Gemini 2.0 Thinking

I recently learned, from the ever-illuminating Simon Willison, that Google has released a new model, gemini-2-0-flash-thinking-exp. So, naturally, I posed it a question, a little puzzle if you will. Given the following conditions, how many ways can Professor Y assign six different books to four different students? The most expensive book must be assigned to student X. Each student must receive at least one book. It took the model some time, a moment of digital contemplation, to complete the task. But it did, correctly yielding the answer 390. So now, alongside gpt-o1, we have another model capable of solving this combinatorial problem, a problem that, it must be said, eludes most of my students. It seems that these “inference scaling” based models will be able to solve more such problems, each one a small victory for the silicon mind. Another reason, perhaps, why I no longer set homework and only give quizzes, a small act of surrender in the face of the inevitable. ...

December 20, 2024 · 1 min · Xing Shi Cai

The Mercy of Gods by James S.A. Corey

I just finished The Mercy of Gods by James S.A. Corey, best known for the Expanse series. It’s a space opera about a team of top biologists who find themselves taken captive by brutal alien invaders. Forced into servitude, they must decide how to navigate life under these new, hostile conditions. The setup is rich with tension and moral dilemmas. The first part of the book reveals certain dynamics in the academic world — competition for discoveries, power plays, and the undercurrent of personal ambitions. Even in pursuit of something noble, like advancing knowledge, human frailties often take centre stage. ...

December 18, 2024 · 2 min · Xing Shi Cai

Factory Farming as a Pressing World Problem by Benjamin Hilton

🙏 Acknowledgement I recently came across a thought-provoking post by Benjamin Hilton of 80,000 Hours on the Effective Altruism Forum. The post provides a detailed overview of the immense harm caused by factory farming. Below is an excerpt highlighting some of the most shocking facts about the industry. For detailed references, please refer to the original article. This excerpt is also posed on Plant Futures DKU’s website. A pig confined to a pen. Photo by Matthias Zomer on Pexels. ...

December 6, 2024 · 16 min · Xing Shi Cai

We Can Stop the First Great Extermination by George Monbiot

🙏 Acknowledgement This essay by George Monbiot, a columnist for The Guardian, is part of his book This Can’t Be Happening, a collection of his writings on environmental issues. We are grateful to Monbiot for allowing us to translate it to Chinese and republish his essay here. Desolate landscape of grazing sheep We Can Stop the First Great Extermination George Monbiot October 2019 The Launch of Animal Rebellion, Smithfield Market, London ...

November 27, 2024 · 8 min · Xing Shi Cai
Will can AI do for us today?

What Can AI Do?

I planned to give a talk on AI’s application at a local cafe. Unfortunately there was not a single one who signed up. In order to not to waste my entire effort in preparing for the talk, I translated my slides into a blog post. You can check out my original slides (in Chinese) here. 😨 Will AI Threaten Humanity? 🤖 What is AI? Artificial Intelligence (AI) is a broad term encompassing various technologies. Here are some key areas: ...

November 1, 2024 · 9 min · Xing Shi Cai
Can LLM Write Poems?

LLM and Tang Ying

For some random reason, I decided to test whether ChatGPT and Claude could write poems in an ancient Chinese style. So, I sent Claude 18 poems by Tang Yin (唐寅, 6 March 1470 – 7 January 1524) and asked it to compose three new ones in Tang’s style. The initial results were impressive but sounded a bit modern, so I asked ChatGPT to revise them. Afterward, I gave them back to Claude, asking it to change any words that sounded modern. Below are four poems: one by Tang Yin and three by AI. If you can guess which is which without Googling, I would say you are an expert in ancient Chinese poetry. ...

October 26, 2024 · 1 min · Xing Shi Cai

Using Claude to Visualize Algorithms

I have been trying to use the Large Language Model (LLM) Claude to generate artifacts (apps written in JavaScript and HTML) to visualize algorithms for my COMPSCI 308 course. It works amazingly well. If I had to write them myself, it would have taken hours. It also has the added benefit that I can run them in a browser on my iPad, which I use for teaching. Previously the only way I found to run code on iPad is to use Wolfram Player, which is quite buggy. ...

October 23, 2024 · 1 min · Xing Shi Cai
Can LLM break lines?

Testing using LLM to do automatic line breaks

I have a habit of manually inserting line breaks when I write. Usually, I do this at punctuation marks. When that’s not possible, I try to break at logical points. Since I am experimenting with what LLMs can do, I thought this could be a good test. I tried many models using the same system prompt: Please: - Adjust line breaks so that lines are neither too short nor too long. - Make sure each line has no more than 90 characters. - Preferably, add line breaks after punctuation marks such as periods or commas. - Always start a new line for a new sentence, i.e., after a period that ends a sentence. - If it's not possible to break lines at punctuation marks, break at logical points to maintain readability. - Preserve the original text structure but make the line breaks more readable. - Do not alter the content of the text, only adjust formatting with line breaks. - Return only the text with improved line breaks. Example: Original: The quick brown fox jumps over the lazy dog. The dog, being lazy, does not respond. The journey took about thirty minutes and covered more than five kilometers without stopping. Corrected: The quick brown fox jumps over the lazy dog. The dog, being lazy, does not respond. The journey took about thirty minutes and covered more than five kilometers without stopping. Note that I only tested each model once, so this is not scientific research. ...

October 4, 2024 · 8 min · Xing Shi Cai
Refuse plastic!

No More Plastic: A Journey Towards Sustainability

On April 21, 2024, I organized a book club to discuss the book No. More. Plastic. by Martin Dorey. To prepare for the event, I spent quite some time drafting a slide deck. Now I have translated the slides into Chinese. You can download the slides here: English Version Chinese Version Summary of My Slides A Book Recommendation Martin Dorey, an author, surfer, swimmer, cyclist, and environmentalist, wrote the book “No More Plastic.” He was inspired to take action after discovering an area knee-deep in plastic bottles during his move to a quiet beach in 2009. His book aims to raise awareness about the plastic pollution crisis. ...

May 31, 2024 · 3 min · Xing Shi Cai

Books That Got Me Interested in Math

I always feel that I became a mathematician accidentally. But in retrospect, since I was a kid, I did read serial books about mathematics and mathematicians and has always been drawn to a career and life in mathematics. Below are the books which ignore my interest. Nature’s Numbers: The Unreal Reality Of Mathematics Nature’s Numbers This book by Ian Stewart has some interesting facts about the nature of mathematics. It has been decades since I read it, but I still remember that I was awe-filled when I learned form the book that Fibonacci sequences appear the arrangement of a pine cone. ...

October 17, 2023 · 1 min · Xing Shi Cai