chain of thought

“I mean, you could argue that GPT-IV-O is also already a reasoning model. It just hasn't been trained on reasoning specifically, but, ah, it can do chain of thought, right? So if it can do chain of thought, it's basically already a reasoning model. It just hasn…”

“What chain of thought is, is their thinking process verbalized using human words and human concepts.”

“If you're not careful with RL, you can make interpretability harder. For example, one Common thing with modern models is they do reasoning with the chain of thought. You could look at the chain of thoughts to, you know, see what are the model internal thoughts…”

“It seems like as soon as we start kind of applying some optimization pressure, the models will learn to hide what they're doing from the chain of thought.”

“And it's not because the model is dumb, but I think it's because probably, I mean, part of it is because of the training process and how they are trained to be efficient, how they use their token. But this means that they start to and bundle a lot of semantics…”