It's more hallucination in the sense that all LLM output is hallucination. CoT is not "what the llm is thinking". I think of it as just creating more context/prompt for itself on the fly, so that when it comes up with a final response it has all that reasoning in its context window.

▲

ziofill 7 months ago | parent [-]

Exactly, whether or not it’s the “actual thought” of the model, it does influence its final output, so it matters to the user.

▲

otabdeveloper4 7 months ago | parent [-]

> it does influence its final output

We don't really know that. So far CoT is only used to sell LLMs to the user. (Both figuratively as a neat trick and literally as a way to increase token count.)

	▲	aqfamnzc 6 months ago \| parent [-]
		Not even remotely true. It's part of the context window, so it greatly influences the final output. CoT is tokens generated by the LLM just like normal output.