Why Scaling Works: Inductive Biases vs The Bitter Lesson

OLAP is Dead — Or Is It ?

LLM vs LLM: Codenames Tournament

From Newton to Neural Networks

Expectedly Unexpected: The Mathematical Art of Measuring Surprise

Understanding Positional Embeddings in Transformers: From Absolute to Rotary

User Action Sequence Modeling: From Attention to Transformers and Beyond

VerifAI Project: Open Source Biomedical Question Answering with Verified Answers

Prompt Engineering for Cognitive Flexibility

Exploring Medusa and Multi-Token Prediction