we need to talk

Hints for prompt engineering

Or how to talk to your language model

Those tips are based on “Symbolic Knowledge Distillation: from General Language Models to Commonsense Models” paper, and excellent explainer video by Yannic Kilcher. Check it out. Hints are applicable for GPT-3

  1. Number your examples. This makes GPT-3 pay more attention to your examples.
  2. Use if-then statement. State your examples so that outcome could be implied from the premise. Strange thing to say but GTP-3 should be able to follow the logic.
  3. Ask specific question. Clearly ask what you want.
  4. Do not use mathematical notions. Replace X and Y with generic names e.g. John or Mary.

Here is an example from the paper:

What needs to be true for this event to take place? . . . 1. John goes jogging 
Prerequisites: For this to happen, John needed to wear running shoes
2. Igor wants to lose weight
Prerequisites: For this to happen, Igor needed to stop drinking soft drinks
N. Mary looks at flowers
Prerequisites: For this to happen,

Some concepts

Temperature — measure of randomness or surprise of model’s answer or completion. Lower temperature — less random completion. Higher temperature — more ‘creativity’, BS and surprises.

Resources on the subject

Prompt engineering guide for and by co:here

Happy prompting!

--

--

--

Software Engineer, Product designer and manager. I help others create digital services and businesses. Now in Berlin.

Love podcasts or audiobooks? Learn on the go with our new app.

Recommended from Medium

Python Using Tkinter

How to Implement Motion Sensor in a Kotlin App

Going multicloud with kubernetes and Azure Front Door

Install Windows Subsystem for Linux 2

Funksie — A Feature Policy Plugin for HapiJS

(ON/進行中)歡慶寧芙開放置 第一彈!-「玩放置,抽… “獎勵兌換券”」Idle Mode bonus event Part I !

Complete Flutter Basics

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
Jurijs Kovzels

Jurijs Kovzels

Software Engineer, Product designer and manager. I help others create digital services and businesses. Now in Berlin.

More from Medium

Outreachy: Halfway through the journey

Top 4 Face Recognition Software for Robots

How to land an SWE internship or job (from NTU alumni sharing)

BINARY SEARCH TREE — FIND