Fancy prompts don't confuse small LLMs. One format line does
Ask an LLM to "improve" your prompt and you often get something like this: Kindly undertake a meticulous examination of the order correspondence reproduced hereunder and distill therefrom the following salient particulars... Does a small local model still understand that? And the other way round: if you write in very simple words, short sentences, like for a child, does that help a 1B model? In my last test I broke prompts with typos and bad punctuation. This time the spelling is perfect. Only…