passdrill
AI & LLM Engineering · Evaluation, Testing & Safety · Card 010/010 easy

A developer building a chat application wants an extra safety layer that classifies both the text a user submits and the text their language model generates, flagging content across categories such as harassment, hate, self-harm, sexual, and violence before either is shown to end users. Referring specifically to OpenAI's Moderation API (the `omni-moderation-latest` model), which statement accurately describes how it is intended to be used?

  1. It replaces the need for the underlying language model to have any safety training of its own, since all content decisions are made entirely by the moderation classifier before generation even begins
  2. It can be called on both standalone user-submitted input and on text generated by a model, returning a flagged status plus per-category violation flags and confidence scores; per OpenAI's own documentation, the underlying model still generates its output normally, and the moderation results are meant to be reviewed before that output is shown to a user or acted on
  3. It can only be used on text a user submits before generation begins, and OpenAI's documentation states it cannot be applied to text a model has already generated
  4. It is a paid, metered endpoint priced per classified token, separate from OpenAI's chat completion pricing, that developers must budget for separately when adding a moderation layer
Next card → Shuffle