Comment by andy_ppp 5 hours ago Shorter is better. This can be applied to human communication too. 1 comment andy_ppp Reply YuechenLi 5 hours ago Not always. If an instruction is short and vague, then LLMs tend to fill in the blanks by guessing and the results are unpredictable. Semantic density is the key, prompts/instructions should be actionable and unambiguous over being terse and vague.So, it's more about being concise.
YuechenLi 5 hours ago Not always. If an instruction is short and vague, then LLMs tend to fill in the blanks by guessing and the results are unpredictable. Semantic density is the key, prompts/instructions should be actionable and unambiguous over being terse and vague.So, it's more about being concise.
Not always. If an instruction is short and vague, then LLMs tend to fill in the blanks by guessing and the results are unpredictable. Semantic density is the key, prompts/instructions should be actionable and unambiguous over being terse and vague.
So, it's more about being concise.