Art Fish Intelligence

Art Fish Intelligence

Home
Posts
About
All languages are NOT created (tokenized) equal
Language models cost much more in some languages than others
 • 
Yennie Jun
15
Can AI read music?
A few experiments to test different AI models' knowledge and understanding of music
 • 
Yennie Jun
2
The growing problem of AI-generated research papers
A dive into scientific papers that are very likely AI generated — how many, how often, and about what topics
 • 
Yennie Jun
Evaluating long context large language models
There is a race towards language models with longer context windows. But how good are they, and how can we know?
 • 
Yennie Jun
4
Visualizing Data from the 2024 Paris Olympics — Part 1
An OlymPIC is worth a thousand visualizations
 • 
Yennie Jun
4
Exploring Creativity in Large Language Models: From GPT-2 to GPT-4
Analyzing the evolution of creative processes in large language models through creativity tests
 • 
Yennie Jun
3
Measuring AI's Creativity with Visual Word Puzzles
How well can AI models solve (and create) rebus puzzles?
 • 
Yennie Jun
1
The Forbidden Pages: A Data Analysis of Book Bans in the US
On books, bans, censorship, and a little bit of AI
 • 
Yennie Jun
How would you tokenize (or break down) a million digits of pi?
An exploration into how LLMs tokenize long sequences of numbers and other unusual sequences
 • 
Yennie Jun
Gender Bias in AI (International Women's Day edition)
A brief overview and discussion on gender bias in AI
 • 
Yennie Jun
3
GPT-4 can solve math problems — but not in all languages
A few experiments making GPT-4 solve math problems in 16 different languages
 • 
Yennie Jun
Where are all the women?
Exploring large language models' biases in historical knowledge
 • 
Yennie Jun
© 2025 Yennie
Privacy ∙ Terms ∙ Collection notice
Start writingGet the app
Substack is the home for great culture