Lecturer: Jules White, Vanderbilt University (Coursera)
Presenter: Xingyu Xie
原理:预测下一个单词!
Mary Had a Little Lamb 是一首经典童谣,在训练集中 ChatGPT 见过很多遍,所以它学会了这首童谣。告诉它前几个词,它就可以猜出下一个词。
注:所有对话都会被发给 ChatGPT,用来生成回复,比如如果我在前面说了一些中文,再跟它讲“Mary had a little”
Predict not only the next word but a distribution of the next words.
a weak prompt
a strong prompt
General prompts stimulate general responses, and specific prompts stimulate specific responses.
Rather than instructing a task, ChatGPT can directly learn a task (pattern) from examples given in the prompts.
Consider examples from the FlashFill paper, 12/14 are solved at here.
Summarize the task from a few examples in natural language.
A subtle "filter" pattern: if Input1 contains "pictures", output equals input2, otherwise, output is 0.
Summarize the task from a few examples in natural language.
Examples of different formats.
First, teach ChatGPT how to grade a prompt by few-shot examples.
Second, ask ChatGPT to grade a prompt.
让 ChatGPT 来“控制”对话。
Tail for remembering
Define an action "write"
Outline Expansion