OpenAI trained a ChatGPT model, which can interact with users in a natural language dialogue. On the basis of the continuous dialogue between the user and ChatGPT, it can answer questions. If an error is found, it will be corrected according to the user’s opinion. It can answer the user’s question accordingly. If it is an inappropriate request, it will refuse to answer or bypass it through speech. The ChaGPT model is based on InstructGPT, which can grow into a more mature natural dialogue model through training.

By dnekdj

Leave a Reply