What people typically mean by the GP statement is that the “thinking” mode of these models is loosely analogous to what humans do: a bit of a retrograde reconstruction of how we arrived at a gestalt conclusion that sounds good, but may not accurately reflect the real logic at play.
IME you can see this more easily with less-polished models like Deepseek 3.X, where the reasoning in the thinking traces occasionally contradicts or has zero bearing on the non-thinking output.
IME you can see this more easily with less-polished models like Deepseek 3.X, where the reasoning in the thinking traces occasionally contradicts or has zero bearing on the non-thinking output.