Neural-network interpretability is extremely difficult, making reasoning models' natural-language chain of thought unusually convenient for safety monitoring.

“very clear that we cannot supervise chain of thought because this is this is really a gift like monitor ability for neural nets is extremely hard and here we have a situation where the neural the neural nets are just like flat out reasoning like laying out their thought process in natural language for us to read that is that is like so convenient it was like really the best case scenario for for safety um but if you look at that chain of thought and say oh the model is thinking bad thoughts”