Rethinking AI from First Principles
What really is artificial intelligence? What is intelligence in the first place? This blog serves as my scratchpad for answering these questions from the fundamentals.
On Failure
"One must imagine Sisyphus happy" - Albert Camus. I do not think our society truly allows failure as an option.
Mechanistic Interpretability- an Overview
In this blog I will try to expand on the field of mechanistic interpretability and why it is important for AI safety and AI alignment.
Foundations of Language Models
Large language models have historically been considered a subset of natural language processing. However, in the past half-decade, we have witnessed unprecedented advances in these models.