Comment by nathan_compton

I'd put it this way: LLMs may reason in the sense that sampling from the distribution of human generated text sometimes reproduces chains of thought that are valid, but this kind of changed sampling is the only compelling model of how they might reason (in my opinion). There might be some kind of "reasoning" in the weights and activations but by construction this is a single pass, feed forward, process calculating outputs from inputs, so if there is reasoning there, it can only be a approximately a single step.