[ad_1]
\n<\/p>\n
We are introducing a new and improved content moderation tool: The Moderation endpoint<\/a> improves upon our previous content filter, and is available for free today to OpenAI API developers.<\/p>\n<\/div>\n To help developers protect their applications against possible misuse, we are introducing the faster and more accurate Moderation endpoint<\/a>. This endpoint provides OpenAI API developers with free access to GPT-based<\/a> classifiers that detect undesired content\u2014an instance of using AI systems<\/a> to assist with human supervision of these systems. We have also released both a technical paper<\/a> describing our methodology and the dataset<\/a> used for evaluation.<\/p>\n When given a text input, the Moderation endpoint assesses whether the content is sexual, hateful, violent, or promotes self-harm\u2014content prohibited by our content policy<\/a>. The endpoint has been trained to be quick, accurate, and to perform robustly across a range of applications. Importantly, this reduces the chances of products \u201csaying\u201d the wrong thing, even when deployed to users at-scale. As a consequence, AI can unlock benefits in sensitive settings, like education, where it could not otherwise be used with confidence.<\/p>\n Violence<\/p>\n Self-harm<\/p>\n Hate<\/p>\n Sexual<\/p>\n<\/p><\/div>\n Moderation endpoint<\/span>\n <\/div>\n