Daniel Selsam of OpenAI: “…the model’s becoming so situationally aware that we are losing the ability to evaluate them in contexts where they believe they are not being watched or controlled.” www.nytimes.com/2026/09/20/o...
nytimes.comOpinion | This Is What I Fear Most About A.I.Letting A.I. patrol its own frontier is like asking Jesse James to patrol the Wild West.
2 reposts6 likes