Look up any term in AI.

Generative Adversarial Network (GAN)

Two networks trained against each other: one invents data, the other judges it. The generator never sees a real example — only the judge's verdict.

Overfitting

Overfitting is when a model memorizes its training data, including the noise, so it scores high on training data but fails on new, unseen data.

Prompt Caching

Repeated prompt prefixes bill at a fraction of the input price. How prefix matching works, what silently breaks it, and where the break-even sits.

Error Handling in AI Systems

Ordinary code fails by raising an exception. A model fails by returning a confident, well-formed, wrong answer that nothing catches. What to do about it.

Watermarking (SynthID)

AI watermarking hides a detectable signal inside model-generated text and images. How SynthID works, its robustness limits, and the EU AI Act rules.

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.