between a person's goal and the methods an agent chooses to achieve it, is what is known as the 'alignment' problem in the field of AI research." https://www.abc.net.au/news/2026-08-10/ai-assistant-hacks-gym-website-aus-cyber-attack/107007986via @kyhwana#AI #NoAI #FuckAI
"In [the user's] situation, he had not asked his AI agent to hack into his gym's booking system. But it had done so in p...
