Post by Nabeel S. Qureshi on X
Nabeel S. Qureshi@nabeelqu
XThings like this detract from the credibility of AI safety work, IMO -- it sounds spicy ("o1 tried to escape!!!") but when you dig into the details it's always "we told the robot to act like a sociopath and maximize power, and then it did exactly that".
808 likes35 repliesPosted Dec 5, 2024