|
|
|
|
|
|
by visarga
501 days ago
|
|
|
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. |
|
|