Look up any term in AI.

Catastrophic Forgetting

Why fine-tuning makes a model worse at everything it used to do well — the mechanism inside shared weights, and what each fix actually costs.

Foundation Models

Not a marketing word for a big AI model: a foundation model is trained once on broad data and reused as the base for many downstream tasks.

FLOPs (Floating Point Operations)

The unit AI compute is measured in — how a training run's FLOP budget is counted, why FLOP and FLOPS are not the same, and why regulators use the number.

World Models

A world model learns an environment's dynamics — given a state and an action, predict the next state — letting an agent plan or train in imagination.

Supervised Learning

Training a model on labeled input-output pairs so it learns a mapping it can apply to new, unlabeled inputs.

Principal Component Analysis (PCA)

Principal Component Analysis (PCA) reduces dimensions by projecting data onto orthogonal directions of maximum variance, ranked by the variance each keeps.