Openai cookbook : GPT-3 , Text writing examples

오늘 다룰 내용 원본은 아래 페이지입니다.

 

https://github.com/openai/openai-cookbook/blob/main/text_writing_examples.md

GitHub - openai/openai-cookbook: Examples and guides for using the OpenAI API

Text writing examples

Large language 모델들은 writing에 아주 탁월합니다. 그들은 모든 종류의 작업을 지원할 수 있습니다.

 

• Blog posts
• Email copy
• Ad copy
• Website copy
• Product descriptions
• Memos
• Storytelling
• Brainstorming
• Question generation
• etc.

GPT-3에서 prompt 하는 가장 쉬운 방법은 여러분이 하고 싶은 말을 하는 것입니다. 예를 들어 여러분이 이메일을 쓰기를 원한다면 아래와 같이 프롬프트를 사용할 수 있습니다.

Write an email to a colleague named Jill congratulating her on her promotion. The tone should be warm yet professional. Mention how you admire the work she's been putting in.  Include a joke about how her pet lizard Max enjoys eating grasshoppers. Mention how you're looking forward to the team off-site next week.

Output:

Subject: Congratulations on Your Promotion, Jill!

Dear Jill,

Congratulations on your promotion! I'm so proud of you and all the hard work you've been putting in. It's been inspiring to watch you grow in your career.

I'm sure Max the lizard is also celebrating with you. I hear he loves eating grasshoppers, so you should treat him to a special snack!

I'm looking forward to seeing you at the team off-site next week. I'm sure it will be a great opportunity to celebrate your success.

All the best,

[Your Name]

일반적으로 writing은 어떤 스타일의 prompt에도 작동합니다. 그것이 어떤 지시 (instruction)이든 따라야 할 일련의 예제들이든 관계 없이 작동합니다. 여러분이 하고 싶은 것을 실현하기 위해 가장 잘 작동 시킬 수 있는 방법은 무엇인지 직접 실험 해 보세요.

 

Writing은 또한 모든 유형의 모델들과 같이 작동할 수 있지만 각각 장 단점이 있습니다.

 

AdvantagesDisadvantages

Instruction-following models (e.g., text-davinci-003)	Easiest to use	Less diverse; less creative; sometimes harder to steer tone, style, etc.
Base models (e.g., davinci)	Potentially more creative and diverse	Harder to prompt well, more expensive (as examples in the prompt cost extra tokens)
Fine-tuned models	Can train off of many examples; cheaper than including examples in the prompt	Hard to gather training data; training makes iteration slower and more expensive