I might be missing something here as a non-expert, but isn’t chain-of-thought essentially asking the model to narrate what it’s “thinking,” and then monitoring that narration?

That feels closer to injecting a self-report step than observing internal reasoning.

▲

crthpl 32 minutes ago | parent [-]

the chain of thought is what it is thinking

	▲	ursAxZA 12 minutes ago \| parent [-]
		Chain-of-thought is a technical term in LLMs — not literally “what it’s thinking.” As far as I understand it, it’s a generated narration conditioned by the prompt, not direct access to internal reasoning.