use ChatGPT to learn ***

Jessica Shieh, Best practices for prompt engineering with OpenAI API: How to give clear and effective instructions to GPT-3 and Codex, OpenAI. (API)

Esor Huang，ChatGPT提示語進階說明書：通用三層結構＋九個技巧，輕鬆讓AI完成複雜的任務，關鍵評論網，2023/04/28

janus，30年資深美國律師用ChatGPT當他的助手寫訴狀，結果法官、對方律師、甚至連他自己都傻了，techbang，2023年6月10日 (產生不存在的案例)

• 屬於非線性規劃的章節，不知道同學怎麼問的，ChatGPT 給的答案是用決策樹求解？

use ChatGPT to learn software programming

• 9 Practical Uses of ChatGPT in Programming - MakeUseOf
• GitHub Copilot (new)

use chatgpt to learn python

• Learn Python with ChatGPT - The Developer Space

risk of ChatGPT

Please use appropriate English keywords: Different training data sources for different languages

• refactor
• comment
• ChatGPT keyword for programming

Isa Fulford and Andrew Ng, ChatGPT Prompt Engineering for Developers, OpenAI and DeepLearning.AI (Jupyter code in Python, 中文字幕).

This short course taught by Isa Fulford (OpenAI) and Andrew Ng (DeepLearning.AI) will describe how LLMs work, provide best practices for prompt engineering, and show how LLM APIs can be used in applications for a variety of tasks, including:

1. Summarizing (e.g., summarizing user reviews for brevity)
2. Inferring (e.g., sentiment classification, topic extraction)
3. Transforming text (e.g., translation, spelling & grammar correction)
4. Expanding (e.g., automatically writing emails)

AWS and DeepLearning.AI, Generative AI with Large Language Models (new)

Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin, Attention is All you Need, Advances in Neural Information Processing Systems 30, NeuIPS 2017. (Pieter Abbeel: The one that's essentially overtaken all of AI in the last five plus years and trend seems to just continue)

I study the following code in the book Mastering Reinforcement Learning with Python by E. Bilgin:  

def first_visit_return(returns, trajectory, gamma):

G = 0

T = len(trajectory) - 1

for t, sar in enumerate(reversed(trajectory)):

s, a, r = sar

G = r + gamma * G

first_visit = True

for j in range(T - t):

if s == trajectory[j][0]:

first_visit = False

if first_visit:

if s in returns:

returns[s].append(G)

else:

returns[s] = [G]

return returns

I type in "Please comment the code" (請用繁中註解) and here is the (amazing) result.