OpenAI’s GPT-3 model, including the ChatGPT API, doesn’t provide direct built-in filters for output, as the level of content moderation needed can largely vary based on the applications built using the API.
However, users can add a moderation layer to the outputs of the ChatGPT API to prevent content that violates OpenAI’s usage policies from being shown. OpenAI provides a moderation guide that gives valuable insights on how to implement such a layer.
Please ensure to thoroughly review and comply with OpenAI’s use case policy before starting implementations.
