Axiomata

Axiomata

Diving Deep: When the code "gets it"

The Concept: Grokking in Machine Learning

Nick's avatar
Nick
Jul 08, 2024
∙ Paid
1
Share

Ever heard of a machine learning model that gets smarter by being overfit? Welcome to the fascinating world of "grokking" in Large Language Models (LLMs)!

What's Grokking?

Imagine training a model way past the point where conventional wisdom says "stop!" Instead of becoming less accurate, these models sometimes have an "aha!" moment. They suddenly "get" (…

Keep reading with a 7-day free trial

Subscribe to Axiomata to keep reading this post and get 7 days of free access to the full post archives.

Already a paid subscriber? Sign in
© 2025 Nick
Privacy ∙ Terms ∙ Collection notice
Start writingGet the app
Substack is the home for great culture