We’re introducing a new-and-improved content material moderation instrument: The Moderation endpoint improves upon our earlier content material filter, and is obtainable without spending a dime at present to OpenAI API builders.
To assist builders defend their functions towards potential misuse, we’re introducing the sooner and extra correct Moderation endpoint. This endpoint offers OpenAI API builders with free entry to GPT-based classifiers that detect undesired content material—an occasion of utilizing AI programs to help with human supervision of those programs. We now have additionally launched each a technical paper describing our methodology and the dataset used for analysis.
When given a textual content enter, the Moderation endpoint assesses whether or not the content material is sexual, hateful, violent, or promotes self-harm—content material prohibited by our content material coverage. The endpoint has been skilled to be fast, correct, and to carry out robustly throughout a variety of functions. Importantly, this reduces the probabilities of merchandise “saying” the flawed factor, even when deployed to customers at-scale. As a consequence, AI can unlock advantages in delicate settings, like schooling, the place it couldn’t in any other case be used with confidence.
Violence
Self-harm
Hate
Sexual
Moderation endpoint
The Moderation endpoint helps builders to profit from our infrastructure investments. Relatively than construct and preserve their very own classifiers—an in depth course of, as we doc in our paper—they will as a substitute entry correct classifiers by means of a single API name.
As a part of OpenAI’s dedication to creating the AI ecosystem safer, we’re offering this endpoint to permit free moderation of all OpenAI API-generated content material. As an example, Inworld, an OpenAI API buyer, makes use of the Moderation endpoint to assist their AI-based digital characters stay acceptable for his or her audiences. By leveraging OpenAI’s know-how, Inworld can give attention to their core product: creating memorable characters. We presently don’t help monitoring of third-party visitors.
Get began with the Moderation endpoint by testing the documentation. Extra particulars of the coaching course of and mannequin efficiency can be found in our paper. We now have additionally launched an analysis dataset, that includes Frequent Crawl knowledge labeled inside these classes, which we hope will spur additional analysis on this space.
