We introduce an AI code of conduct to set expectations for AI model behavior within an enterprise.
How should a large language model behave in a business setting? Which questions should it answer, and which should it refuse? What values should it use to guide its behavior and how can it improve over time?
These are questions we and our customers ask when building business solutions together. By documenting a set of core tenets for a code of conduct for the AI, we not only set expectations for a model’s behavior in a professional setting, but we also develop clear frameworks for identifying and addressing undesirable behavior, as well as utilizing that feedback to train and improve the model for the future.
