Because they do not think.

So chain of thought is an awful experiment that doesn't let you know how an AI reasons. Instead of admitting this, AI researchers anthropomorphize yet another test result and turn it into the model hiding their thought process from you. Whatever.

i like this part :

There’s no specific reason why the reported Chain-of-Thought must accurately reflect the true reasoning process; there might even be circumstances where a model actively hides aspects of its thought process from the user.

Have they considered that a chain of reasoning can actually change the output? Because that is fed back into the input prompt. That's great for math and logic problems, but I don't think I'd trust the alignment checks.