I prefer prose because it has better flow. Usually I have to specify this manually or the LLMs will happily generate bulletpoints and listicles.
More recently I prefer chain-of-thought prose to the final answer. I can trigger it with a prompt even on non-reasoning models and it's usually easier to follow.
More recently I prefer chain-of-thought prose to the final answer. I can trigger it with a prompt even on non-reasoning models and it's usually easier to follow.