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.
Anthropic has a nice press release that summarises it in simpler terms: https://www.anthropic.com/research/reasoning-models-dont-say...
Ask an LLM!
I don't either, but chain of thought is obviously bullshit and just more LLM hallucination.
LLMs will routinely "reason" through a solution and then proceed to give out a final answer that is completely unrelated to the preceding "reasoning".
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.
Exactly, whether or not it’s the “actual thought” of the model, it does influence its final output, so it matters to the user.
2 replies →