161
overfitting
The model memorized the training rows. It looks brilliant on them and wrong on the next ones.
What is overfitting?
Overfitting is low error on the data the model trained on and high error on data it did not. The gap is the signal. A bigger model and more epochs make the gap easier to open. Regularization, early stopping, and a held-out set are how you see it.
Why does overfitting matter when vibe coding?
Models train until training loss is ~0 and ship it. They report that number as accuracy. Name the holdout before training starts.
How do you do overfitting?
Split first. Never train on the test set. Plot both curves. Stop when validation error rises. Do not tune on the test set either — that is a second kind of fit.
How do you ask a model for overfitting?
Guard against overfitting. Hold out a test set before training and do not touch it while tuning. Report validation error, not only training error. Stop when validation gets worse.
What goes wrong with overfitting?
A random split that puts the same user in train and test. The model memorized the user. Split by user or time.