What it is Chain of thought is the visible, step-by-step reasoning a model produces before its final answer. In this channel's material it shows up in two ways: as a prompting technique you ask a model to do, and — more prominently — as a native capability. OpenAI's o1 is described as a genuinely new way to make models better: instead of training on more data or compute, the model is trained to spend more time thinking before answering, using native chain-of-thought reasoning. How it appears in the material - o1 and o1-mini: the chain-of-thought work happens inside the model itself, which is why prompting o1 differs from prompting GPT-4o — you hand it the problem rather than scripting its reasoning. - Chain of thought = step-by-step reasoning before the final answer. - In o1 it is native: the model is trained to think longer, not just prompted to. - That shift changes how you prompt: o1 is not prompted like GPT-4o.