AI

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. ...

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: ...

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. ...

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. ...

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. ...