FOUNDATIONS • 35 / 397
Start before LLMs. Understand where AI, ML and neural networks fit.
Overfitting
Overfitting happens when a model learns the training data too specifically and performs worse on new data.
Think of it like
Think of Overfitting as one layer in a very large toolbox: you only need to understand what job that layer performs.
Real life
A phone spam filter, recommendation engine, fraud detector or voice assistant may use Overfitting somewhere inside.
SRE lens
An incident classifier may memorize old wording but fail on new services.
Remember thisOverfitting happens when a model learns the training data too specifically and performs worse on new data.