It lets engineers moderate text and images with a single small model by simply writing new policies in plain language at inferenceRunning a trained model to get answers — the phase where AI is actually used, as opposed to trained.Full definition → time, instead of retraining or maintaining separate classifiers for each harm taxonomy.
Terms in this piece · Glossary
multimodal — A model that works with more than text — reading images, audio, or video, and sometimes generating them too.
inference — Running a trained model to get answers — the phase where AI is actually used, as opposed to trained.
