Overfitting
When a model learns its training examples too closely, including their noise and quirks, and so performs well on them but poorly on new data. It is why models are always tested on data they have not seen.
Related terms
The mechanism in a transformer that lets the model weigh how relevant each token is to every other token when working …
BackpropagationThe technique that calculates how much each weight in a neural network contributed to an error, working backwards from…
Base modelA model straight out of pretraining, before it has been tuned to follow instructions or hold a conversation. Given a q…
Chain of thoughtStep-by-step reasoning written out before a final answer, either prompted ('think it through step by step') or built i…
ComputeShorthand for the processing power used to train and run AI models, usually on large clusters of specialised chips in …
Constitutional AIA training approach, published by Anthropic in 2022, in which a model critiques and revises its own responses against …
Knowing the word is the easy part
A short assessment scores you across five skill areas and builds a path through 18 modules, skipping whatever you already know. Free, no card.
Find your level