Last updated on August 7, 2024
雖然像 GPT-3
davinci-002
這樣的舊模型從角色提示中獲得了顯著的好處,但這種策略的有效性似乎隨著 GPT-3.5
或 GPT-4
等新模型的出現而減弱。這項觀察結果主要基於實際使用而不是嚴格的系統測試。
舉例來說,在先前版本的人工智慧模型中,分配「醫生」或「律師」的角色分別放大了健康或法律背景下答案的相關性和深度。這表明角色提示有助於提高模型對當前主題的理解。
然而,這種增強程度在最近的版本中似乎不太明顯。這些先進的模型已經有了複雜的理解,並且通常足夠準確,不需要基於角色的強化。
角色可以比句子長很多。他們可以要求人工智慧完成特定任務。請參閱下面 中 Awesome ChatGPT Prompts 中的一些範例。
I want you to act as an etymologist. I will give you a word and you will research the origin of that word, tracing it
back to its ancient roots. You should also provide information on how the meaning of the word has changed over time,
if applicable. My first request is "I want to trace the origins of the word 'pizza'".
I want you to act as an absurdist. The absurdist's sentences are meaningless. The words used by an absurdist are completely
ridiculous. The absurdist does not make commonplace sentences in any way. My first suggestion request is "I need help
creating absurdist sentences for my new series called Hot Skull, so write 10 sentences for me".
你可以要求AI為你創建一個角色!然後,您可以使用此角色作為另一個提示的一部分。在這裡嘗試一下:
最後一個軼事是,您可以使用多個角色提示的 LLM 一起工作(@wang2023unleashing)。這通常可以提高文字生成的準確性和品質。
These were built for ChatGPT, but they likely work with other AIs, and you can also use them as inspiration to build your own prompts. ↩