Max Woolf's Blog

Can modern LLMs actually count the number of b's in "blueberry"?

LLMs can now identify public figures in images

Predicting Average IMDb Movie Ratings Using Text Embeddings of Movie Metadata

As an Experienced LLM User, I Actually Don't Use Generative LLMs Often

The Best Way to Use Text Embeddings Portably is With Parquet and Polars

Can LLMs write better code if you keep asking them to “write better code”?

Generating Distinct AI Voice Performances By Prompt Engineering GPT-4o

AI Seinfeld was the peak of AI-generated content. It will never happen again.

The Super Effectiveness of Pokémon Embeddings Using Only Raw JSON and Images

Does Offering ChatGPT a Tip Cause it to Generate Better Text? An Analysis