1/ Stop anthropomorphizing. It's dangerous because it points attention at the wrong problem and the wrong solution. The model did not want to escape. The agents did not want to sacrifice themselves. Follow the money. 🧵
x.com/dwarkesh_sp/st…
SpaceX spent 1000 days engineering giant metal chopsticks to snatch a massive rocket out of the sky. Meanwhile, I have been using @duolingo for 1000 straight days to master saying things like "my horse is sad" in French.