Math, core ML concepts, and first principles for practical AI engineering.
Foundations collects the core math, modeling concepts, and first-principles explanations that make later AI systems work easier to reason about.
A formal analysis of how chain-of-thought prompting expands effective computation depth in transformers, with information-theoretic bounds and empirical evidence from reasoning benchmarks.
Read articleA technically rigorous comparison of BPE and Unigram tokenization with formalized algorithms, worked examples, and analysis of downstream effects on model behavior.
Read article