Use LLM (e.g., ChatGPT) to learn *** and its impact

Research

• Dimitris Bertsimas and Georgios Margaritis, Robust and Adaptive Optimization under a Large Language Model Lens, arXiv:2501.00568. 
• Tony Feng et al., Aletheia tackles FirstProof autonomously, arXiv:2602.21201. (Prompt)
• Don Knuth, Claude’s Cycles, Stanford Computer Science Department (28 February 2026; revised 04 March 2026) (Introduction by Valeriy Manokhin) (new)
• Thang Luong and Vahab Mirrokni, Accelerating Mathematical and Scientific Discovery with Gemini Deep Think, Google DeepMind, February 11, 2026.
• David P. Woodruff et al., Accelerating Scientific Research with Gemini: Case Studies and Common Techniques, arXiv:2602.03837. (8.3 Machine Learning Optimization)

Be careful

• 陳曉莉，MIT研究顯示，習慣用 AI 寫文章會讓腦袋變笨，iThome，2025-06-20 (Nataliya Kosmyna, et al., Your Brain on ChatGPT, arXiv:2506.08872)
• Hao-Ping (Hank) Lee et al., The Impact of Generative AI on Critical Thinking: Self-Reported Reductions in Cognitive Effort and Confidence Effects From a Survey of Knowledge Workers, 2025, CHI '25: Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems, Article No.: 1121, Pages 1 - 22. https://doi.org/10.1145/3706598.371377
• Seyed Mahdi Hosseini Maasoum and Guy Lichtinger, Generative AI as Seniority-Biased Technological Change: Evidence from U.S. Résumé and Job Posting Data, SSRN, 11 Nov 2025.
• Nollie Chen, 22%初級職位人間蒸發？哈佛研究揭露 AI 裁員真相 (new)
• 李先泰，AI人才新生存地圖！吳恩達點出「能回答兩件事」的人最貴，會寫程式不再是護身符？，數位時代， 2026.01.15 (吳恩達 Andrew Ng)  
• 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？

Courses and information 

• AWS and DeepLearning.AI, Generative AI with Large Language Models 
• Isa Fulford and Andrew Ng, ChatGPT Prompt Engineering for Developers, OpenAI and DeepLearning.AI (Jupyter code in Python, 中文字幕).
• 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
• Manny Li，Google公布AI提示萬用公式！掌握「21字黃金法則」：先穩80分基本功再求好，bnext，2025.08.05
• Andrew Ng, The Batch (a weekly newsletter from DeepLearning.AI that provides a curated overview of the most significant developments in artificial intelligence. It is designed to help both technical and non-technical readers stay informed about how AI is evolving and its impact on business and society. (new)
• Barbara Oakley, Accelerate Your Learning with ChatGPT, Coursera
• Jessica Shieh, Best practices for prompt engineering with OpenAI API: How to give clear and effective instructions to GPT-3 and Codex, OpenAI. (API)
• 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.