CoT is Not True Reasoning, It Is Just a Tight Constraint to Imitate: A Theory Perspective · HackerPapers discussions

CoT is Not True Reasoning, It Is Just a Tight Constraint to Imitate: A Theory Perspective — mentioned by batshit_beaver

Wed, 06 May 2026 15:42:46 GMT

Examples: https://arxiv.org/html/2506.02878v1 https://arxiv.org/pdf/2508.01191 Anthropic themselves: https://www.anthropic.com/research/reasoning-models-dont-say... They were approaching this from an interpretability standpoint, but the more interesting finding in there is that models come up with an answer that fits their training and context provided. CoT is generated to fit the anticipated answer. In these studies, there are examples of CoT that directly contradicts the response these models ultimately settle on. This is not reasoning. This is pretense.

Paper and discussion history. A mention is not an endorsement.

CoT is Not True Reasoning, It Is Just a Tight Constraint to Imitate: A Theory Perspective — mentioned by xtracto

Sun, 15 Jun 2025 06:09:13 GMT

I think the paper got unwanted attention... for a scientific paper. It's like that old paper about a "gravity shielding" podkelnov rings experiment that got publicized by some UK news paper as "scientists find antigravity" and ended up destroying the Russian author's career. By the way, it seems Appke researchers got inspired by this [1] older chinese paper to get their title. The Chinese author's made a very similar argument, without the experiments. I myself believe Apple experiments are just good curiosities, but don't drive as much of a point as they believe. [1]…

Paper and discussion history. A mention is not an endorsement.